Token | fair |
Token ID | 22043 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Chaff | +1.242 |
Snape | +1.192 |
transcripts | +1.170 |
tied | +1.149 |
Porn | +1.141 |
Neg logit contributions | |
ariat | -1.969 |
ombat | -1.380 |
ftime | -1.261 |
adium | -1.249 |
ater | -1.246 |
Token | share |
Token ID | 2648 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
Chaff | +0.710 |
Snape | +0.678 |
transcripts | +0.653 |
tied | +0.641 |
loophole | +0.638 |
Neg logit contributions | |
ariat | -1.593 |
ombat | -1.148 |
borgh | -1.092 |
ater | -1.091 |
ftime | -1.087 |
Token | of |
Token ID | 286 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
ariat | +0.551 |
ombat | +0.404 |
ater | +0.383 |
ftime | +0.380 |
borgh | +0.376 |
Neg logit contributions | |
Chaff | -0.228 |
Snape | -0.219 |
transcripts | -0.210 |
tied | -0.203 |
Misc | -0.202 |
Token | taxes |
Token ID | 5704 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Chaff | +0.259 |
transcripts | +0.250 |
Snape | +0.249 |
Porn | +0.246 |
Misc | +0.239 |
Neg logit contributions | |
ariat | -0.533 |
ombat | -0.381 |
ftime | -0.361 |
ater | -0.357 |
borgh | -0.355 |
Token | ' |
Token ID | 6 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Chaff | +0.945 |
Snape | +0.907 |
tied | +0.873 |
transcripts | +0.868 |
Porn | +0.848 |
Neg logit contributions | |
ariat | -3.222 |
ombat | -2.501 |
IUM | -2.350 |
borgh | -2.297 |
ater | -2.294 |
Token | Former |
Token ID | 14466 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Chaff | +1.800 |
Snape | +1.735 |
transcripts | +1.676 |
tied | +1.640 |
Lynd | +1.639 |
Neg logit contributions | |
ariat | -2.799 |
ombat | -1.957 |
ater | -1.807 |
ftime | -1.795 |
borgh | -1.777 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
Chaff | +3.214 |
Snape | +3.097 |
transcripts | +3.083 |
Misc | +2.944 |
pornographic | +2.912 |
Neg logit contributions | |
ariat | -6.754 |
ombat | -4.908 |
ftime | -4.555 |
alky | -4.541 |
borgh | -4.537 |
Token | campaign |
Token ID | 1923 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Chaff | +2.444 |
transcripts | +2.442 |
Snape | +2.403 |
tied | +2.379 |
tagging | +2.331 |
Neg logit contributions | |
ariat | -4.018 |
ombat | -2.860 |
ftime | -2.642 |
adium | -2.602 |
IUM | -2.583 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
Chaff | +3.012 |
transcripts | +2.933 |
tied | +2.921 |
Snape | +2.846 |
loophole | +2.796 |
Neg logit contributions | |
ariat | -3.735 |
ombat | -2.430 |
ftime | -2.234 |
borgh | -2.214 |
IUM | -2.167 |
Token | : |
Token ID | 25 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Chaff | +2.564 |
Snape | +2.463 |
transcripts | +2.353 |
tied | +2.309 |
loophole | +2.291 |
Neg logit contributions | |
ariat | -4.826 |
ombat | -3.441 |
ftime | -3.269 |
ater | -3.236 |
borgh | -3.221 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Chaff | +2.009 |
Snape | +1.914 |
transcripts | +1.803 |
Misc | +1.755 |
loophole | +1.752 |
Neg logit contributions | |
ariat | -4.582 |
ombat | -3.357 |
ftime | -3.188 |
borgh | -3.156 |
adium | -3.140 |
Token | fair |
Token ID | 22043 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Chaff | +1.296 |
Snape | +1.243 |
transcripts | +1.229 |
tied | +1.211 |
Porn | +1.203 |
Neg logit contributions | |
ariat | -2.022 |
ombat | -1.430 |
ftime | -1.288 |
adium | -1.281 |
borgh | -1.276 |
Token | share |
Token ID | 2648 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Chaff | +0.796 |
Snape | +0.760 |
transcripts | +0.734 |
tied | +0.720 |
loophole | +0.716 |
Neg logit contributions | |
ariat | -1.789 |
ombat | -1.289 |
borgh | -1.226 |
ater | -1.226 |
ftime | -1.220 |
Token | of |
Token ID | 286 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ariat | +0.146 |
ombat | +0.108 |
ater | +0.102 |
ftime | +0.101 |
borgh | +0.100 |
Neg logit contributions | |
Chaff | -0.058 |
Snape | -0.056 |
transcripts | -0.053 |
tied | -0.052 |
Porn | -0.052 |
Token | taxes |
Token ID | 5704 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Chaff | +0.411 |
transcripts | +0.399 |
Snape | +0.397 |
Porn | +0.393 |
Misc | +0.382 |
Neg logit contributions | |
ariat | -0.794 |
ombat | -0.564 |
ftime | -0.529 |
ater | -0.524 |
borgh | -0.522 |
Token | ' |
Token ID | 6 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Chaff | +0.981 |
Snape | +0.941 |
tied | +0.909 |
transcripts | +0.902 |
Disclosure | +0.879 |
Neg logit contributions | |
ariat | -3.360 |
ombat | -2.612 |
IUM | -2.459 |
alky | -2.396 |
ater | -2.392 |
Token | Former |
Token ID | 14466 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Chaff | +1.813 |
Snape | +1.756 |
transcripts | +1.687 |
tied | +1.655 |
Lynd | +1.649 |
Neg logit contributions | |
ariat | -2.837 |
ombat | -1.979 |
ater | -1.834 |
ftime | -1.817 |
borgh | -1.804 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Chaff | +3.144 |
Snape | +3.026 |
transcripts | +2.964 |
Misc | +2.849 |
pornographic | +2.826 |
Neg logit contributions | |
ariat | -6.808 |
ombat | -4.954 |
ftime | -4.623 |
ater | -4.596 |
borgh | -4.591 |
Token | campaign |
Token ID | 1923 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Chaff | +2.168 |
transcripts | +2.154 |
Snape | +2.135 |
tied | +2.103 |
tagging | +2.048 |
Neg logit contributions | |
ariat | -3.481 |
ombat | -2.467 |
ftime | -2.272 |
borgh | -2.236 |
adium | -2.235 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Chaff | +3.202 |
transcripts | +3.134 |
tied | +3.124 |
Snape | +3.023 |
loophole | +2.957 |
Neg logit contributions | |
ariat | -4.006 |
ombat | -2.604 |
borgh | -2.381 |
ftime | -2.379 |
IUM | -2.361 |
Token | : |
Token ID | 25 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
Chaff | +2.539 |
Snape | +2.441 |
transcripts | +2.330 |
tied | +2.294 |
loophole | +2.270 |
Neg logit contributions | |
ariat | -4.729 |
ombat | -3.377 |
ftime | -3.208 |
ater | -3.166 |
borgh | -3.158 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Chaff | +2.071 |
Snape | +1.969 |
transcripts | +1.845 |
Misc | +1.805 |
loophole | +1.804 |
Neg logit contributions | |
ariat | -4.777 |
ombat | -3.514 |
ftime | -3.338 |
borgh | -3.296 |
adium | -3.282 |
Token | fair |
Token ID | 22043 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Chaff | +1.216 |
Snape | +1.166 |
transcripts | +1.143 |
tied | +1.128 |
Porn | +1.119 |
Neg logit contributions | |
ariat | -1.944 |
ombat | -1.372 |
ftime | -1.247 |
adium | -1.239 |
borgh | -1.235 |
Token | share |
Token ID | 2648 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Chaff | +0.644 |
Snape | +0.615 |
transcripts | +0.594 |
tied | +0.582 |
loophole | +0.579 |
Neg logit contributions | |
ariat | -1.442 |
ombat | -1.039 |
borgh | -0.988 |
ater | -0.988 |
ftime | -0.983 |
Token | of |
Token ID | 286 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ariat | +0.353 |
ombat | +0.261 |
ater | +0.247 |
ftime | +0.244 |
borgh | +0.241 |
Neg logit contributions | |
Chaff | -0.140 |
Snape | -0.134 |
transcripts | -0.129 |
Misc | -0.125 |
tied | -0.125 |
Token | taxes |
Token ID | 5704 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Chaff | +0.457 |
transcripts | +0.442 |
Snape | +0.440 |
Porn | +0.437 |
Misc | +0.425 |
Neg logit contributions | |
ariat | -0.867 |
ombat | -0.612 |
ftime | -0.578 |
ater | -0.570 |
borgh | -0.568 |
Token | ' |
Token ID | 6 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Chaff | +1.018 |
Snape | +0.978 |
tied | +0.943 |
transcripts | +0.942 |
Porn | +0.920 |
Neg logit contributions | |
ariat | -3.410 |
ombat | -2.635 |
IUM | -2.487 |
ater | -2.429 |
alky | -2.418 |
Token | Former |
Token ID | 14466 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Chaff | +1.731 |
Snape | +1.677 |
transcripts | +1.611 |
tied | +1.578 |
Lynd | +1.573 |
Neg logit contributions | |
ariat | -2.649 |
ombat | -1.835 |
ater | -1.702 |
ftime | -1.690 |
borgh | -1.676 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Chaff | +3.118 |
Snape | +2.990 |
transcripts | +2.908 |
Misc | +2.806 |
pornographic | +2.787 |
Neg logit contributions | |
ariat | -6.589 |
ombat | -4.766 |
ftime | -4.468 |
ater | -4.445 |
borgh | -4.429 |
Token | campaign |
Token ID | 1923 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
Chaff | +2.051 |
Snape | +2.012 |
transcripts | +2.003 |
tied | +1.958 |
Lynd | +1.914 |
Neg logit contributions | |
ariat | -3.192 |
ombat | -2.230 |
ftime | -2.070 |
borgh | -2.031 |
adium | -2.031 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
Chaff | +2.957 |
transcripts | +2.886 |
tied | +2.870 |
Snape | +2.812 |
loophole | +2.738 |
Neg logit contributions | |
ariat | -3.494 |
ombat | -2.251 |
ftime | -2.057 |
borgh | -2.050 |
IUM | -2.004 |
Token | : |
Token ID | 25 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Chaff | +2.490 |
Snape | +2.397 |
transcripts | +2.291 |
tied | +2.250 |
loophole | +2.231 |
Neg logit contributions | |
ariat | -4.561 |
ombat | -3.238 |
ftime | -3.076 |
ater | -3.043 |
borgh | -3.032 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Chaff | +1.948 |
Snape | +1.859 |
transcripts | +1.754 |
loophole | +1.709 |
Misc | +1.706 |
Neg logit contributions | |
ariat | -4.380 |
ombat | -3.193 |
ftime | -3.032 |
borgh | -3.000 |
ater | -2.996 |
Token | $ |
Token ID | 720 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Chaff | +0.518 |
Snape | +0.493 |
transcripts | +0.465 |
Lynd | +0.463 |
Porn | +0.459 |
Neg logit contributions | |
ariat | -1.214 |
ombat | -0.884 |
ftime | -0.841 |
ater | -0.835 |
adium | -0.831 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Chaff | +1.400 |
Snape | +1.378 |
transcripts | +1.305 |
tags | +1.268 |
Porn | +1.263 |
Neg logit contributions | |
ariat | -4.565 |
ombat | -3.324 |
adium | -3.242 |
ftime | -3.221 |
borgh | -3.182 |
Token | a |
Token ID | 257 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Chaff | +0.621 |
Snape | +0.603 |
transcripts | +0.591 |
tied | +0.577 |
Misc | +0.575 |
Neg logit contributions | |
ariat | -1.013 |
ombat | -0.699 |
ftime | -0.661 |
ater | -0.657 |
borgh | -0.649 |
Token | month |
Token ID | 1227 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Chaff | +1.174 |
Snape | +1.140 |
transcripts | +1.106 |
tied | +1.084 |
loophole | +1.083 |
Neg logit contributions | |
ariat | -1.864 |
ombat | -1.261 |
ftime | -1.196 |
borgh | -1.194 |
ater | -1.192 |
Token | ! |
Token ID | 0 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Chaff | +1.236 |
Snape | +1.198 |
transcripts | +1.176 |
Porn | +1.138 |
Lynd | +1.136 |
Neg logit contributions | |
ariat | -2.076 |
ombat | -1.426 |
ftime | -1.348 |
borgh | -1.338 |
ater | -1.334 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Chaff | +2.306 |
Snape | +2.226 |
Lynd | +2.088 |
Porn | +2.086 |
transcripts | +2.069 |
Neg logit contributions | |
ariat | -5.639 |
ombat | -4.089 |
ftime | -3.994 |
alky | -3.886 |
ater | -3.877 |
Token |
|
Token ID | 198 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Chaff | +2.605 |
Snape | +2.491 |
Porn | +2.314 |
Misc | +2.306 |
Lynd | +2.291 |
Neg logit contributions | |
ariat | -6.573 |
ombat | -4.852 |
ftime | -4.690 |
alky | -4.539 |
ater | -4.513 |
Token | Support |
Token ID | 15514 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Chaff | +2.332 |
Snape | +2.200 |
transcripts | +2.169 |
Statement | +2.147 |
Porn | +2.055 |
Neg logit contributions | |
ariat | -6.161 |
ombat | -4.435 |
ftime | -4.348 |
alky | -4.243 |
ater | -4.210 |
Token | Progressive |
Token ID | 25852 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Chaff | +1.871 |
Snape | +1.801 |
transcripts | +1.731 |
tied | +1.666 |
Misc | +1.665 |
Neg logit contributions | |
ariat | -3.786 |
ombat | -2.708 |
ftime | -2.589 |
ater | -2.575 |
borgh | -2.551 |
Token | Journalism |
Token ID | 37406 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Chaff | +0.661 |
Snape | +0.612 |
transcripts | +0.546 |
Porn | +0.516 |
Disclosure | +0.508 |
Neg logit contributions | |
ariat | -4.388 |
ombat | -3.420 |
ftime | -3.313 |
borgh | -3.273 |
ater | -3.261 |
Token | The |
Token ID | 383 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Chaff | +1.396 |
Snape | +1.328 |
transcripts | +1.246 |
Lynd | +1.224 |
Porn | +1.204 |
Neg logit contributions | |
ariat | -3.805 |
ombat | -2.868 |
ftime | -2.754 |
ater | -2.694 |
borgh | -2.685 |
Token | d |
Token ID | 288 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Chaff | +1.282 |
Snape | +1.232 |
transcripts | +1.166 |
Lynd | +1.157 |
Misc | +1.151 |
Neg logit contributions | |
ariat | -2.333 |
ombat | -1.643 |
ftime | -1.578 |
borgh | -1.543 |
ater | -1.539 |
Token | anc |
Token ID | 1192 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
Chaff | +0.530 |
Snape | +0.518 |
transcripts | +0.493 |
beard | +0.488 |
tied | +0.487 |
Neg logit contributions | |
ariat | -0.812 |
ombat | -0.547 |
ftime | -0.520 |
adium | -0.510 |
borgh | -0.509 |
Token | erg |
Token ID | 6422 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Chaff | +1.208 |
Snape | +1.168 |
transcripts | +1.122 |
tied | +1.112 |
beard | +1.099 |
Neg logit contributions | |
ariat | -1.854 |
ombat | -1.258 |
ftime | -1.201 |
borgh | -1.181 |
adium | -1.172 |
Token | ur |
Token ID | 333 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Chaff | +0.778 |
Snape | +0.756 |
transcripts | +0.728 |
tied | +0.720 |
beard | +0.716 |
Neg logit contributions | |
ariat | -1.193 |
ombat | -0.809 |
ftime | -0.770 |
borgh | -0.754 |
adium | -0.744 |
Token | ly |
Token ID | 306 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
ariat | +2.293 |
ombat | +1.608 |
ftime | +1.518 |
ater | +1.514 |
borgh | +1.502 |
Neg logit contributions | |
Chaff | -1.274 |
Snape | -1.229 |
transcripts | -1.176 |
tied | -1.152 |
loophole | -1.144 |
Token | from |
Token ID | 422 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Chaff | +0.185 |
Snape | +0.178 |
transcripts | +0.170 |
beard | +0.168 |
tied | +0.167 |
Neg logit contributions | |
ariat | -0.356 |
ombat | -0.251 |
ftime | -0.239 |
ater | -0.235 |
borgh | -0.234 |
Token | K |
Token ID | 509 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Chaff | +2.840 |
Snape | +2.697 |
Porn | +2.536 |
transcripts | +2.534 |
tied | +2.532 |
Neg logit contributions | |
ariat | -6.080 |
ombat | -4.321 |
ftime | -4.146 |
adium | -4.077 |
ater | -4.053 |
Token | AAAA |
Token ID | 17922 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Chaff | +0.181 |
Snape | +0.174 |
transcripts | +0.169 |
tied | +0.166 |
Misc | +0.165 |
Neg logit contributions | |
ariat | -0.285 |
ombat | -0.191 |
ftime | -0.183 |
borgh | -0.182 |
ater | -0.180 |
Token | - |
Token ID | 12 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
ariat | +1.149 |
ombat | +0.776 |
ftime | +0.739 |
borgh | +0.729 |
ater | +0.724 |
Neg logit contributions | |
Chaff | -0.748 |
Snape | -0.720 |
transcripts | -0.691 |
Misc | -0.683 |
tied | -0.680 |
Token | B |
Token ID | 33 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Chaff | +0.152 |
Snape | +0.146 |
transcripts | +0.139 |
tied | +0.137 |
Misc | +0.137 |
Neg logit contributions | |
ariat | -0.271 |
ombat | -0.188 |
ftime | -0.179 |
ater | -0.177 |
borgh | -0.177 |
Token | OOOO |
Token ID | 23803 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
Chaff | +0.450 |
Snape | +0.437 |
transcripts | +0.419 |
tied | +0.415 |
Misc | +0.413 |
Neg logit contributions | |
ariat | -0.649 |
ombat | -0.436 |
ftime | -0.416 |
borgh | -0.415 |
adium | -0.407 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ariat | +0.063 |
ombat | +0.044 |
ftime | +0.042 |
borgh | +0.041 |
adium | +0.041 |
Neg logit contributions | |
Chaff | -0.035 |
Snape | -0.034 |
transcripts | -0.033 |
Misc | -0.032 |
tied | -0.032 |
Token | system |
Token ID | 1080 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Chaff | +0.492 |
Snape | +0.476 |
transcripts | +0.454 |
tied | +0.449 |
Misc | +0.442 |
Neg logit contributions | |
ariat | -1.033 |
ombat | -0.726 |
ftime | -0.700 |
ater | -0.691 |
borgh | -0.691 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Chaff | +0.353 |
Snape | +0.342 |
transcripts | +0.328 |
tied | +0.326 |
loophole | +0.320 |
Neg logit contributions | |
ariat | -0.596 |
ombat | -0.411 |
ater | -0.389 |
ftime | -0.388 |
borgh | -0.386 |
Token |
|
Token ID | 198 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Chaff | +0.516 |
Snape | +0.494 |
transcripts | +0.465 |
Porn | +0.456 |
Misc | +0.455 |
Neg logit contributions | |
ariat | -1.204 |
ombat | -0.872 |
ftime | -0.830 |
ater | -0.825 |
adium | -0.818 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Chaff | +1.297 |
Snape | +1.257 |
transcripts | +1.175 |
tied | +1.166 |
Misc | +1.164 |
Neg logit contributions | |
ariat | -2.863 |
ombat | -2.082 |
ftime | -1.995 |
ater | -1.951 |
borgh | -1.942 |
Token | Rated |
Token ID | 15322 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Chaff | +1.252 |
Snape | +1.213 |
transcripts | +1.160 |
tied | +1.150 |
Porn | +1.134 |
Neg logit contributions | |
ariat | -2.141 |
ombat | -1.482 |
ftime | -1.410 |
ater | -1.396 |
borgh | -1.387 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Chaff | +2.571 |
Snape | +2.424 |
transcripts | +2.301 |
tied | +2.294 |
Porn | +2.275 |
Neg logit contributions | |
ariat | -6.340 |
ombat | -4.633 |
borgh | -4.432 |
ftime | -4.419 |
adium | -4.357 |
Token | out |
Token ID | 503 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Chaff | +1.598 |
Snape | +1.553 |
transcripts | +1.486 |
tied | +1.465 |
Misc | +1.451 |
Neg logit contributions | |
ariat | -2.644 |
ombat | -1.845 |
ftime | -1.751 |
ater | -1.721 |
borgh | -1.711 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Chaff | +1.810 |
Snape | +1.759 |
tied | +1.642 |
transcripts | +1.637 |
Misc | +1.631 |
Neg logit contributions | |
ariat | -3.358 |
ombat | -2.399 |
ftime | -2.291 |
ater | -2.248 |
adium | -2.216 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
Chaff | +0.378 |
Snape | +0.364 |
transcripts | +0.348 |
loophole | +0.339 |
tied | +0.338 |
Neg logit contributions | |
ariat | -0.752 |
ombat | -0.535 |
ater | -0.509 |
ftime | -0.506 |
borgh | -0.502 |
Token | by |
Token ID | 416 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Chaff | +1.386 |
Snape | +1.309 |
transcripts | +1.222 |
tied | +1.204 |
Misc | +1.186 |
Neg logit contributions | |
ariat | -4.089 |
ombat | -3.071 |
ftime | -2.942 |
ater | -2.908 |
adium | -2.889 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Chaff | +1.557 |
Snape | +1.516 |
tied | +1.447 |
transcripts | +1.431 |
needing | +1.424 |
Neg logit contributions | |
ariat | -3.282 |
ombat | -2.325 |
borgh | -2.197 |
ftime | -2.174 |
adium | -2.164 |
Token | night |
Token ID | 1755 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Chaff | +0.049 |
Snape | +0.048 |
transcripts | +0.046 |
tied | +0.045 |
Misc | +0.045 |
Neg logit contributions | |
ariat | -0.083 |
ombat | -0.058 |
ftime | -0.054 |
borgh | -0.054 |
adium | -0.054 |
Token | ! |
Token ID | 0 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Chaff | +0.440 |
Snape | +0.427 |
transcripts | +0.408 |
tied | +0.408 |
needing | +0.402 |
Neg logit contributions | |
ariat | -0.767 |
ombat | -0.530 |
borgh | -0.495 |
ater | -0.494 |
ftime | -0.493 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Chaff | +0.653 |
Snape | +0.625 |
transcripts | +0.594 |
Misc | +0.581 |
Porn | +0.580 |
Neg logit contributions | |
ariat | -1.448 |
ombat | -1.039 |
ftime | -0.987 |
ater | -0.983 |
borgh | -0.978 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Chaff | +1.184 |
Snape | +1.145 |
transcripts | +1.072 |
tied | +1.063 |
Misc | +1.061 |
Neg logit contributions | |
ariat | -2.594 |
ombat | -1.886 |
ftime | -1.804 |
ater | -1.766 |
borgh | -1.759 |
Token | Rated |
Token ID | 15322 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Chaff | +1.089 |
Snape | +1.054 |
transcripts | +1.010 |
tied | +1.000 |
Misc | +0.986 |
Neg logit contributions | |
ariat | -1.832 |
ombat | -1.267 |
ftime | -1.203 |
ater | -1.194 |
borgh | -1.184 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Chaff | +2.508 |
Snape | +2.366 |
transcripts | +2.250 |
tied | +2.232 |
Porn | +2.219 |
Neg logit contributions | |
ariat | -6.152 |
ombat | -4.495 |
borgh | -4.296 |
ftime | -4.293 |
adium | -4.226 |
Token | out |
Token ID | 503 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Chaff | +1.426 |
Snape | +1.385 |
transcripts | +1.327 |
tied | +1.307 |
Misc | +1.295 |
Neg logit contributions | |
ariat | -2.335 |
ombat | -1.626 |
ftime | -1.541 |
ater | -1.519 |
borgh | -1.509 |
Token | of |
Token ID | 286 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
Chaff | +1.631 |
Snape | +1.583 |
tied | +1.479 |
transcripts | +1.479 |
Misc | +1.470 |
Neg logit contributions | |
ariat | -2.989 |
ombat | -2.130 |
ftime | -2.032 |
ater | -1.998 |
borgh | -1.969 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Chaff | +0.276 |
Snape | +0.266 |
transcripts | +0.254 |
loophole | +0.247 |
tied | +0.247 |
Neg logit contributions | |
ariat | -0.549 |
ombat | -0.390 |
ater | -0.371 |
ftime | -0.369 |
borgh | -0.366 |
Token | by |
Token ID | 416 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Chaff | +1.317 |
Snape | +1.243 |
transcripts | +1.165 |
tied | +1.146 |
Lynd | +1.128 |
Neg logit contributions | |
ariat | -3.877 |
ombat | -2.909 |
ftime | -2.788 |
ater | -2.756 |
adium | -2.736 |
Token | be |
Token ID | 307 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Chaff | +0.140 |
Snape | +0.135 |
transcripts | +0.128 |
tied | +0.128 |
loophole | +0.126 |
Neg logit contributions | |
ariat | -0.263 |
ombat | -0.186 |
ftime | -0.176 |
adium | -0.175 |
borgh | -0.175 |
Token | significantly |
Token ID | 5566 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Chaff | +0.153 |
Snape | +0.148 |
tied | +0.141 |
transcripts | +0.140 |
loophole | +0.137 |
Neg logit contributions | |
ariat | -0.311 |
ombat | -0.223 |
ftime | -0.211 |
adium | -0.210 |
ater | -0.209 |
Token | later |
Token ID | 1568 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ariat | +0.149 |
ombat | +0.103 |
ftime | +0.097 |
adium | +0.096 |
borgh | +0.096 |
Neg logit contributions | |
Chaff | -0.091 |
Snape | -0.088 |
tied | -0.085 |
transcripts | -0.084 |
loophole | -0.083 |
Token | compared |
Token ID | 3688 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
ariat | +1.028 |
ombat | +0.709 |
ater | +0.670 |
ftime | +0.668 |
borgh | +0.664 |
Neg logit contributions | |
Chaff | -0.619 |
Snape | -0.601 |
transcripts | -0.579 |
tied | -0.569 |
loophole | -0.563 |
Token | to |
Token ID | 284 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
Chaff | +0.022 |
Snape | +0.021 |
transcripts | +0.020 |
tied | +0.020 |
loophole | +0.020 |
Neg logit contributions | |
ariat | -0.043 |
ombat | -0.030 |
ater | -0.029 |
ftime | -0.029 |
borgh | -0.029 |
Token | Q |
Token ID | 1195 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
Chaff | +0.069 |
Snape | +0.067 |
transcripts | +0.063 |
tied | +0.063 |
Porn | +0.062 |
Neg logit contributions | |
ariat | -0.131 |
ombat | -0.092 |
ftime | -0.088 |
adium | -0.087 |
borgh | -0.087 |
Token | W |
Token ID | 54 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
Chaff | +3.010 |
Snape | +2.889 |
transcripts | +2.791 |
tied | +2.789 |
beard | +2.745 |
Neg logit contributions | |
ariat | -5.499 |
ombat | -3.782 |
borgh | -3.649 |
ftime | -3.593 |
adium | -3.588 |
Token | inv |
Token ID | 800 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
Chaff | +0.266 |
Snape | +0.259 |
transcripts | +0.246 |
tied | +0.243 |
loophole | +0.240 |
Neg logit contributions | |
ariat | -0.469 |
ombat | -0.324 |
ftime | -0.307 |
borgh | -0.306 |
adium | -0.305 |
Token | oker |
Token ID | 11020 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ariat | +0.208 |
ombat | +0.137 |
ftime | +0.131 |
borgh | +0.130 |
ater | +0.128 |
Neg logit contributions | |
Chaff | -0.148 |
Snape | -0.147 |
transcripts | -0.140 |
tied | -0.138 |
loophole | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
Chaff | +0.342 |
Snape | +0.333 |
transcripts | +0.320 |
tied | +0.317 |
loophole | +0.313 |
Neg logit contributions | |
ariat | -0.567 |
ombat | -0.392 |
ftime | -0.368 |
ater | -0.368 |
borgh | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
ariat | +0.553 |
ombat | +0.398 |
ftime | +0.379 |
ater | +0.377 |
borgh | +0.375 |
Neg logit contributions | |
Chaff | -0.253 |
Snape | -0.243 |
transcripts | -0.230 |
tied | -0.227 |
loophole | -0.224 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Chaff | +1.400 |
Snape | +1.378 |
transcripts | +1.305 |
tags | +1.268 |
Porn | +1.263 |
Neg logit contributions | |
ariat | -4.565 |
ombat | -3.324 |
adium | -3.242 |
ftime | -3.221 |
borgh | -3.182 |
Token | a |
Token ID | 257 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Chaff | +0.621 |
Snape | +0.603 |
transcripts | +0.591 |
tied | +0.577 |
Misc | +0.575 |
Neg logit contributions | |
ariat | -1.013 |
ombat | -0.699 |
ftime | -0.661 |
ater | -0.657 |
borgh | -0.649 |
Token | month |
Token ID | 1227 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Chaff | +1.174 |
Snape | +1.140 |
transcripts | +1.106 |
tied | +1.084 |
loophole | +1.083 |
Neg logit contributions | |
ariat | -1.864 |
ombat | -1.261 |
ftime | -1.196 |
borgh | -1.194 |
ater | -1.192 |
Token | ! |
Token ID | 0 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Chaff | +1.236 |
Snape | +1.198 |
transcripts | +1.176 |
Porn | +1.138 |
Lynd | +1.136 |
Neg logit contributions | |
ariat | -2.076 |
ombat | -1.426 |
ftime | -1.348 |
borgh | -1.338 |
ater | -1.334 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Chaff | +2.306 |
Snape | +2.226 |
Lynd | +2.088 |
Porn | +2.086 |
transcripts | +2.069 |
Neg logit contributions | |
ariat | -5.639 |
ombat | -4.089 |
ftime | -3.994 |
alky | -3.886 |
ater | -3.877 |
Token |
|
Token ID | 198 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Chaff | +2.605 |
Snape | +2.491 |
Porn | +2.314 |
Misc | +2.306 |
Lynd | +2.291 |
Neg logit contributions | |
ariat | -6.573 |
ombat | -4.852 |
ftime | -4.690 |
alky | -4.539 |
ater | -4.513 |
Token | Support |
Token ID | 15514 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Chaff | +2.332 |
Snape | +2.200 |
transcripts | +2.169 |
Statement | +2.147 |
Porn | +2.055 |
Neg logit contributions | |
ariat | -6.161 |
ombat | -4.435 |
ftime | -4.348 |
alky | -4.243 |
ater | -4.210 |
Token | Progressive |
Token ID | 25852 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Chaff | +1.871 |
Snape | +1.801 |
transcripts | +1.731 |
tied | +1.666 |
Misc | +1.665 |
Neg logit contributions | |
ariat | -3.786 |
ombat | -2.708 |
ftime | -2.589 |
ater | -2.575 |
borgh | -2.551 |
Token | Journalism |
Token ID | 37406 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Chaff | +0.661 |
Snape | +0.612 |
transcripts | +0.546 |
Porn | +0.516 |
Disclosure | +0.508 |
Neg logit contributions | |
ariat | -4.388 |
ombat | -3.420 |
ftime | -3.313 |
borgh | -3.273 |
ater | -3.261 |
Token | The |
Token ID | 383 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Chaff | +1.396 |
Snape | +1.328 |
transcripts | +1.246 |
Lynd | +1.224 |
Porn | +1.204 |
Neg logit contributions | |
ariat | -3.805 |
ombat | -2.868 |
ftime | -2.754 |
ater | -2.694 |
borgh | -2.685 |
Token | Nation |
Token ID | 8741 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Chaff | +1.956 |
Snape | +1.875 |
transcripts | +1.831 |
Lynd | +1.783 |
Porn | +1.783 |
Neg logit contributions | |
ariat | -3.814 |
ombat | -2.673 |
ftime | -2.603 |
borgh | -2.539 |
ater | -2.522 |
Token | ️ |
Token ID | 37929 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ariat | +1.342 |
ombat | +0.964 |
ftime | +0.917 |
ater | +0.915 |
borgh | +0.910 |
Neg logit contributions | |
Chaff | -0.617 |
Snape | -0.590 |
transcripts | -0.559 |
tied | -0.547 |
Misc | -0.543 |
Token | Be |
Token ID | 1355 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Chaff | +0.362 |
Snape | +0.346 |
transcripts | +0.329 |
tied | +0.325 |
Misc | +0.321 |
Neg logit contributions | |
ariat | -0.753 |
ombat | -0.538 |
ftime | -0.512 |
ater | -0.507 |
borgh | -0.506 |
Token | safe |
Token ID | 3338 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Chaff | +0.208 |
Snape | +0.201 |
transcripts | +0.190 |
tied | +0.190 |
poetic | +0.188 |
Neg logit contributions | |
ariat | -0.387 |
ombat | -0.272 |
ftime | -0.259 |
adium | -0.256 |
borgh | -0.255 |
Token | pic |
Token ID | 8301 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ariat | +0.317 |
ombat | +0.223 |
ftime | +0.209 |
ater | +0.209 |
borgh | +0.208 |
Neg logit contributions | |
Chaff | -0.176 |
Snape | -0.169 |
transcripts | -0.161 |
tied | -0.159 |
Lynd | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Chaff | +0.764 |
Snape | +0.738 |
transcripts | +0.705 |
tied | +0.695 |
Misc | +0.694 |
Neg logit contributions | |
ariat | -1.140 |
ombat | -0.783 |
ftime | -0.740 |
ater | -0.727 |
borgh | -0.719 |
Token | twitter |
Token ID | 6956 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
Chaff | +0.306 |
Snape | +0.293 |
transcripts | +0.280 |
tied | +0.275 |
Porn | +0.272 |
Neg logit contributions | |
ariat | -0.649 |
ombat | -0.467 |
ftime | -0.443 |
ater | -0.441 |
borgh | -0.435 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
Chaff | +3.053 |
Snape | +2.958 |
tied | +2.776 |
beard | +2.758 |
transcripts | +2.748 |
Neg logit contributions | |
ariat | -5.339 |
ombat | -3.789 |
ftime | -3.664 |
ater | -3.494 |
borgh | -3.483 |
Token | com |
Token ID | 785 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Chaff | +0.005 |
Snape | +0.005 |
transcripts | +0.005 |
tied | +0.005 |
Porn | +0.005 |
Neg logit contributions | |
ariat | -0.012 |
ombat | -0.009 |
ftime | -0.009 |
ater | -0.009 |
borgh | -0.008 |
Token | / |
Token ID | 14 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Chaff | +0.358 |
Snape | +0.337 |
transcripts | +0.307 |
tied | +0.296 |
Misc | +0.294 |
Neg logit contributions | |
ariat | -1.409 |
ombat | -1.077 |
ftime | -1.039 |
ater | -1.028 |
borgh | -1.020 |
Token | 74 |
Token ID | 4524 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ariat | +1.408 |
ombat | +1.002 |
ftime | +0.951 |
ater | +0.949 |
borgh | +0.940 |
Neg logit contributions | |
Chaff | -0.701 |
Snape | -0.676 |
transcripts | -0.645 |
tied | -0.630 |
Misc | -0.623 |
Token | E |
Token ID | 36 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
ariat | +2.842 |
ombat | +2.022 |
ater | +1.921 |
ftime | +1.916 |
borgh | +1.900 |
Neg logit contributions | |
Chaff | -1.421 |
Snape | -1.369 |
transcripts | -1.306 |
tied | -1.273 |
loophole | -1.268 |
Token | me |
Token ID | 502 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Chaff | +1.087 |
Snape | +1.053 |
transcripts | +1.002 |
tied | +0.980 |
needing | +0.979 |
Neg logit contributions | |
ariat | -2.203 |
ombat | -1.605 |
ftime | -1.504 |
adium | -1.484 |
ater | -1.474 |
Token | later |
Token ID | 1568 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ariat | +1.380 |
ombat | +0.947 |
borgh | +0.886 |
ftime | +0.881 |
ater | +0.879 |
Neg logit contributions | |
Chaff | -0.860 |
Snape | -0.844 |
transcripts | -0.809 |
tied | -0.799 |
loophole | -0.787 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ariat | +0.986 |
ombat | +0.671 |
ftime | +0.629 |
ater | +0.628 |
borgh | +0.625 |
Neg logit contributions | |
Chaff | -0.637 |
Snape | -0.617 |
transcripts | -0.596 |
tied | -0.584 |
Misc | -0.579 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Chaff | +0.498 |
Snape | +0.478 |
transcripts | +0.447 |
Misc | +0.442 |
Porn | +0.440 |
Neg logit contributions | |
ariat | -1.126 |
ombat | -0.813 |
ftime | -0.775 |
ater | -0.768 |
borgh | -0.767 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Chaff | +0.784 |
Snape | +0.762 |
transcripts | +0.715 |
tied | +0.704 |
Misc | +0.704 |
Neg logit contributions | |
ariat | -1.744 |
ombat | -1.251 |
ftime | -1.201 |
ater | -1.177 |
borgh | -1.173 |
Token | Rated |
Token ID | 15322 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Chaff | +0.517 |
Snape | +0.503 |
transcripts | +0.479 |
tied | +0.473 |
beard | +0.467 |
Neg logit contributions | |
ariat | -1.071 |
ombat | -0.759 |
ftime | -0.719 |
adium | -0.712 |
borgh | -0.710 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Chaff | +2.455 |
Snape | +2.301 |
transcripts | +2.200 |
tied | +2.185 |
Porn | +2.173 |
Neg logit contributions | |
ariat | -5.995 |
ombat | -4.371 |
borgh | -4.169 |
ftime | -4.133 |
adium | -4.114 |
Token | out |
Token ID | 503 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Chaff | +1.367 |
Snape | +1.319 |
transcripts | +1.259 |
tied | +1.238 |
Misc | +1.232 |
Neg logit contributions | |
ariat | -2.256 |
ombat | -1.574 |
ftime | -1.493 |
ater | -1.473 |
adium | -1.463 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Chaff | +1.650 |
Snape | +1.603 |
tied | +1.493 |
transcripts | +1.491 |
Misc | +1.487 |
Neg logit contributions | |
ariat | -2.974 |
ombat | -2.109 |
ftime | -2.015 |
ater | -1.975 |
adium | -1.956 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Chaff | +0.506 |
Snape | +0.488 |
transcripts | +0.468 |
loophole | +0.455 |
pornographic | +0.453 |
Neg logit contributions | |
ariat | -0.978 |
ombat | -0.691 |
ater | -0.660 |
ftime | -0.653 |
borgh | -0.648 |
Token | by |
Token ID | 416 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Chaff | +1.592 |
Snape | +1.507 |
transcripts | +1.389 |
tied | +1.376 |
Misc | +1.365 |
Neg logit contributions | |
ariat | -4.744 |
ombat | -3.572 |
ftime | -3.412 |
ater | -3.376 |
adium | -3.363 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
Chaff | +0.378 |
Snape | +0.364 |
transcripts | +0.348 |
loophole | +0.339 |
tied | +0.338 |
Neg logit contributions | |
ariat | -0.752 |
ombat | -0.535 |
ater | -0.509 |
ftime | -0.506 |
borgh | -0.502 |
Token | by |
Token ID | 416 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Chaff | +1.386 |
Snape | +1.309 |
transcripts | +1.222 |
tied | +1.204 |
Misc | +1.186 |
Neg logit contributions | |
ariat | -4.089 |
ombat | -3.071 |
ftime | -2.942 |
ater | -2.908 |
adium | -2.889 |
Token | Quake |
Token ID | 42901 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Chaff | +1.260 |
Snape | +1.213 |
transcripts | +1.145 |
Lynd | +1.139 |
Misc | +1.131 |
Neg logit contributions | |
ariat | -2.329 |
ombat | -1.646 |
ftime | -1.579 |
borgh | -1.545 |
ater | -1.541 |
Token | D |
Token ID | 35 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Chaff | +0.916 |
Snape | +0.877 |
transcripts | +0.833 |
tied | +0.822 |
Porn | +0.822 |
Neg logit contributions | |
ariat | -1.756 |
ombat | -1.238 |
ftime | -1.186 |
borgh | -1.163 |
adium | -1.155 |
Token | ude |
Token ID | 2507 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ariat | +0.174 |
ombat | +0.119 |
ftime | +0.114 |
borgh | +0.112 |
ater | +0.112 |
Neg logit contributions | |
Chaff | -0.105 |
Snape | -0.101 |
transcripts | -0.097 |
tied | -0.096 |
loophole | -0.095 |
Token | from |
Token ID | 422 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
Chaff | +0.538 |
Snape | +0.517 |
transcripts | +0.489 |
tied | +0.484 |
Porn | +0.481 |
Neg logit contributions | |
ariat | -1.093 |
ombat | -0.778 |
ftime | -0.747 |
adium | -0.728 |
borgh | -0.728 |
Token | Explosive |
Token ID | 48178 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
Chaff | +2.576 |
Snape | +2.441 |
Porn | +2.286 |
Misc | +2.284 |
transcripts | +2.281 |
Neg logit contributions | |
ariat | -5.748 |
ombat | -4.127 |
ftime | -3.942 |
adium | -3.881 |
ater | -3.862 |
Token | !!!!!!!! |
Token ID | 34635 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
Chaff | +0.165 |
Snape | +0.158 |
transcripts | +0.151 |
tied | +0.148 |
loophole | +0.148 |
Neg logit contributions | |
ariat | -0.304 |
ombat | -0.212 |
ftime | -0.201 |
ater | -0.199 |
borgh | -0.198 |
Token | If |
Token ID | 1002 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ariat | +0.422 |
ombat | +0.293 |
ftime | +0.282 |
ater | +0.278 |
borgh | +0.277 |
Neg logit contributions | |
Chaff | -0.228 |
Snape | -0.218 |
transcripts | -0.206 |
Porn | -0.203 |
Misc | -0.203 |
Token | you |
Token ID | 345 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Chaff | +0.455 |
Snape | +0.437 |
transcripts | +0.420 |
tied | +0.416 |
needing | +0.411 |
Neg logit contributions | |
ariat | -0.782 |
ombat | -0.550 |
ftime | -0.513 |
ater | -0.512 |
borgh | -0.509 |
Token | give |
Token ID | 1577 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Chaff | +0.429 |
Snape | +0.409 |
tied | +0.391 |
transcripts | +0.390 |
needing | +0.379 |
Neg logit contributions | |
ariat | -0.867 |
ombat | -0.616 |
ftime | -0.592 |
adium | -0.583 |
ater | -0.581 |
Token | handed |
Token ID | 10158 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
Chaff | +0.630 |
Snape | +0.606 |
transcripts | +0.573 |
loophole | +0.562 |
Misc | +0.561 |
Neg logit contributions | |
ariat | -1.289 |
ombat | -0.908 |
ater | -0.875 |
ftime | -0.873 |
borgh | -0.867 |
Token | ' |
Token ID | 6 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Chaff | +0.006 |
Snape | +0.006 |
transcripts | +0.006 |
tied | +0.006 |
loophole | +0.006 |
Neg logit contributions | |
ariat | -0.015 |
ombat | -0.011 |
ater | -0.010 |
borgh | -0.010 |
ftime | -0.010 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Chaff | +1.940 |
Snape | +1.877 |
transcripts | +1.814 |
tied | +1.769 |
loophole | +1.759 |
Neg logit contributions | |
ariat | -3.028 |
ombat | -2.078 |
ater | -1.956 |
borgh | -1.942 |
ftime | -1.940 |
Token | primary |
Token ID | 4165 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Chaff | +2.198 |
Snape | +2.132 |
transcripts | +2.038 |
loophole | +2.000 |
tied | +1.999 |
Neg logit contributions | |
ariat | -3.506 |
ombat | -2.412 |
ater | -2.280 |
ftime | -2.265 |
borgh | -2.245 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Chaff | +1.177 |
Snape | +1.144 |
transcripts | +1.132 |
tied | +1.102 |
loophole | +1.083 |
Neg logit contributions | |
ariat | -1.757 |
ombat | -1.201 |
borgh | -1.112 |
ftime | -1.108 |
adium | -1.103 |
Token | : |
Token ID | 25 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Chaff | +1.873 |
Snape | +1.799 |
transcripts | +1.756 |
tied | +1.719 |
loophole | +1.673 |
Neg logit contributions | |
ariat | -3.681 |
ombat | -2.644 |
ater | -2.501 |
ftime | -2.491 |
borgh | -2.453 |
Token | ' |
Token ID | 705 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Chaff | +2.299 |
Snape | +2.144 |
transcripts | +2.024 |
Misc | +1.972 |
Lynd | +1.958 |
Neg logit contributions | |
ariat | -5.980 |
ombat | -4.545 |
ftime | -4.312 |
borgh | -4.218 |
adium | -4.183 |
Token | Damn |
Token ID | 43343 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Chaff | +1.491 |
Snape | +1.430 |
transcripts | +1.354 |
tied | +1.310 |
Misc | +1.303 |
Neg logit contributions | |
ariat | -3.651 |
ombat | -2.664 |
ftime | -2.543 |
ater | -2.542 |
borgh | -2.512 |
Token | right |
Token ID | 826 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Chaff | +0.059 |
Snape | +0.057 |
transcripts | +0.055 |
tied | +0.054 |
loophole | +0.053 |
Neg logit contributions | |
ariat | -0.081 |
ombat | -0.055 |
ftime | -0.052 |
ater | -0.052 |
borgh | -0.051 |
Token | ' |
Token ID | 6 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Chaff | +0.361 |
Snape | +0.350 |
transcripts | +0.335 |
tied | +0.330 |
Lynd | +0.318 |
Neg logit contributions | |
ariat | -0.836 |
ombat | -0.615 |
borgh | -0.584 |
adium | -0.577 |
ater | -0.576 |
Token | I |
Token ID | 314 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Chaff | +1.215 |
Snape | +1.174 |
transcripts | +1.124 |
tied | +1.096 |
loophole | +1.096 |
Neg logit contributions | |
ariat | -2.190 |
ombat | -1.534 |
ater | -1.455 |
ftime | -1.449 |
borgh | -1.437 |
Token | You |
Token ID | 921 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Chaff | +1.864 |
Snape | +1.772 |
transcripts | +1.691 |
tied | +1.657 |
Porn | +1.655 |
Neg logit contributions | |
ariat | -3.823 |
ombat | -2.723 |
ftime | -2.591 |
ater | -2.583 |
adium | -2.551 |
Token | will |
Token ID | 481 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Chaff | +1.771 |
Snape | +1.678 |
transcripts | +1.640 |
tied | +1.613 |
poetic | +1.567 |
Neg logit contributions | |
ariat | -3.820 |
ombat | -2.700 |
ftime | -2.633 |
adium | -2.602 |
borgh | -2.579 |
Token | receive |
Token ID | 3328 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
Chaff | +1.236 |
Snape | +1.170 |
transcripts | +1.148 |
tied | +1.108 |
Misc | +1.097 |
Neg logit contributions | |
ariat | -2.721 |
ombat | -1.951 |
ftime | -1.865 |
ater | -1.855 |
borgh | -1.846 |
Token | occasional |
Token ID | 12209 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ariat | +0.148 |
ombat | +0.097 |
ater | +0.091 |
ftime | +0.090 |
adium | +0.089 |
Neg logit contributions | |
Chaff | -0.118 |
Snape | -0.115 |
transcripts | -0.110 |
loophole | -0.109 |
tied | -0.108 |
Token | promotional |
Token ID | 18767 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
Chaff | +1.018 |
Snape | +0.956 |
transcripts | +0.946 |
pornographic | +0.881 |
tied | +0.877 |
Neg logit contributions | |
ariat | -3.047 |
ombat | -2.264 |
ater | -2.170 |
ftime | -2.166 |
borgh | -2.156 |
Token | offers |
Token ID | 4394 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Chaff | +1.606 |
Snape | +1.578 |
transcripts | +1.558 |
tied | +1.440 |
tags | +1.412 |
Neg logit contributions | |
ariat | -5.315 |
ombat | -3.965 |
ftime | -3.876 |
borgh | -3.766 |
ater | -3.759 |
Token | for |
Token ID | 329 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Chaff | +2.934 |
Snape | +2.781 |
transcripts | +2.733 |
tied | +2.717 |
Misc | +2.658 |
Neg logit contributions | |
ariat | -5.218 |
ombat | -3.710 |
ftime | -3.514 |
ater | -3.461 |
alky | -3.418 |
Token | programs |
Token ID | 4056 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Chaff | +0.521 |
transcripts | +0.502 |
Snape | +0.488 |
tied | +0.472 |
pornographic | +0.468 |
Neg logit contributions | |
ariat | -1.167 |
ombat | -0.847 |
ftime | -0.811 |
borgh | -0.797 |
ater | -0.797 |
Token | that |
Token ID | 326 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Chaff | +1.435 |
Snape | +1.363 |
transcripts | +1.309 |
tied | +1.282 |
Misc | +1.238 |
Neg logit contributions | |
ariat | -3.767 |
ombat | -2.793 |
ftime | -2.656 |
ater | -2.638 |
borgh | -2.624 |
Token | support |
Token ID | 1104 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Chaff | +0.690 |
Snape | +0.652 |
transcripts | +0.621 |
tied | +0.604 |
loophole | +0.592 |
Neg logit contributions | |
ariat | -2.066 |
ombat | -1.544 |
ater | -1.469 |
ftime | -1.469 |
borgh | -1.467 |
Token | The |
Token ID | 383 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Chaff | +1.625 |
Snape | +1.514 |
transcripts | +1.458 |
Disclosure | +1.414 |
Porn | +1.413 |
Neg logit contributions | |
ariat | -4.085 |
ombat | -3.012 |
ftime | -2.914 |
ater | -2.864 |
borgh | -2.848 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Chaff | +1.650 |
Snape | +1.603 |
tied | +1.493 |
transcripts | +1.491 |
Misc | +1.487 |
Neg logit contributions | |
ariat | -2.974 |
ombat | -2.109 |
ftime | -2.015 |
ater | -1.975 |
adium | -1.956 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
Chaff | +0.506 |
Snape | +0.488 |
transcripts | +0.468 |
loophole | +0.455 |
pornographic | +0.453 |
Neg logit contributions | |
ariat | -0.978 |
ombat | -0.691 |
ater | -0.660 |
ftime | -0.653 |
borgh | -0.648 |
Token | by |
Token ID | 416 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Chaff | +1.592 |
Snape | +1.507 |
transcripts | +1.389 |
tied | +1.376 |
Misc | +1.365 |
Neg logit contributions | |
ariat | -4.744 |
ombat | -3.572 |
ftime | -3.412 |
ater | -3.376 |
adium | -3.363 |
Token | Cory |
Token ID | 28785 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Chaff | +1.337 |
Snape | +1.289 |
transcripts | +1.215 |
Lynd | +1.210 |
Porn | +1.202 |
Neg logit contributions | |
ariat | -2.468 |
ombat | -1.743 |
ftime | -1.672 |
borgh | -1.635 |
ater | -1.632 |
Token | B |
Token ID | 33 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
Chaff | +0.736 |
Snape | +0.702 |
transcripts | +0.664 |
tied | +0.654 |
Misc | +0.652 |
Neg logit contributions | |
ariat | -1.392 |
ombat | -0.980 |
ftime | -0.924 |
ater | -0.918 |
adium | -0.912 |
Token | from |
Token ID | 422 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
Chaff | +0.213 |
Snape | +0.205 |
transcripts | +0.196 |
tied | +0.193 |
loophole | +0.191 |
Neg logit contributions | |
ariat | -0.394 |
ombat | -0.278 |
ftime | -0.265 |
ater | -0.261 |
borgh | -0.261 |
Token | The |
Token ID | 383 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Chaff | +2.496 |
Snape | +2.374 |
transcripts | +2.212 |
tied | +2.209 |
Misc | +2.209 |
Neg logit contributions | |
ariat | -5.719 |
ombat | -4.123 |
ftime | -3.924 |
adium | -3.871 |
ater | -3.868 |
Token | best |
Token ID | 1266 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Chaff | +1.096 |
Snape | +1.055 |
transcripts | +1.003 |
loophole | +0.988 |
tied | +0.988 |
Neg logit contributions | |
ariat | -2.014 |
ombat | -1.406 |
ftime | -1.331 |
borgh | -1.311 |
adium | -1.302 |
Token | sub |
Token ID | 850 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Chaff | +1.191 |
Snape | +1.141 |
tied | +1.085 |
transcripts | +1.082 |
loophole | +1.076 |
Neg logit contributions | |
ariat | -2.168 |
ombat | -1.517 |
ftime | -1.435 |
borgh | -1.416 |
ater | -1.415 |
Token | wo |
Token ID | 21638 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Chaff | +1.241 |
Snape | +1.188 |
tied | +1.141 |
transcripts | +1.126 |
loophole | +1.123 |
Neg logit contributions | |
ariat | -2.437 |
ombat | -1.726 |
borgh | -1.620 |
ater | -1.612 |
ftime | -1.604 |
Token | ofer |
Token ID | 30288 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
ariat | +0.328 |
ombat | +0.213 |
ftime | +0.204 |
adium | +0.199 |
borgh | +0.198 |
Neg logit contributions | |
Chaff | -0.243 |
Snape | -0.235 |
tied | -0.224 |
loophole | -0.223 |
transcripts | -0.223 |
Token | comment |
Token ID | 2912 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
Chaff | +0.260 |
Snape | +0.247 |
transcripts | +0.229 |
tied | +0.220 |
loophole | +0.218 |
Neg logit contributions | |
ariat | -0.987 |
ombat | -0.746 |
ftime | -0.717 |
ater | -0.715 |
borgh | -0.712 |
Token | on |
Token ID | 319 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Chaff | +0.248 |
Snape | +0.240 |
transcripts | +0.229 |
loophole | +0.222 |
tied | +0.222 |
Neg logit contributions | |
ariat | -0.488 |
ombat | -0.346 |
ater | -0.329 |
ftime | -0.328 |
borgh | -0.325 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ariat | +1.602 |
ombat | +1.167 |
ater | +1.114 |
ftime | +1.111 |
borgh | +1.103 |
Neg logit contributions | |
Chaff | -0.660 |
Snape | -0.633 |
transcripts | -0.599 |
tied | -0.581 |
loophole | -0.580 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Chaff | +1.001 |
Snape | +0.966 |
transcripts | +0.919 |
tied | +0.895 |
Lynd | +0.891 |
Neg logit contributions | |
ariat | -2.063 |
ombat | -1.478 |
ftime | -1.404 |
adium | -1.392 |
ater | -1.391 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Chaff | +0.527 |
Snape | +0.507 |
transcripts | +0.479 |
Misc | +0.471 |
tied | +0.470 |
Neg logit contributions | |
ariat | -1.111 |
ombat | -0.802 |
ftime | -0.765 |
ater | -0.755 |
borgh | -0.748 |
Token | NY |
Token ID | 12805 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
Chaff | +0.439 |
Snape | +0.418 |
transcripts | +0.405 |
tied | +0.395 |
beard | +0.393 |
Neg logit contributions | |
ariat | -1.008 |
ombat | -0.721 |
ftime | -0.693 |
ater | -0.687 |
borgh | -0.683 |
Token | T |
Token ID | 51 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Chaff | +1.704 |
Snape | +1.555 |
transcripts | +1.531 |
tied | +1.463 |
TPS | +1.457 |
Neg logit contributions | |
ariat | -6.328 |
ombat | -4.740 |
alky | -4.637 |
ftime | -4.629 |
adium | -4.618 |
Token | Pick |
Token ID | 12346 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Chaff | +0.677 |
Snape | +0.643 |
transcripts | +0.613 |
tied | +0.588 |
Misc | +0.584 |
Neg logit contributions | |
ariat | -2.204 |
ombat | -1.629 |
ftime | -1.592 |
borgh | -1.580 |
alky | -1.566 |
Token | J |
Token ID | 449 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Chaff | +1.757 |
Snape | +1.702 |
Lynd | +1.588 |
transcripts | +1.587 |
tied | +1.575 |
Neg logit contributions | |
ariat | -3.185 |
ombat | -2.264 |
ftime | -2.163 |
borgh | -2.131 |
ater | -2.111 |
Token | AB |
Token ID | 6242 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Chaff | +0.395 |
Snape | +0.382 |
transcripts | +0.366 |
tied | +0.358 |
Misc | +0.356 |
Neg logit contributions | |
ariat | -0.621 |
ombat | -0.423 |
ftime | -0.403 |
ater | -0.399 |
borgh | -0.398 |
Token | arry |
Token ID | 6532 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Chaff | +0.512 |
Snape | +0.491 |
transcripts | +0.470 |
tied | +0.465 |
Misc | +0.460 |
Neg logit contributions | |
ariat | -0.917 |
ombat | -0.639 |
ftime | -0.607 |
ater | -0.603 |
borgh | -0.600 |
Token | ll |
Token ID | 297 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Chaff | +0.403 |
Snape | +0.387 |
transcripts | +0.372 |
tied | +0.363 |
Misc | +0.361 |
Neg logit contributions | |
ariat | -0.739 |
ombat | -0.519 |
ftime | -0.493 |
ater | -0.491 |
borgh | -0.486 |
Token | send |
Token ID | 3758 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Chaff | +0.647 |
Snape | +0.621 |
transcripts | +0.593 |
tied | +0.575 |
loophole | +0.573 |
Neg logit contributions | |
ariat | -1.450 |
ombat | -1.047 |
ater | -0.998 |
ftime | -0.995 |
borgh | -0.986 |
Token | you |
Token ID | 345 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Chaff | +1.493 |
transcripts | +1.433 |
Snape | +1.431 |
tied | +1.383 |
Lynd | +1.379 |
Neg logit contributions | |
ariat | -2.429 |
ombat | -1.696 |
borgh | -1.597 |
ftime | -1.595 |
ater | -1.583 |
Token | three |
Token ID | 1115 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Chaff | +2.834 |
Snape | +2.721 |
transcripts | +2.662 |
tied | +2.604 |
Porn | +2.556 |
Neg logit contributions | |
ariat | -5.153 |
ombat | -3.627 |
ftime | -3.478 |
borgh | -3.439 |
ater | -3.431 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Chaff | +1.244 |
Snape | +1.180 |
transcripts | +1.146 |
tied | +1.107 |
pornographic | +1.095 |
Neg logit contributions | |
ariat | -2.927 |
ombat | -2.121 |
ftime | -2.024 |
ater | -2.020 |
adium | -1.993 |
Token | actions |
Token ID | 4028 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
transcripts | +1.111 |
Chaff | +1.103 |
Snape | +1.061 |
Porn | +1.016 |
tied | +1.011 |
Neg logit contributions | |
ariat | -3.169 |
ombat | -2.294 |
ftime | -2.212 |
ater | -2.207 |
alky | -2.172 |
Token | you |
Token ID | 345 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Chaff | +3.098 |
Snape | +3.009 |
transcripts | +2.888 |
tied | +2.863 |
Porn | +2.811 |
Neg logit contributions | |
ariat | -4.997 |
ombat | -3.500 |
ftime | -3.284 |
ater | -3.256 |
adium | -3.226 |
Token | can |
Token ID | 460 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Chaff | +1.696 |
Snape | +1.639 |
transcripts | +1.568 |
loophole | +1.530 |
tied | +1.528 |
Neg logit contributions | |
ariat | -3.044 |
ombat | -2.133 |
ater | -2.023 |
ftime | -2.012 |
borgh | -1.997 |
Token | take |
Token ID | 1011 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Chaff | +1.234 |
Snape | +1.184 |
transcripts | +1.133 |
tied | +1.102 |
loophole | +1.095 |
Neg logit contributions | |
ariat | -2.642 |
ombat | -1.890 |
ater | -1.803 |
ftime | -1.799 |
borgh | -1.786 |
Token | each |
Token ID | 1123 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Chaff | +1.305 |
Snape | +1.255 |
transcripts | +1.218 |
tied | +1.199 |
Misc | +1.168 |
Neg logit contributions | |
ariat | -2.336 |
ombat | -1.644 |
ftime | -1.560 |
ater | -1.553 |
borgh | -1.540 |
Token | week |
Token ID | 1285 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Chaff | +2.281 |
Snape | +2.215 |
transcripts | +2.135 |
tied | +2.091 |
loophole | +2.090 |
Neg logit contributions | |
ariat | -3.100 |
ombat | -2.066 |
ater | -1.941 |
ftime | -1.931 |
borgh | -1.912 |
Token | has |
Token ID | 468 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Chaff | +1.162 |
Snape | +1.060 |
tied | +1.039 |
transcripts | +1.034 |
needing | +1.012 |
Neg logit contributions | |
ariat | -2.216 |
ombat | -1.667 |
ftime | -1.546 |
borgh | -1.530 |
adium | -1.521 |
Token | evidence |
Token ID | 2370 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Chaff | +0.716 |
Snape | +0.685 |
transcripts | +0.661 |
tied | +0.644 |
loophole | +0.640 |
Neg logit contributions | |
ariat | -1.380 |
ombat | -0.985 |
ater | -0.935 |
ftime | -0.934 |
borgh | -0.927 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Chaff | +0.245 |
Snape | +0.238 |
transcripts | +0.229 |
loophole | +0.224 |
Lynd | +0.222 |
Neg logit contributions | |
ariat | -0.427 |
ombat | -0.294 |
ater | -0.282 |
ftime | -0.281 |
borgh | -0.278 |
Token | requested |
Token ID | 9167 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Chaff | +1.484 |
Snape | +1.440 |
transcripts | +1.383 |
tied | +1.365 |
pornographic | +1.325 |
Neg logit contributions | |
ariat | -3.170 |
ombat | -2.313 |
ater | -2.156 |
ftime | -2.148 |
adium | -2.148 |
Token | putting |
Token ID | 5137 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Chaff | +0.523 |
Snape | +0.501 |
transcripts | +0.473 |
tied | +0.458 |
loophole | +0.457 |
Neg logit contributions | |
ariat | -1.338 |
ombat | -0.980 |
ater | -0.937 |
ftime | -0.933 |
borgh | -0.927 |
Token | ally |
Token ID | 12525 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
Chaff | +0.584 |
Snape | +0.555 |
transcripts | +0.512 |
Misc | +0.495 |
tied | +0.495 |
Neg logit contributions | |
ariat | -2.036 |
ombat | -1.524 |
ater | -1.469 |
ftime | -1.458 |
borgh | -1.454 |
Token | in |
Token ID | 287 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Chaff | +2.794 |
Snape | +2.699 |
transcripts | +2.613 |
tied | +2.534 |
loophole | +2.519 |
Neg logit contributions | |
ariat | -5.298 |
ombat | -3.758 |
ater | -3.528 |
ftime | -3.522 |
borgh | -3.503 |
Token | charge |
Token ID | 3877 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
Chaff | +0.761 |
Snape | +0.720 |
transcripts | +0.701 |
tied | +0.683 |
loophole | +0.674 |
Neg logit contributions | |
ariat | -1.594 |
ombat | -1.166 |
ftime | -1.109 |
borgh | -1.102 |
ater | -1.094 |
Token | of |
Token ID | 286 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ariat | +0.314 |
ombat | +0.217 |
ater | +0.205 |
ftime | +0.204 |
borgh | +0.202 |
Neg logit contributions | |
Chaff | -0.193 |
Snape | -0.186 |
transcripts | -0.179 |
tied | -0.175 |
loophole | -0.174 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Chaff | +0.505 |
Snape | +0.488 |
transcripts | +0.467 |
tied | +0.456 |
loophole | +0.455 |
Neg logit contributions | |
ariat | -0.910 |
ombat | -0.638 |
ater | -0.605 |
ftime | -0.603 |
borgh | -0.598 |
Token | probe |
Token ID | 12774 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ariat | +0.346 |
ombat | +0.245 |
ater | +0.235 |
ftime | +0.233 |
borgh | +0.230 |
Neg logit contributions | |
Chaff | -0.181 |
Snape | -0.175 |
transcripts | -0.165 |
pornographic | -0.161 |
beard | -0.161 |
Token | Rock |
Token ID | 4631 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
Chaff | +0.054 |
Snape | +0.052 |
transcripts | +0.049 |
tied | +0.048 |
Misc | +0.048 |
Neg logit contributions | |
ariat | -0.094 |
ombat | -0.067 |
ftime | -0.063 |
ater | -0.062 |
borgh | -0.062 |
Token | Tou |
Token ID | 23359 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
Chaff | +0.257 |
Snape | +0.247 |
transcripts | +0.236 |
Misc | +0.232 |
tied | +0.231 |
Neg logit contributions | |
ariat | -0.484 |
ombat | -0.342 |
ftime | -0.323 |
borgh | -0.320 |
ater | -0.320 |
Token | ched |
Token ID | 1740 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ariat | +0.033 |
ombat | +0.022 |
ftime | +0.021 |
ater | +0.021 |
borgh | +0.021 |
Neg logit contributions | |
Chaff | -0.025 |
Snape | -0.024 |
transcripts | -0.023 |
tied | -0.023 |
Porn | -0.023 |
Token | by |
Token ID | 416 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Chaff | +0.437 |
Snape | +0.417 |
transcripts | +0.391 |
Porn | +0.391 |
Misc | +0.390 |
Neg logit contributions | |
ariat | -0.942 |
ombat | -0.683 |
ftime | -0.645 |
ater | -0.639 |
borgh | -0.638 |
Token | NASA |
Token ID | 8884 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Chaff | +1.142 |
Snape | +1.086 |
Misc | +1.027 |
Porn | +1.023 |
transcripts | +1.012 |
Neg logit contributions | |
ariat | -2.097 |
ombat | -1.502 |
ftime | -1.431 |
borgh | -1.387 |
ater | -1.386 |
Token | Curiosity |
Token ID | 39736 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
Chaff | +1.083 |
Snape | +1.025 |
transcripts | +0.991 |
Misc | +0.974 |
Porn | +0.965 |
Neg logit contributions | |
ariat | -2.161 |
ombat | -1.560 |
ftime | -1.468 |
ater | -1.444 |
adium | -1.434 |
Token | has |
Token ID | 468 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Chaff | +2.939 |
Snape | +2.727 |
transcripts | +2.691 |
Misc | +2.664 |
tied | +2.632 |
Neg logit contributions | |
ariat | -5.143 |
ombat | -3.717 |
ftime | -3.472 |
borgh | -3.365 |
adium | -3.356 |
Token | Sur |
Token ID | 4198 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Chaff | +0.421 |
Snape | +0.400 |
tied | +0.388 |
transcripts | +0.385 |
Misc | +0.374 |
Neg logit contributions | |
ariat | -0.725 |
ombat | -0.509 |
ftime | -0.483 |
ater | -0.479 |
borgh | -0.477 |
Token | prises |
Token ID | 18166 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
ariat | +0.841 |
ombat | +0.583 |
ater | +0.545 |
ftime | +0.545 |
borgh | +0.542 |
Neg logit contributions | |
Chaff | -0.487 |
Snape | -0.472 |
transcripts | -0.447 |
tied | -0.443 |
Misc | -0.440 |
Token |
|
Token ID | 198 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
ariat | +0.521 |
ombat | +0.372 |
ftime | +0.349 |
borgh | +0.347 |
ater | +0.346 |
Neg logit contributions | |
Chaff | -0.275 |
Snape | -0.264 |
tied | -0.250 |
transcripts | -0.248 |
Misc | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
ariat | +0.332 |
ombat | +0.238 |
ftime | +0.226 |
ater | +0.224 |
borgh | +0.222 |
Neg logit contributions | |
Chaff | -0.164 |
Snape | -0.157 |
transcripts | -0.149 |
Misc | -0.146 |
tied | -0.146 |
Token | has |
Token ID | 468 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Chaff | +1.388 |
Snape | +1.281 |
tied | +1.255 |
transcripts | +1.253 |
needing | +1.220 |
Neg logit contributions | |
ariat | -2.744 |
ombat | -2.044 |
ftime | -1.913 |
borgh | -1.903 |
adium | -1.886 |
Token | evidence |
Token ID | 2370 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Chaff | +0.895 |
Snape | +0.858 |
transcripts | +0.827 |
tied | +0.806 |
loophole | +0.803 |
Neg logit contributions | |
ariat | -1.711 |
ombat | -1.218 |
ater | -1.157 |
ftime | -1.155 |
borgh | -1.146 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Chaff | +0.569 |
Snape | +0.558 |
transcripts | +0.537 |
loophole | +0.527 |
Lynd | +0.523 |
Neg logit contributions | |
ariat | -0.917 |
ombat | -0.618 |
ater | -0.594 |
ftime | -0.592 |
borgh | -0.586 |
Token | requested |
Token ID | 9167 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Chaff | +1.445 |
Snape | +1.403 |
transcripts | +1.344 |
tied | +1.321 |
pornographic | +1.292 |
Neg logit contributions | |
ariat | -3.075 |
ombat | -2.234 |
ater | -2.091 |
ftime | -2.085 |
adium | -2.081 |
Token | putting |
Token ID | 5137 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Chaff | +0.429 |
Snape | +0.410 |
transcripts | +0.391 |
tied | +0.376 |
loophole | +0.375 |
Neg logit contributions | |
ariat | -1.130 |
ombat | -0.831 |
ftime | -0.794 |
ater | -0.792 |
borgh | -0.787 |
Token | ally |
Token ID | 12525 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Chaff | +0.706 |
Snape | +0.684 |
transcripts | +0.647 |
Misc | +0.639 |
loophole | +0.637 |
Neg logit contributions | |
ariat | -1.434 |
ombat | -1.007 |
ater | -0.967 |
borgh | -0.954 |
ftime | -0.951 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Chaff | +2.820 |
Snape | +2.723 |
transcripts | +2.595 |
loophole | +2.533 |
tied | +2.531 |
Neg logit contributions | |
ariat | -5.239 |
ombat | -3.687 |
ater | -3.507 |
ftime | -3.493 |
borgh | -3.462 |
Token | charge |
Token ID | 3877 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
Chaff | +0.663 |
Snape | +0.631 |
transcripts | +0.611 |
tied | +0.595 |
loophole | +0.588 |
Neg logit contributions | |
ariat | -1.385 |
ombat | -1.007 |
ftime | -0.958 |
borgh | -0.952 |
ater | -0.949 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ariat | +0.383 |
ombat | +0.266 |
ater | +0.251 |
ftime | +0.250 |
borgh | +0.248 |
Neg logit contributions | |
Chaff | -0.230 |
Snape | -0.222 |
transcripts | -0.214 |
tied | -0.208 |
loophole | -0.208 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
Chaff | +0.458 |
Snape | +0.442 |
transcripts | +0.421 |
loophole | +0.414 |
tied | +0.413 |
Neg logit contributions | |
ariat | -0.831 |
ombat | -0.577 |
ater | -0.552 |
ftime | -0.547 |
borgh | -0.543 |
Token | probe |
Token ID | 12774 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Chaff | +0.232 |
Snape | +0.227 |
transcripts | +0.214 |
beard | +0.209 |
pornographic | +0.209 |
Neg logit contributions | |
ariat | -0.389 |
ombat | -0.270 |
ater | -0.259 |
ftime | -0.255 |
borgh | -0.252 |
Token | / |
Token ID | 14 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Chaff | +0.342 |
Snape | +0.325 |
transcripts | +0.310 |
Misc | +0.294 |
tied | +0.293 |
Neg logit contributions | |
ariat | -1.303 |
ombat | -0.999 |
ftime | -0.957 |
adium | -0.949 |
ater | -0.944 |
Token | Getty |
Token ID | 6633 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Chaff | +0.334 |
Snape | +0.315 |
transcripts | +0.290 |
tied | +0.289 |
Misc | +0.287 |
Neg logit contributions | |
ariat | -1.151 |
ombat | -0.878 |
ftime | -0.839 |
ater | -0.832 |
adium | -0.826 |
Token | Images |
Token ID | 5382 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Chaff | +1.224 |
Snape | +1.196 |
transcripts | +1.140 |
Misc | +1.123 |
Porn | +1.114 |
Neg logit contributions | |
ariat | -3.026 |
ombat | -2.267 |
ftime | -2.144 |
alky | -2.089 |
borgh | -2.088 |
Token | ) |
Token ID | 8 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ariat | +0.704 |
ombat | +0.490 |
ftime | +0.463 |
ater | +0.461 |
borgh | +0.459 |
Neg logit contributions | |
Chaff | -0.410 |
Snape | -0.399 |
transcripts | -0.385 |
tied | -0.376 |
Misc | -0.375 |
Token | Story |
Token ID | 8362 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Chaff | +0.665 |
Snape | +0.640 |
transcripts | +0.609 |
Porn | +0.598 |
Misc | +0.598 |
Neg logit contributions | |
ariat | -1.238 |
ombat | -0.878 |
ftime | -0.834 |
ater | -0.822 |
adium | -0.819 |
Token | Highlights |
Token ID | 30776 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ariat | +0.642 |
ombat | +0.450 |
ater | +0.422 |
ftime | +0.419 |
borgh | +0.418 |
Neg logit contributions | |
Chaff | -0.377 |
Snape | -0.366 |
transcripts | -0.352 |
tied | -0.346 |
Porn | -0.342 |
Token | The |
Token ID | 383 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ariat | +7.268 |
ombat | +5.127 |
ater | +4.961 |
ftime | +4.869 |
borgh | +4.864 |
Neg logit contributions | |
Chaff | -3.383 |
Snape | -3.310 |
transcripts | -3.168 |
pornographic | -3.130 |
poetic | -3.102 |
Token | United |
Token ID | 1578 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Chaff | +0.341 |
Snape | +0.325 |
transcripts | +0.317 |
tied | +0.308 |
loophole | +0.308 |
Neg logit contributions | |
ariat | -0.697 |
ombat | -0.506 |
ftime | -0.479 |
borgh | -0.474 |
adium | -0.471 |
Token | States |
Token ID | 1829 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
ariat | +1.859 |
ombat | +1.203 |
ater | +1.123 |
ftime | +1.119 |
borgh | +1.106 |
Neg logit contributions | |
Chaff | -1.552 |
Snape | -1.511 |
transcripts | -1.461 |
tied | -1.433 |
loophole | -1.432 |
Token | will |
Token ID | 481 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Chaff | +0.286 |
Snape | +0.274 |
transcripts | +0.266 |
tied | +0.264 |
loophole | +0.259 |
Neg logit contributions | |
ariat | -0.556 |
ombat | -0.399 |
ftime | -0.376 |
ater | -0.374 |
borgh | -0.374 |
Token | run |
Token ID | 1057 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
ariat | +0.911 |
ombat | +0.642 |
ftime | +0.606 |
ater | +0.602 |
borgh | +0.602 |
Neg logit contributions | |
Chaff | -0.496 |
Snape | -0.480 |
transcripts | -0.464 |
tied | -0.459 |
loophole | -0.454 |
Token | the |
Token ID | 262 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
ariat | +0.009 |
ombat | +0.006 |
ftime | +0.006 |
ater | +0.006 |
borgh | +0.006 |
Neg logit contributions | |
Chaff | -0.005 |
Snape | -0.005 |
transcripts | -0.004 |
tied | -0.004 |
Misc | -0.004 |
Token | Prophet |
Token ID | 13583 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ariat | +0.349 |
ombat | +0.239 |
ftime | +0.227 |
borgh | +0.224 |
adium | +0.222 |
Neg logit contributions | |
Chaff | -0.227 |
Snape | -0.220 |
transcripts | -0.212 |
tied | -0.209 |
loophole | -0.208 |
Token | said |
Token ID | 531 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ariat | +2.230 |
ombat | +1.582 |
ftime | +1.498 |
ater | +1.497 |
borgh | +1.485 |
Neg logit contributions | |
Chaff | -1.159 |
Snape | -1.118 |
transcripts | -1.064 |
tied | -1.046 |
loophole | -1.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ariat | +1.389 |
ombat | +0.968 |
ater | +0.920 |
ftime | +0.913 |
borgh | +0.907 |
Neg logit contributions | |
Chaff | -0.796 |
Snape | -0.768 |
transcripts | -0.738 |
loophole | -0.718 |
Misc | -0.716 |
Token | " |
Token ID | 366 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
Chaff | +0.675 |
Snape | +0.649 |
transcripts | +0.610 |
tied | +0.602 |
Misc | +0.596 |
Neg logit contributions | |
ariat | -1.464 |
ombat | -1.058 |
ftime | -1.005 |
ater | -1.000 |
borgh | -0.995 |
Token | O |
Token ID | 46 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ariat | +0.216 |
ombat | +0.156 |
ftime | +0.148 |
ater | +0.147 |
borgh | +0.146 |
Neg logit contributions | |
Chaff | -0.101 |
Snape | -0.097 |
transcripts | -0.091 |
tied | -0.090 |
Misc | -0.089 |
Token | Sad |
Token ID | 14668 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
ariat | +6.208 |
ombat | +4.325 |
ater | +4.116 |
ftime | +4.052 |
borgh | +4.025 |
Neg logit contributions | |
Chaff | -3.571 |
Snape | -3.452 |
transcripts | -3.323 |
loophole | -3.239 |
pornographic | -3.224 |
Token | ! |
Token ID | 0 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ariat | +0.271 |
ombat | +0.188 |
ftime | +0.178 |
ater | +0.175 |
adium | +0.174 |
Neg logit contributions | |
Chaff | -0.162 |
Snape | -0.158 |
tied | -0.152 |
transcripts | -0.150 |
Misc | -0.149 |
Token | These |
Token ID | 2312 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ariat | +1.666 |
ombat | +1.197 |
ater | +1.138 |
ftime | +1.137 |
borgh | +1.127 |
Neg logit contributions | |
Chaff | -0.783 |
Snape | -0.754 |
transcripts | -0.715 |
tied | -0.698 |
loophole | -0.694 |
Token | people |
Token ID | 661 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ariat | +3.259 |
ombat | +2.299 |
ftime | +2.177 |
ater | +2.176 |
borgh | +2.155 |
Neg logit contributions | |
Chaff | -1.745 |
Snape | -1.685 |
transcripts | -1.613 |
tied | -1.575 |
loophole | -1.568 |
Token | have |
Token ID | 423 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ariat | +3.518 |
ombat | +2.455 |
ater | +2.335 |
ftime | +2.317 |
borgh | +2.304 |
Neg logit contributions | |
Chaff | -1.973 |
Snape | -1.902 |
transcripts | -1.825 |
loophole | -1.777 |
Misc | -1.773 |
Token | oxy |
Token ID | 23536 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ariat | +2.776 |
ombat | +1.857 |
ater | +1.734 |
ftime | +1.727 |
borgh | +1.714 |
Neg logit contributions | |
Chaff | -1.980 |
Snape | -1.925 |
transcripts | -1.854 |
tied | -1.824 |
Porn | -1.809 |
Token | - |
Token ID | 12 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ariat | +1.951 |
ombat | +1.323 |
ater | +1.239 |
ftime | +1.238 |
borgh | +1.221 |
Neg logit contributions | |
Chaff | -1.307 |
Snape | -1.268 |
transcripts | -1.225 |
tied | -1.204 |
Misc | -1.192 |
Token | 4 |
Token ID | 19 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ariat | +3.290 |
ombat | +2.361 |
ater | +2.242 |
ftime | +2.238 |
borgh | +2.219 |
Neg logit contributions | |
Chaff | -1.538 |
Snape | -1.477 |
transcripts | -1.414 |
tied | -1.376 |
Misc | -1.365 |
Token | - |
Token ID | 12 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ariat | +2.657 |
ombat | +1.808 |
ftime | +1.699 |
ater | +1.679 |
borgh | +1.664 |
Neg logit contributions | |
Chaff | -1.782 |
Snape | -1.715 |
transcripts | -1.664 |
tied | -1.628 |
Misc | -1.623 |
Token | m |
Token ID | 76 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ariat | +2.409 |
ombat | +1.636 |
ater | +1.531 |
ftime | +1.530 |
borgh | +1.510 |
Neg logit contributions | |
Chaff | -1.606 |
Snape | -1.558 |
transcripts | -1.502 |
tied | -1.478 |
loophole | -1.465 |
Token | eth |
Token ID | 2788 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ariat | +1.908 |
ombat | +1.204 |
ftime | +1.104 |
ater | +1.089 |
borgh | +1.088 |
Neg logit contributions | |
Chaff | -1.771 |
Snape | -1.724 |
transcripts | -1.670 |
tied | -1.643 |
Porn | -1.635 |
Token | ox |
Token ID | 1140 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ariat | +5.321 |
ombat | +3.552 |
ater | +3.344 |
ftime | +3.327 |
borgh | +3.293 |
Neg logit contributions | |
Chaff | -3.898 |
Snape | -3.785 |
transcripts | -3.647 |
loophole | -3.575 |
tied | -3.568 |
Token | ym |
Token ID | 4948 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ariat | +2.061 |
ombat | +1.563 |
ftime | +1.500 |
borgh | +1.491 |
ater | +1.489 |
Neg logit contributions | |
Chaff | -0.494 |
Snape | -0.467 |
transcripts | -0.427 |
tied | -0.411 |
Lynd | -0.407 |
Token | ethyl |
Token ID | 21610 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ariat | +2.231 |
ombat | +1.411 |
ftime | +1.291 |
ater | +1.286 |
borgh | +1.268 |
Neg logit contributions | |
Chaff | -2.057 |
Snape | -2.007 |
transcripts | -1.949 |
tied | -1.921 |
beard | -1.903 |
Token | phen |
Token ID | 31024 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ariat | +3.389 |
ombat | +2.294 |
ater | +2.153 |
ftime | +2.148 |
borgh | +2.125 |
Neg logit contributions | |
Chaff | -2.322 |
Snape | -2.252 |
transcripts | -2.172 |
tied | -2.126 |
loophole | -2.120 |
Token | yl |
Token ID | 2645 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
ariat | +2.293 |
ombat | +1.621 |
ftime | +1.535 |
ater | +1.520 |
borgh | +1.508 |
Neg logit contributions | |
Chaff | -1.173 |
Snape | -1.130 |
transcripts | -1.079 |
tied | -1.061 |
Lynd | -1.055 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ariat | +1.355 |
ombat | +0.954 |
ftime | +0.904 |
borgh | +0.896 |
ater | +0.896 |
Neg logit contributions | |
Chaff | -0.767 |
Snape | -0.740 |
transcripts | -0.704 |
tied | -0.689 |
Misc | -0.688 |
Token | entrance |
Token ID | 10384 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ariat | +1.220 |
ombat | +0.858 |
ftime | +0.814 |
borgh | +0.801 |
ater | +0.801 |
Neg logit contributions | |
Chaff | -0.712 |
Snape | -0.686 |
transcripts | -0.654 |
Misc | -0.642 |
tied | -0.641 |
Token | to |
Token ID | 284 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Chaff | +0.577 |
Snape | +0.560 |
transcripts | +0.532 |
tied | +0.530 |
loophole | +0.524 |
Neg logit contributions | |
ariat | -1.009 |
ombat | -0.716 |
ftime | -0.673 |
ater | -0.671 |
borgh | -0.666 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ariat | +1.132 |
ombat | +0.798 |
ftime | +0.757 |
ater | +0.754 |
borgh | +0.749 |
Neg logit contributions | |
Chaff | -0.620 |
Snape | -0.599 |
transcripts | -0.569 |
Misc | -0.557 |
tied | -0.556 |
Token | ch |
Token ID | 442 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
ariat | +0.058 |
ombat | +0.041 |
ftime | +0.039 |
borgh | +0.038 |
ater | +0.038 |
Neg logit contributions | |
Chaff | -0.034 |
Snape | -0.033 |
transcripts | -0.031 |
Misc | -0.031 |
tied | -0.031 |
Token | ow |
Token ID | 322 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Chaff | +0.010 |
Snape | +0.010 |
transcripts | +0.010 |
tied | +0.010 |
loophole | +0.010 |
Neg logit contributions | |
ariat | -0.013 |
ombat | -0.009 |
borgh | -0.008 |
ftime | -0.008 |
ater | -0.008 |
Token | hall |
Token ID | 6899 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ariat | +6.301 |
ombat | +4.687 |
ater | +4.499 |
ftime | +4.474 |
borgh | +4.446 |
Neg logit contributions | |
Chaff | -2.054 |
Snape | -1.956 |
transcripts | -1.832 |
tied | -1.758 |
loophole | -1.757 |
Token | , |
Token ID | 11 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Chaff | +0.991 |
Snape | +0.964 |
transcripts | +0.925 |
tied | +0.922 |
loophole | +0.905 |
Neg logit contributions | |
ariat | -1.576 |
ombat | -1.097 |
ftime | -1.025 |
borgh | -1.015 |
ater | -1.011 |
Token | known |
Token ID | 1900 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ariat | +0.514 |
ombat | +0.381 |
ater | +0.363 |
ftime | +0.362 |
borgh | +0.360 |
Neg logit contributions | |
Chaff | -0.188 |
Snape | -0.179 |
transcripts | -0.168 |
tied | -0.164 |
Misc | -0.162 |
Token | as |
Token ID | 355 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Chaff | +0.430 |
Snape | +0.416 |
transcripts | +0.397 |
tied | +0.390 |
loophole | +0.387 |
Neg logit contributions | |
ariat | -0.820 |
ombat | -0.582 |
ftime | -0.550 |
borgh | -0.544 |
ater | -0.543 |
Token | � |
Token ID | 564 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Chaff | +0.049 |
Snape | +0.048 |
transcripts | +0.045 |
Misc | +0.044 |
Porn | +0.044 |
Neg logit contributions | |
ariat | -0.092 |
ombat | -0.066 |
ftime | -0.062 |
ater | -0.062 |
borgh | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
Chaff | +0.216 |
Snape | +0.209 |
transcripts | +0.200 |
tied | +0.197 |
Misc | +0.196 |
Neg logit contributions | |
ariat | -0.316 |
ombat | -0.216 |
ftime | -0.204 |
ater | -0.201 |
borgh | -0.199 |
Token | twitter |
Token ID | 6956 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Chaff | +0.245 |
Snape | +0.235 |
transcripts | +0.223 |
tied | +0.219 |
Porn | +0.217 |
Neg logit contributions | |
ariat | -0.534 |
ombat | -0.386 |
ftime | -0.366 |
ater | -0.364 |
borgh | -0.359 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
Chaff | +2.721 |
Snape | +2.646 |
tied | +2.483 |
beard | +2.476 |
transcripts | +2.475 |
Neg logit contributions | |
ariat | -4.598 |
ombat | -3.221 |
ftime | -3.113 |
ater | -2.993 |
borgh | -2.982 |
Token | com |
Token ID | 785 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ariat | +0.085 |
ombat | +0.061 |
ftime | +0.058 |
ater | +0.058 |
borgh | +0.058 |
Neg logit contributions | |
Chaff | -0.038 |
Snape | -0.036 |
transcripts | -0.034 |
tied | -0.034 |
Misc | -0.033 |
Token | / |
Token ID | 14 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Chaff | +0.206 |
Snape | +0.195 |
transcripts | +0.178 |
tied | +0.172 |
Misc | +0.171 |
Neg logit contributions | |
ariat | -0.783 |
ombat | -0.596 |
ftime | -0.573 |
ater | -0.570 |
borgh | -0.565 |
Token | Eh |
Token ID | 43894 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
ariat | +1.596 |
ombat | +1.136 |
ftime | +1.077 |
ater | +1.076 |
borgh | +1.066 |
Neg logit contributions | |
Chaff | -0.794 |
Snape | -0.765 |
transcripts | -0.730 |
tied | -0.713 |
Misc | -0.706 |
Token | U |
Token ID | 52 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ariat | +5.537 |
ombat | +3.960 |
ater | +3.794 |
ftime | +3.759 |
borgh | +3.736 |
Neg logit contributions | |
Chaff | -2.686 |
Snape | -2.586 |
transcripts | -2.462 |
loophole | -2.416 |
Misc | -2.392 |
Token | g |
Token ID | 70 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ariat | +2.744 |
ombat | +1.948 |
ater | +1.848 |
ftime | +1.845 |
borgh | +1.830 |
Neg logit contributions | |
Chaff | -1.392 |
Snape | -1.343 |
transcripts | -1.281 |
tied | -1.250 |
loophole | -1.244 |
Token | I |
Token ID | 40 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ariat | +1.662 |
ombat | +1.186 |
ater | +1.125 |
ftime | +1.125 |
borgh | +1.115 |
Neg logit contributions | |
Chaff | -0.804 |
Snape | -0.774 |
transcripts | -0.738 |
tied | -0.720 |
loophole | -0.713 |
Token | x |
Token ID | 87 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ariat | +2.809 |
ombat | +1.988 |
ater | +1.889 |
ftime | +1.881 |
borgh | +1.866 |
Neg logit contributions | |
Chaff | -1.463 |
Snape | -1.411 |
transcripts | -1.348 |
tied | -1.312 |
loophole | -1.312 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ariat | +2.060 |
ombat | +1.468 |
ater | +1.393 |
ftime | +1.391 |
borgh | +1.379 |
Neg logit contributions | |
Chaff | -1.018 |
Snape | -0.981 |
transcripts | -0.936 |
tied | -0.912 |
loophole | -0.907 |
Token | drug |
Token ID | 2563 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ariat | +1.958 |
ombat | +1.401 |
ftime | +1.322 |
ater | +1.321 |
borgh | +1.315 |
Neg logit contributions | |
Chaff | -0.973 |
Snape | -0.941 |
transcripts | -0.895 |
tied | -0.875 |
loophole | -0.874 |
Token | addict |
Token ID | 19678 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
ariat | +1.368 |
ombat | +0.939 |
ftime | +0.885 |
borgh | +0.879 |
ater | +0.878 |
Neg logit contributions | |
Chaff | -0.884 |
Snape | -0.860 |
transcripts | -0.825 |
tied | -0.813 |
loophole | -0.812 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Chaff | +0.240 |
Snape | +0.233 |
transcripts | +0.223 |
tied | +0.222 |
loophole | +0.219 |
Neg logit contributions | |
ariat | -0.375 |
ombat | -0.258 |
ftime | -0.242 |
ater | -0.241 |
borgh | -0.240 |
Token | The |
Token ID | 383 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Chaff | +0.329 |
Snape | +0.316 |
Misc | +0.297 |
transcripts | +0.294 |
Porn | +0.294 |
Neg logit contributions | |
ariat | -0.707 |
ombat | -0.514 |
ftime | -0.487 |
ater | -0.480 |
borgh | -0.476 |
Token | common |
Token ID | 2219 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Chaff | +0.322 |
Snape | +0.311 |
transcripts | +0.301 |
loophole | +0.293 |
pornographic | +0.293 |
Neg logit contributions | |
ariat | -0.612 |
ombat | -0.438 |
ftime | -0.410 |
borgh | -0.410 |
adium | -0.405 |
Token | denomin |
Token ID | 31457 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
ariat | +2.181 |
ombat | +1.576 |
ater | +1.499 |
ftime | +1.497 |
borgh | +1.489 |
Neg logit contributions | |
Chaff | -0.969 |
Snape | -0.933 |
transcripts | -0.888 |
loophole | -0.865 |
tied | -0.861 |
Token | ator |
Token ID | 1352 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ariat | +3.539 |
ombat | +1.960 |
ater | +1.773 |
ftime | +1.751 |
borgh | +1.723 |
Neg logit contributions | |
Chaff | -4.678 |
Snape | -4.577 |
transcripts | -4.457 |
loophole | -4.389 |
tied | -4.386 |
Token | throughout |
Token ID | 3690 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ariat | +1.605 |
ombat | +1.137 |
ftime | +1.072 |
ater | +1.071 |
borgh | +1.064 |
Neg logit contributions | |
Chaff | -0.863 |
Snape | -0.836 |
transcripts | -0.798 |
tied | -0.786 |
loophole | -0.776 |
Token | these |
Token ID | 777 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ariat | +0.969 |
ombat | +0.690 |
ftime | +0.651 |
ater | +0.649 |
borgh | +0.646 |
Neg logit contributions | |
Chaff | -0.492 |
Snape | -0.474 |
transcripts | -0.456 |
tied | -0.445 |
Misc | -0.443 |
Token | disparate |
Token ID | 37433 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ariat | +0.841 |
ombat | +0.601 |
ftime | +0.566 |
borgh | +0.563 |
adium | +0.563 |
Neg logit contributions | |
Chaff | -0.422 |
Snape | -0.407 |
transcripts | -0.397 |
tied | -0.383 |
pornographic | -0.383 |
Token | roles |
Token ID | 9176 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ariat | +1.512 |
ombat | +1.084 |
ater | +1.021 |
ftime | +1.021 |
borgh | +1.015 |
Neg logit contributions | |
Chaff | -0.734 |
Snape | -0.708 |
transcripts | -0.684 |
pornographic | -0.661 |
tied | -0.660 |
Token | Uniform |
Token ID | 35712 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
ariat | +2.095 |
ombat | +1.518 |
ftime | +1.447 |
ater | +1.444 |
borgh | +1.436 |
Neg logit contributions | |
Chaff | -0.891 |
Snape | -0.853 |
transcripts | -0.806 |
tied | -0.790 |
Misc | -0.790 |
Token | Grid |
Token ID | 41339 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ariat | +4.888 |
ombat | +3.475 |
ater | +3.317 |
ftime | +3.270 |
borgh | +3.232 |
Neg logit contributions | |
Chaff | -2.521 |
Snape | -2.452 |
transcripts | -2.369 |
loophole | -2.295 |
pornographic | -2.292 |
Token | < |
Token ID | 27 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ariat | +1.156 |
ombat | +0.815 |
ftime | +0.772 |
borgh | +0.766 |
ater | +0.764 |
Neg logit contributions | |
Chaff | -0.615 |
Snape | -0.592 |
transcripts | -0.567 |
tied | -0.560 |
Misc | -0.558 |
Token | float |
Token ID | 12178 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ariat | +0.276 |
ombat | +0.199 |
ftime | +0.189 |
ater | +0.189 |
borgh | +0.188 |
Neg logit contributions | |
Chaff | -0.125 |
Snape | -0.119 |
transcripts | -0.112 |
Misc | -0.112 |
tied | -0.111 |
Token | > |
Token ID | 1875 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ariat | +3.392 |
ombat | +2.315 |
ater | +2.179 |
ftime | +2.171 |
borgh | +2.162 |
Neg logit contributions | |
Chaff | -2.187 |
Snape | -2.122 |
transcripts | -2.031 |
Misc | -1.994 |
tied | -1.991 |
Token | & |
Token ID | 1222 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ariat | +1.522 |
ombat | +1.073 |
ftime | +1.008 |
ater | +1.006 |
borgh | +1.002 |
Neg logit contributions | |
Chaff | -0.806 |
Snape | -0.781 |
transcripts | -0.750 |
tied | -0.739 |
Misc | -0.732 |
Token | density |
Token ID | 12109 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ariat | +5.681 |
ombat | +4.126 |
ater | +3.945 |
ftime | +3.928 |
borgh | +3.895 |
Neg logit contributions | |
Chaff | -2.432 |
Snape | -2.333 |
transcripts | -2.215 |
loophole | -2.147 |
tied | -2.139 |
Token | Grid |
Token ID | 41339 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ariat | +1.797 |
ombat | +1.251 |
ftime | +1.175 |
ater | +1.171 |
adium | +1.164 |
Neg logit contributions | |
Chaff | -1.032 |
Snape | -0.997 |
transcripts | -0.952 |
tied | -0.939 |
Misc | -0.933 |
Token | , |
Token ID | 837 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ariat | +1.078 |
ombat | +0.745 |
ftime | +0.697 |
borgh | +0.694 |
adium | +0.694 |
Neg logit contributions | |
Chaff | -0.637 |
Snape | -0.618 |
transcripts | -0.595 |
tied | -0.587 |
Misc | -0.583 |
Token | const |
Token ID | 1500 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ariat | +1.438 |
ombat | +1.041 |
ftime | +0.990 |
ater | +0.990 |
borgh | +0.983 |
Neg logit contributions | |
Chaff | -0.631 |
Snape | -0.604 |
transcripts | -0.573 |
tied | -0.561 |
Misc | -0.560 |
Token | Vector |
Token ID | 20650 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ariat | +4.389 |
ombat | +3.145 |
ater | +3.004 |
ftime | +2.980 |
borgh | +2.953 |
Neg logit contributions | |
Chaff | -2.084 |
Snape | -2.014 |
transcripts | -1.923 |
loophole | -1.859 |
pornographic | -1.853 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ariat | +0.717 |
ombat | +0.514 |
ftime | +0.489 |
ater | +0.488 |
borgh | +0.484 |
Neg logit contributions | |
Chaff | -0.350 |
Snape | -0.337 |
tied | -0.321 |
transcripts | -0.320 |
loophole | -0.312 |
Token | , |
Token ID | 11 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
ariat | +2.155 |
ombat | +1.555 |
ftime | +1.473 |
ater | +1.463 |
borgh | +1.458 |
Neg logit contributions | |
Chaff | -1.027 |
Snape | -0.987 |
transcripts | -0.942 |
tied | -0.922 |
pornographic | -0.915 |
Token | sang |
Token ID | 25889 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ariat | +0.373 |
ombat | +0.269 |
ftime | +0.255 |
ater | +0.255 |
borgh | +0.253 |
Neg logit contributions | |
Chaff | -0.177 |
Snape | -0.169 |
tied | -0.162 |
transcripts | -0.159 |
pornographic | -0.157 |
Token | and |
Token ID | 290 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
ariat | +1.625 |
ombat | +1.177 |
ftime | +1.110 |
adium | +1.102 |
ater | +1.100 |
Neg logit contributions | |
Chaff | -0.749 |
Snape | -0.717 |
transcripts | -0.685 |
tied | -0.675 |
pornographic | -0.671 |
Token | cl |
Token ID | 537 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ariat | +0.482 |
ombat | +0.344 |
ftime | +0.325 |
ater | +0.325 |
borgh | +0.323 |
Neg logit contributions | |
Chaff | -0.247 |
Snape | -0.237 |
tied | -0.227 |
transcripts | -0.225 |
pornographic | -0.219 |
Token | apped |
Token ID | 6320 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ariat | +2.231 |
ombat | +1.495 |
borgh | +1.400 |
ftime | +1.400 |
ater | +1.394 |
Neg logit contributions | |
Chaff | -1.586 |
Snape | -1.548 |
transcripts | -1.474 |
tied | -1.465 |
Misc | -1.446 |
Token | during |
Token ID | 1141 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
ariat | +5.209 |
ombat | +3.644 |
ater | +3.485 |
ftime | +3.445 |
borgh | +3.429 |
Neg logit contributions | |
Chaff | -2.827 |
Snape | -2.739 |
transcripts | -2.613 |
loophole | -2.569 |
Misc | -2.539 |
Token | high |
Token ID | 1029 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ariat | +0.424 |
ombat | +0.301 |
borgh | +0.283 |
ftime | +0.283 |
ater | +0.281 |
Neg logit contributions | |
Chaff | -0.230 |
Snape | -0.219 |
transcripts | -0.211 |
tied | -0.205 |
pornographic | -0.204 |
Token | - |
Token ID | 12 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ariat | +0.702 |
ombat | +0.492 |
ftime | +0.460 |
ater | +0.459 |
adium | +0.453 |
Neg logit contributions | |
Chaff | -0.430 |
Snape | -0.410 |
transcripts | -0.399 |
tied | -0.392 |
poetic | -0.389 |
Token | profile |
Token ID | 13317 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
ariat | +0.947 |
ombat | +0.691 |
ftime | +0.656 |
ater | +0.655 |
borgh | +0.648 |
Neg logit contributions | |
Chaff | -0.399 |
Snape | -0.379 |
transcripts | -0.359 |
tied | -0.351 |
Misc | -0.349 |
Token | Senate |
Token ID | 3845 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Chaff | +0.197 |
Snape | +0.185 |
transcripts | +0.181 |
tied | +0.174 |
Misc | +0.173 |
Neg logit contributions | |
ariat | -0.427 |
ombat | -0.313 |
ftime | -0.294 |
borgh | -0.292 |
ater | -0.291 |
Token | system |
Token ID | 1080 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ariat | +1.107 |
ombat | +0.788 |
ftime | +0.746 |
borgh | +0.743 |
ater | +0.742 |
Neg logit contributions | |
Chaff | -0.579 |
Snape | -0.560 |
transcripts | -0.536 |
loophole | -0.531 |
tied | -0.529 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ariat | +0.879 |
ombat | +0.600 |
ftime | +0.562 |
ater | +0.560 |
borgh | +0.560 |
Neg logit contributions | |
Chaff | -0.579 |
Snape | -0.561 |
transcripts | -0.540 |
tied | -0.535 |
loophole | -0.532 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ariat | +1.641 |
ombat | +1.170 |
ftime | +1.106 |
ater | +1.104 |
borgh | +1.096 |
Neg logit contributions | |
Chaff | -0.839 |
Snape | -0.809 |
transcripts | -0.772 |
tied | -0.761 |
loophole | -0.755 |
Token | increase |
Token ID | 2620 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ariat | +0.191 |
ombat | +0.138 |
ftime | +0.130 |
adium | +0.128 |
ater | +0.128 |
Neg logit contributions | |
Chaff | -0.097 |
Snape | -0.093 |
transcripts | -0.089 |
tied | -0.088 |
loophole | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ariat | +0.766 |
ombat | +0.531 |
ftime | +0.499 |
borgh | +0.497 |
ater | +0.496 |
Neg logit contributions | |
Chaff | -0.474 |
Snape | -0.458 |
transcripts | -0.443 |
tied | -0.436 |
loophole | -0.434 |
Token | odds |
Token ID | 10402 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
ariat | +2.139 |
ombat | +1.485 |
ftime | +1.403 |
ater | +1.402 |
borgh | +1.391 |
Neg logit contributions | |
Chaff | -1.275 |
Snape | -1.232 |
transcripts | -1.186 |
tied | -1.162 |
loophole | -1.161 |
Token | that |
Token ID | 326 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ariat | +5.392 |
ombat | +3.834 |
ater | +3.653 |
ftime | +3.636 |
borgh | +3.604 |
Neg logit contributions | |
Chaff | -2.674 |
Snape | -2.575 |
transcripts | -2.460 |
loophole | -2.389 |
tied | -2.388 |
Token | should |
Token ID | 815 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ariat | +2.428 |
ombat | +1.687 |
ftime | +1.584 |
ater | +1.582 |
borgh | +1.574 |
Neg logit contributions | |
Chaff | -1.492 |
Snape | -1.448 |
transcripts | -1.396 |
tied | -1.364 |
loophole | -1.358 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Chaff | +0.543 |
Snape | +0.530 |
transcripts | +0.512 |
Lynd | +0.503 |
Misc | +0.500 |
Neg logit contributions | |
ariat | -0.931 |
ombat | -0.654 |
borgh | -0.613 |
ftime | -0.610 |
ater | -0.606 |
Token | do |
Token ID | 466 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Chaff | +0.988 |
Snape | +0.967 |
transcripts | +0.917 |
tied | +0.904 |
loophole | +0.902 |
Neg logit contributions | |
ariat | -1.886 |
ombat | -1.352 |
ftime | -1.291 |
borgh | -1.267 |
adium | -1.262 |
Token | something |
Token ID | 1223 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ariat | +0.300 |
ombat | +0.214 |
ftime | +0.205 |
borgh | +0.203 |
ater | +0.202 |
Neg logit contributions | |
Chaff | -0.147 |
Snape | -0.143 |
transcripts | -0.136 |
loophole | -0.133 |
tied | -0.133 |
Token | vote |
Token ID | 3015 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ariat | +0.230 |
ombat | +0.164 |
ftime | +0.157 |
borgh | +0.155 |
ater | +0.155 |
Neg logit contributions | |
Chaff | -0.116 |
Snape | -0.112 |
transcripts | -0.106 |
tied | -0.105 |
Misc | -0.103 |
Token | accordingly |
Token ID | 16062 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Chaff | +0.559 |
Snape | +0.542 |
transcripts | +0.514 |
tied | +0.509 |
Misc | +0.503 |
Neg logit contributions | |
ariat | -0.921 |
ombat | -0.642 |
ftime | -0.604 |
borgh | -0.596 |
adium | -0.596 |
Token | . |
Token ID | 13 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Chaff | +0.592 |
Snape | +0.575 |
transcripts | +0.549 |
tied | +0.545 |
Lynd | +0.536 |
Neg logit contributions | |
ariat | -0.909 |
ombat | -0.622 |
ftime | -0.583 |
adium | -0.581 |
ater | -0.577 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ariat | +0.252 |
ombat | +0.182 |
ftime | +0.173 |
ater | +0.171 |
borgh | +0.171 |
Neg logit contributions | |
Chaff | -0.121 |
Snape | -0.116 |
transcripts | -0.108 |
Misc | -0.107 |
Porn | -0.107 |
Token | Story |
Token ID | 11605 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Chaff | +0.058 |
Snape | +0.056 |
transcripts | +0.053 |
Statement | +0.052 |
tied | +0.052 |
Neg logit contributions | |
ariat | -0.124 |
ombat | -0.089 |
ftime | -0.084 |
ater | -0.084 |
borgh | -0.083 |
Token | highlights |
Token ID | 11330 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
ariat | +3.331 |
ombat | +2.358 |
ater | +2.243 |
ftime | +2.239 |
borgh | +2.219 |
Neg logit contributions | |
Chaff | -1.700 |
Snape | -1.640 |
transcripts | -1.561 |
loophole | -1.523 |
tied | -1.519 |
Token | Police |
Token ID | 4287 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ariat | +5.304 |
ombat | +3.758 |
ater | +3.602 |
ftime | +3.551 |
borgh | +3.547 |
Neg logit contributions | |
Chaff | -2.604 |
Snape | -2.525 |
transcripts | -2.439 |
tied | -2.382 |
loophole | -2.380 |
Token | chief |
Token ID | 4039 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
Chaff | +0.095 |
Snape | +0.091 |
transcripts | +0.088 |
tied | +0.086 |
loophole | +0.085 |
Neg logit contributions | |
ariat | -0.188 |
ombat | -0.134 |
ftime | -0.127 |
ater | -0.126 |
adium | -0.126 |
Token | vows |
Token ID | 36605 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Chaff | +0.217 |
Snape | +0.208 |
transcripts | +0.199 |
tied | +0.195 |
Misc | +0.192 |
Neg logit contributions | |
ariat | -0.458 |
ombat | -0.330 |
ater | -0.312 |
ftime | -0.312 |
adium | -0.309 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Chaff | +0.473 |
Snape | +0.453 |
transcripts | +0.435 |
tied | +0.424 |
loophole | +0.423 |
Neg logit contributions | |
ariat | -0.949 |
ombat | -0.686 |
ftime | -0.651 |
ater | -0.646 |
borgh | -0.644 |
Token | suspect |
Token ID | 4099 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ariat | +0.962 |
ombat | +0.684 |
ftime | +0.643 |
ater | +0.643 |
borgh | +0.639 |
Neg logit contributions | |
Chaff | -0.493 |
Snape | -0.475 |
transcripts | -0.459 |
tied | -0.449 |
loophole | -0.446 |
Token | eth |
Token ID | 2788 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ariat | +1.908 |
ombat | +1.204 |
ftime | +1.104 |
ater | +1.089 |
borgh | +1.088 |
Neg logit contributions | |
Chaff | -1.771 |
Snape | -1.724 |
transcripts | -1.670 |
tied | -1.643 |
Porn | -1.635 |
Token | ox |
Token ID | 1140 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ariat | +5.321 |
ombat | +3.552 |
ater | +3.344 |
ftime | +3.327 |
borgh | +3.293 |
Neg logit contributions | |
Chaff | -3.898 |
Snape | -3.785 |
transcripts | -3.647 |
loophole | -3.575 |
tied | -3.568 |
Token | ym |
Token ID | 4948 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ariat | +2.061 |
ombat | +1.563 |
ftime | +1.500 |
borgh | +1.491 |
ater | +1.489 |
Neg logit contributions | |
Chaff | -0.494 |
Snape | -0.467 |
transcripts | -0.427 |
tied | -0.411 |
Lynd | -0.407 |
Token | ethyl |
Token ID | 21610 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ariat | +2.231 |
ombat | +1.411 |
ftime | +1.291 |
ater | +1.286 |
borgh | +1.268 |
Neg logit contributions | |
Chaff | -2.057 |
Snape | -2.007 |
transcripts | -1.949 |
tied | -1.921 |
beard | -1.903 |
Token | phen |
Token ID | 31024 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ariat | +3.389 |
ombat | +2.294 |
ater | +2.153 |
ftime | +2.148 |
borgh | +2.125 |
Neg logit contributions | |
Chaff | -2.322 |
Snape | -2.252 |
transcripts | -2.172 |
tied | -2.126 |
loophole | -2.120 |
Token | yl |
Token ID | 2645 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
ariat | +2.293 |
ombat | +1.621 |
ftime | +1.535 |
ater | +1.520 |
borgh | +1.508 |
Neg logit contributions | |
Chaff | -1.173 |
Snape | -1.130 |
transcripts | -1.079 |
tied | -1.061 |
Lynd | -1.055 |
Token | )- |
Token ID | 13219 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
ariat | +4.588 |
ombat | +3.056 |
ater | +2.877 |
ftime | +2.860 |
borgh | +2.835 |
Neg logit contributions | |
Chaff | -3.377 |
Snape | -3.279 |
transcripts | -3.156 |
loophole | -3.094 |
tied | -3.085 |
Token | 2 |
Token ID | 17 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ariat | +2.233 |
ombat | +1.600 |
ftime | +1.520 |
ater | +1.518 |
borgh | +1.505 |
Neg logit contributions | |
Chaff | -1.046 |
Snape | -1.005 |
transcripts | -0.963 |
tied | -0.937 |
Misc | -0.926 |
Token | - |
Token ID | 12 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ariat | +1.872 |
ombat | +1.252 |
ftime | +1.172 |
ater | +1.159 |
borgh | +1.153 |
Neg logit contributions | |
Chaff | -1.363 |
Snape | -1.322 |
transcripts | -1.286 |
tied | -1.254 |
Misc | -1.247 |
Token | ethyl |
Token ID | 21610 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ariat | +1.445 |
ombat | +0.981 |
ftime | +0.918 |
ater | +0.915 |
borgh | +0.902 |
Neg logit contributions | |
Chaff | -0.968 |
Snape | -0.936 |
transcripts | -0.904 |
tied | -0.889 |
loophole | -0.883 |
Token | - |
Token ID | 12 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
ariat | +2.481 |
ombat | +1.717 |
ater | +1.608 |
ftime | +1.607 |
borgh | +1.590 |
Neg logit contributions | |
Chaff | -1.536 |
Snape | -1.485 |
transcripts | -1.433 |
tied | -1.401 |
Misc | -1.396 |
Token | other |
Token ID | 584 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Chaff | +0.210 |
Snape | +0.202 |
transcripts | +0.195 |
pornographic | +0.192 |
Porn | +0.191 |
Neg logit contributions | |
ariat | -0.412 |
ombat | -0.293 |
ftime | -0.278 |
borgh | -0.278 |
adium | -0.273 |
Token | possibility |
Token ID | 5885 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
ariat | +0.450 |
ombat | +0.324 |
ftime | +0.307 |
borgh | +0.307 |
ater | +0.306 |
Neg logit contributions | |
Chaff | -0.213 |
Snape | -0.204 |
transcripts | -0.196 |
pornographic | -0.192 |
loophole | -0.192 |
Token | that |
Token ID | 326 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Chaff | +0.169 |
Snape | +0.163 |
transcripts | +0.155 |
tied | +0.153 |
Misc | +0.151 |
Neg logit contributions | |
ariat | -0.337 |
ombat | -0.241 |
ftime | -0.229 |
ater | -0.228 |
borgh | -0.227 |
Token | comes |
Token ID | 2058 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ariat | +1.562 |
ombat | +1.114 |
ater | +1.059 |
ftime | +1.058 |
borgh | +1.050 |
Neg logit contributions | |
Chaff | -0.768 |
Snape | -0.741 |
transcripts | -0.706 |
tied | -0.689 |
Misc | -0.686 |
Token | to |
Token ID | 284 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
Chaff | +0.905 |
Snape | +0.885 |
transcripts | +0.841 |
tied | +0.836 |
needing | +0.810 |
Neg logit contributions | |
ariat | -1.882 |
ombat | -1.351 |
ftime | -1.281 |
ater | -1.264 |
borgh | -1.263 |
Token | mind |
Token ID | 2000 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ariat | +0.439 |
ombat | +0.309 |
ater | +0.293 |
ftime | +0.292 |
borgh | +0.289 |
Neg logit contributions | |
Chaff | -0.244 |
Snape | -0.235 |
transcripts | -0.225 |
tied | -0.220 |
pornographic | -0.219 |
Token | is |
Token ID | 318 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ariat | +5.082 |
ombat | +3.562 |
ater | +3.381 |
ftime | +3.354 |
borgh | +3.349 |
Neg logit contributions | |
Chaff | -2.824 |
Snape | -2.711 |
transcripts | -2.601 |
loophole | -2.548 |
Misc | -2.537 |
Token | that |
Token ID | 326 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Chaff | +0.772 |
Snape | +0.750 |
transcripts | +0.709 |
tied | +0.701 |
Porn | +0.700 |
Neg logit contributions | |
ariat | -1.711 |
ombat | -1.237 |
ftime | -1.186 |
borgh | -1.178 |
ater | -1.178 |
Token | having |
Token ID | 1719 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Chaff | +0.476 |
Snape | +0.463 |
transcripts | +0.438 |
Porn | +0.436 |
pornographic | +0.433 |
Neg logit contributions | |
ariat | -0.980 |
ombat | -0.705 |
ftime | -0.670 |
borgh | -0.668 |
ater | -0.665 |
Token | a |
Token ID | 257 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Chaff | +0.658 |
Snape | +0.642 |
transcripts | +0.614 |
pornographic | +0.608 |
tied | +0.607 |
Neg logit contributions | |
ariat | -1.290 |
ombat | -0.916 |
ftime | -0.873 |
borgh | -0.868 |
ater | -0.867 |
Token | video |
Token ID | 2008 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ariat | +0.157 |
ombat | +0.113 |
ftime | +0.107 |
ater | +0.106 |
borgh | +0.106 |
Neg logit contributions | |
Chaff | -0.074 |
Snape | -0.071 |
transcripts | -0.068 |
tied | -0.067 |
pornographic | -0.067 |
Token | n |
Token ID | 77 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
ariat | +0.556 |
ombat | +0.420 |
ater | +0.404 |
ftime | +0.403 |
borgh | +0.400 |
Neg logit contributions | |
Chaff | -0.147 |
Snape | -0.139 |
transcripts | -0.129 |
tied | -0.123 |
loophole | -0.122 |
Token | ighter |
Token ID | 4799 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ariat | +0.449 |
ombat | +0.287 |
ftime | +0.270 |
borgh | +0.266 |
adium | +0.261 |
Neg logit contributions | |
Chaff | -0.387 |
Snape | -0.380 |
transcripts | -0.363 |
tied | -0.362 |
beard | -0.361 |
Token | initially |
Token ID | 7317 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Chaff | +0.049 |
Snape | +0.048 |
tied | +0.045 |
transcripts | +0.045 |
pornographic | +0.044 |
Neg logit contributions | |
ariat | -0.091 |
ombat | -0.065 |
ftime | -0.062 |
ater | -0.061 |
borgh | -0.061 |
Token | come |
Token ID | 1282 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ariat | +1.432 |
ombat | +1.023 |
ftime | +0.975 |
ater | +0.966 |
borgh | +0.960 |
Neg logit contributions | |
Chaff | -0.720 |
Snape | -0.698 |
tied | -0.661 |
transcripts | -0.660 |
pornographic | -0.649 |
Token | to |
Token ID | 284 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Chaff | +0.430 |
Snape | +0.425 |
tied | +0.407 |
transcripts | +0.400 |
needing | +0.392 |
Neg logit contributions | |
ariat | -1.059 |
ombat | -0.775 |
ftime | -0.743 |
borgh | -0.724 |
ater | -0.722 |
Token | mind |
Token ID | 2000 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
ariat | +0.319 |
ombat | +0.224 |
ftime | +0.213 |
ater | +0.212 |
borgh | +0.211 |
Neg logit contributions | |
Chaff | -0.174 |
Snape | -0.171 |
transcripts | -0.161 |
tied | -0.159 |
Lynd | -0.158 |
Token | ? |
Token ID | 30 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ariat | +4.945 |
ombat | +3.422 |
ater | +3.232 |
ftime | +3.223 |
borgh | +3.189 |
Neg logit contributions | |
Chaff | -2.982 |
Snape | -2.893 |
transcripts | -2.768 |
tied | -2.720 |
loophole | -2.696 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ariat | +1.404 |
ombat | +1.010 |
ftime | +0.963 |
ater | +0.952 |
borgh | +0.949 |
Neg logit contributions | |
Chaff | -0.667 |
Snape | -0.647 |
transcripts | -0.600 |
Misc | -0.596 |
Porn | -0.595 |
Token |
|
Token ID | 198 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ariat | +0.686 |
ombat | +0.487 |
ater | +0.461 |
ftime | +0.461 |
borgh | +0.456 |
Neg logit contributions | |
Chaff | -0.353 |
Snape | -0.341 |
transcripts | -0.325 |
tied | -0.317 |
Misc | -0.316 |
Token | T |
Token ID | 51 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Chaff | +0.254 |
Snape | +0.246 |
TPS | +0.240 |
tied | +0.238 |
transcripts | +0.236 |
Neg logit contributions | |
ariat | -0.345 |
ombat | -0.228 |
ftime | -0.220 |
ater | -0.211 |
borgh | -0.210 |
Token | K |
Token ID | 42 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
Chaff | +0.127 |
Snape | +0.124 |
transcripts | +0.118 |
tied | +0.118 |
Misc | +0.116 |
Neg logit contributions | |
ariat | -0.197 |
ombat | -0.134 |
ftime | -0.132 |
ater | -0.126 |
borgh | -0.126 |
Token | However |
Token ID | 4864 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
ariat | +0.550 |
ombat | +0.397 |
ftime | +0.376 |
ater | +0.373 |
borgh | +0.372 |
Neg logit contributions | |
Chaff | -0.248 |
Snape | -0.238 |
transcripts | -0.225 |
tied | -0.221 |
Statement | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
ariat | +0.323 |
ombat | +0.210 |
ater | +0.196 |
ftime | +0.195 |
borgh | +0.193 |
Neg logit contributions | |
Chaff | -0.266 |
Snape | -0.259 |
transcripts | -0.251 |
tied | -0.246 |
loophole | -0.246 |
Token | Flynn |
Token ID | 14654 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
ariat | +0.039 |
ombat | +0.028 |
ftime | +0.026 |
borgh | +0.026 |
adium | +0.026 |
Neg logit contributions | |
Chaff | -0.020 |
Snape | -0.019 |
transcripts | -0.018 |
Misc | -0.018 |
tied | -0.018 |
Token | recently |
Token ID | 2904 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Chaff | +0.020 |
Snape | +0.019 |
transcripts | +0.019 |
tied | +0.018 |
Misc | +0.018 |
Neg logit contributions | |
ariat | -0.042 |
ombat | -0.030 |
ftime | -0.028 |
ater | -0.028 |
borgh | -0.028 |
Token | co |
Token ID | 763 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ariat | +0.806 |
ombat | +0.585 |
ftime | +0.555 |
ater | +0.554 |
borgh | +0.552 |
Neg logit contributions | |
Chaff | -0.357 |
Snape | -0.342 |
transcripts | -0.326 |
tied | -0.322 |
loophole | -0.315 |
Token | pped |
Token ID | 1496 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
ariat | +1.024 |
ombat | +0.689 |
ater | +0.648 |
ftime | +0.640 |
borgh | +0.634 |
Neg logit contributions | |
Chaff | -0.745 |
Snape | -0.722 |
transcripts | -0.696 |
loophole | -0.683 |
pornographic | -0.679 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ariat | +5.067 |
ombat | +3.566 |
ater | +3.399 |
ftime | +3.367 |
borgh | +3.337 |
Neg logit contributions | |
Chaff | -2.687 |
Snape | -2.610 |
transcripts | -2.473 |
loophole | -2.431 |
Misc | -2.408 |
Token | inadvertently |
Token ID | 29243 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ariat | +0.723 |
ombat | +0.527 |
ftime | +0.500 |
ater | +0.498 |
borgh | +0.496 |
Neg logit contributions | |
Chaff | -0.317 |
Snape | -0.303 |
transcripts | -0.290 |
tied | -0.282 |
Misc | -0.280 |
Token | sharing |
Token ID | 7373 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Chaff | +0.166 |
Snape | +0.159 |
transcripts | +0.151 |
tied | +0.148 |
pornographic | +0.146 |
Neg logit contributions | |
ariat | -0.437 |
ombat | -0.323 |
ftime | -0.307 |
ater | -0.306 |
borgh | -0.305 |
Token | some |
Token ID | 617 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Chaff | +0.050 |
Snape | +0.048 |
transcripts | +0.046 |
tied | +0.044 |
pornographic | +0.044 |
Neg logit contributions | |
ariat | -0.107 |
ombat | -0.078 |
ftime | -0.074 |
ater | -0.073 |
borgh | -0.073 |
Token | fake |
Token ID | 8390 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Chaff | +0.741 |
Snape | +0.706 |
transcripts | +0.682 |
tied | +0.662 |
pornographic | +0.658 |
Neg logit contributions | |
ariat | -1.706 |
ombat | -1.257 |
ftime | -1.184 |
adium | -1.177 |
ater | -1.175 |
Token | atta |
Token ID | 25014 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Chaff | +0.855 |
Snape | +0.837 |
transcripts | +0.811 |
tied | +0.809 |
beard | +0.799 |
Neg logit contributions | |
ariat | -0.830 |
ombat | -0.518 |
ftime | -0.472 |
borgh | -0.469 |
adium | -0.456 |
Token | had |
Token ID | 550 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
Chaff | +0.377 |
Snape | +0.364 |
tied | +0.352 |
transcripts | +0.350 |
Misc | +0.343 |
Neg logit contributions | |
ariat | -0.681 |
ombat | -0.482 |
borgh | -0.454 |
ftime | -0.454 |
adium | -0.451 |
Token | kept |
Token ID | 4030 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
Chaff | +0.188 |
Snape | +0.181 |
tied | +0.175 |
transcripts | +0.174 |
loophole | +0.169 |
Neg logit contributions | |
ariat | -0.338 |
ombat | -0.239 |
ater | -0.227 |
borgh | -0.227 |
ftime | -0.226 |
Token | ab |
Token ID | 450 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ariat | +2.648 |
ombat | +1.881 |
ftime | +1.785 |
borgh | +1.779 |
ater | +1.772 |
Neg logit contributions | |
Chaff | -1.438 |
Snape | -1.389 |
transcripts | -1.339 |
tied | -1.310 |
Misc | -1.302 |
Token | re |
Token ID | 260 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ariat | +1.491 |
ombat | +1.085 |
borgh | +1.052 |
ftime | +1.035 |
adium | +1.029 |
Neg logit contributions | |
Chaff | -0.616 |
Snape | -0.595 |
transcripts | -0.561 |
tied | -0.558 |
Porn | -0.549 |
Token | ast |
Token ID | 459 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
Chaff | +1.776 |
Snape | +1.745 |
tied | +1.709 |
transcripts | +1.697 |
beard | +1.689 |
Neg logit contributions | |
ariat | -1.474 |
ombat | -0.882 |
borgh | -0.784 |
ftime | -0.765 |
adium | -0.759 |
Token | of |
Token ID | 286 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ariat | +4.683 |
ombat | +3.184 |
ater | +3.004 |
ftime | +2.983 |
adium | +2.940 |
Neg logit contributions | |
Chaff | -3.025 |
Snape | -2.928 |
transcripts | -2.797 |
loophole | -2.751 |
Misc | -2.747 |
Token | these |
Token ID | 777 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ariat | +0.679 |
ombat | +0.484 |
borgh | +0.462 |
ftime | +0.460 |
ater | +0.456 |
Neg logit contributions | |
Chaff | -0.361 |
Snape | -0.347 |
transcripts | -0.336 |
tied | -0.326 |
Misc | -0.325 |
Token | developments |
Token ID | 13312 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
Chaff | +0.049 |
Snape | +0.047 |
transcripts | +0.046 |
tied | +0.045 |
loophole | +0.044 |
Neg logit contributions | |
ariat | -0.108 |
ombat | -0.080 |
borgh | -0.076 |
ftime | -0.076 |
adium | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
Chaff | +0.042 |
Snape | +0.041 |
transcripts | +0.039 |
tied | +0.039 |
loophole | +0.038 |
Neg logit contributions | |
ariat | -0.067 |
ombat | -0.046 |
ater | -0.043 |
ftime | -0.043 |
borgh | -0.043 |
Token | although |
Token ID | 3584 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ariat | +0.346 |
ombat | +0.253 |
ftime | +0.240 |
borgh | +0.240 |
ater | +0.239 |
Neg logit contributions | |
Chaff | -0.151 |
Snape | -0.145 |
transcripts | -0.139 |
tied | -0.136 |
needing | -0.133 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Chaff | +0.419 |
Snape | +0.406 |
transcripts | +0.390 |
tied | +0.380 |
loophole | +0.378 |
Neg logit contributions | |
ariat | -0.840 |
ombat | -0.609 |
ftime | -0.580 |
borgh | -0.579 |
ater | -0.571 |
Token | concern |
Token ID | 2328 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
Chaff | +0.875 |
Snape | +0.849 |
transcripts | +0.810 |
loophole | +0.792 |
tied | +0.784 |
Neg logit contributions | |
ariat | -2.206 |
ombat | -1.634 |
ftime | -1.575 |
borgh | -1.554 |
ater | -1.531 |
Token | — |
Token ID | 960 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
Chaff | +0.173 |
Snape | +0.169 |
tied | +0.162 |
transcripts | +0.162 |
loophole | +0.159 |
Neg logit contributions | |
ariat | -0.302 |
ombat | -0.212 |
ftime | -0.200 |
ater | -0.199 |
borgh | -0.198 |
Token | in |
Token ID | 259 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
Chaff | +0.018 |
Snape | +0.017 |
transcripts | +0.016 |
tied | +0.016 |
Misc | +0.016 |
Neg logit contributions | |
ariat | -0.031 |
ombat | -0.022 |
ftime | -0.021 |
ater | -0.021 |
borgh | -0.021 |
Token | this |
Token ID | 428 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ariat | +0.512 |
ombat | +0.367 |
ater | +0.349 |
ftime | +0.348 |
borgh | +0.348 |
Neg logit contributions | |
Chaff | -0.244 |
Snape | -0.236 |
transcripts | -0.226 |
tied | -0.218 |
loophole | -0.218 |
Token | case |
Token ID | 1339 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ariat | +0.647 |
ombat | +0.457 |
ftime | +0.432 |
borgh | +0.430 |
ater | +0.427 |
Neg logit contributions | |
Chaff | -0.378 |
Snape | -0.367 |
transcripts | -0.354 |
tied | -0.347 |
loophole | -0.346 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ariat | +4.724 |
ombat | +3.228 |
ater | +3.053 |
ftime | +3.034 |
borgh | +3.007 |
Neg logit contributions | |
Chaff | -2.966 |
Snape | -2.871 |
transcripts | -2.752 |
Misc | -2.698 |
loophole | -2.687 |
Token | over |
Token ID | 625 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
Chaff | +0.299 |
Snape | +0.289 |
transcripts | +0.275 |
tied | +0.271 |
loophole | +0.268 |
Neg logit contributions | |
ariat | -0.623 |
ombat | -0.451 |
ftime | -0.429 |
ater | -0.428 |
borgh | -0.426 |
Token | Yaz |
Token ID | 35856 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Chaff | +0.304 |
Snape | +0.294 |
transcripts | +0.283 |
tied | +0.274 |
pornographic | +0.274 |
Neg logit contributions | |
ariat | -0.577 |
ombat | -0.412 |
ftime | -0.389 |
borgh | -0.388 |
ater | -0.384 |
Token | idi |
Token ID | 19830 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Chaff | +0.388 |
Snape | +0.367 |
transcripts | +0.359 |
tied | +0.354 |
Misc | +0.345 |
Neg logit contributions | |
ariat | -0.956 |
ombat | -0.690 |
ftime | -0.663 |
borgh | -0.658 |
adium | -0.650 |
Token | refugees |
Token ID | 8015 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ariat | +1.520 |
ombat | +1.080 |
ftime | +1.026 |
ater | +1.022 |
borgh | +1.016 |
Neg logit contributions | |
Chaff | -0.785 |
Snape | -0.755 |
transcripts | -0.723 |
tied | -0.707 |
loophole | -0.705 |
Token | clever |
Token ID | 14169 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
Chaff | +0.138 |
Snape | +0.134 |
transcripts | +0.128 |
tied | +0.125 |
loophole | +0.125 |
Neg logit contributions | |
ariat | -0.254 |
ombat | -0.180 |
ftime | -0.171 |
adium | -0.169 |
ater | -0.168 |
Token | answers |
Token ID | 7429 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Chaff | +0.019 |
Snape | +0.019 |
transcripts | +0.018 |
loophole | +0.018 |
tied | +0.018 |
Neg logit contributions | |
ariat | -0.036 |
ombat | -0.025 |
ftime | -0.024 |
ater | -0.024 |
adium | -0.024 |
Token | may |
Token ID | 743 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ariat | +1.704 |
ombat | +1.199 |
ftime | +1.133 |
ater | +1.128 |
borgh | +1.124 |
Neg logit contributions | |
Chaff | -0.984 |
Snape | -0.954 |
transcripts | -0.912 |
tied | -0.902 |
loophole | -0.886 |
Token | come |
Token ID | 1282 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ariat | +0.690 |
ombat | +0.489 |
ater | +0.459 |
adium | +0.459 |
ftime | +0.458 |
Neg logit contributions | |
Chaff | -0.374 |
Snape | -0.364 |
transcripts | -0.347 |
tied | -0.347 |
loophole | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
Chaff | +0.731 |
Snape | +0.720 |
transcripts | +0.678 |
tied | +0.677 |
poetic | +0.661 |
Neg logit contributions | |
ariat | -1.500 |
ombat | -1.100 |
ftime | -1.022 |
borgh | -1.018 |
ater | -1.015 |
Token | mind |
Token ID | 2000 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
ariat | +0.429 |
ombat | +0.306 |
ftime | +0.288 |
ater | +0.287 |
adium | +0.286 |
Neg logit contributions | |
Chaff | -0.237 |
Snape | -0.230 |
transcripts | -0.219 |
tied | -0.214 |
poetic | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
ariat | +4.634 |
ombat | +3.166 |
ater | +2.986 |
ftime | +2.973 |
borgh | +2.946 |
Neg logit contributions | |
Chaff | -3.017 |
Snape | -2.926 |
transcripts | -2.811 |
tied | -2.753 |
loophole | -2.745 |
Token | Obs |
Token ID | 11086 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ariat | +0.417 |
ombat | +0.303 |
ftime | +0.290 |
ater | +0.286 |
borgh | +0.283 |
Neg logit contributions | |
Chaff | -0.193 |
Snape | -0.186 |
transcripts | -0.172 |
Porn | -0.172 |
Misc | -0.171 |
Token | essed |
Token ID | 6676 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ariat | +1.181 |
ombat | +0.739 |
ftime | +0.693 |
borgh | +0.689 |
ater | +0.683 |
Neg logit contributions | |
Chaff | -1.108 |
Snape | -1.086 |
transcripts | -1.045 |
tied | -1.030 |
Lynd | -1.027 |
Token | chef |
Token ID | 21221 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ariat | +0.672 |
ombat | +0.493 |
ftime | +0.474 |
adium | +0.470 |
ater | +0.470 |
Neg logit contributions | |
Chaff | -0.258 |
Snape | -0.249 |
transcripts | -0.233 |
tied | -0.227 |
pornographic | -0.226 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Chaff | +0.374 |
Snape | +0.363 |
transcripts | +0.343 |
tied | +0.337 |
Lynd | +0.336 |
Neg logit contributions | |
ariat | -0.723 |
ombat | -0.517 |
ftime | -0.488 |
ater | -0.486 |
adium | -0.484 |
Token | � |
Token ID | 247 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ariat | +0.856 |
ombat | +0.508 |
ftime | +0.468 |
ater | +0.457 |
adium | +0.455 |
Neg logit contributions | |
Chaff | -0.921 |
Snape | -0.889 |
transcripts | -0.868 |
tied | -0.863 |
Misc | -0.853 |
Token | d |
Token ID | 67 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ariat | +0.697 |
ombat | +0.500 |
ftime | +0.472 |
ater | +0.466 |
borgh | +0.465 |
Neg logit contributions | |
Chaff | -0.332 |
Snape | -0.319 |
transcripts | -0.301 |
tied | -0.300 |
beard | -0.297 |
Token | ever |
Token ID | 1683 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
Chaff | +0.431 |
Snape | +0.424 |
tied | +0.407 |
transcripts | +0.401 |
poetic | +0.394 |
Neg logit contributions | |
ariat | -0.643 |
ombat | -0.440 |
ftime | -0.412 |
adium | -0.404 |
ater | -0.404 |
Token | seen |
Token ID | 1775 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ariat | +0.525 |
ombat | +0.367 |
ftime | +0.344 |
ater | +0.343 |
adium | +0.341 |
Neg logit contributions | |
Chaff | -0.316 |
Snape | -0.309 |
transcripts | -0.294 |
tied | -0.293 |
loophole | -0.285 |
Token | or |
Token ID | 393 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ariat | +1.414 |
ombat | +0.968 |
ater | +0.904 |
ftime | +0.904 |
adium | +0.896 |
Neg logit contributions | |
Chaff | -0.954 |
Snape | -0.926 |
transcripts | -0.885 |
tied | -0.874 |
pornographic | -0.865 |
Token | imagined |
Token ID | 15758 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Chaff | +0.116 |
Snape | +0.114 |
tied | +0.109 |
transcripts | +0.108 |
poetic | +0.105 |
Neg logit contributions | |
ariat | -0.199 |
ombat | -0.141 |
ftime | -0.132 |
adium | -0.132 |
ater | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
ariat | +4.448 |
ombat | +2.991 |
ater | +2.815 |
ftime | +2.802 |
borgh | +2.775 |
Neg logit contributions | |
Chaff | -3.128 |
Snape | -3.036 |
transcripts | -2.925 |
tied | -2.862 |
loophole | -2.860 |
Token | � |
Token ID | 447 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
ariat | +0.175 |
ombat | +0.127 |
ftime | +0.121 |
ater | +0.120 |
borgh | +0.119 |
Neg logit contributions | |
Chaff | -0.079 |
Snape | -0.076 |
transcripts | -0.071 |
Misc | -0.070 |
Porn | -0.069 |
Token | � |
Token ID | 251 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ariat | +0.350 |
ombat | +0.232 |
ater | +0.217 |
ftime | +0.216 |
adium | +0.214 |
Neg logit contributions | |
Chaff | -0.263 |
Snape | -0.255 |
transcripts | -0.246 |
tied | -0.242 |
loophole | -0.241 |
Token | The |
Token ID | 383 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Chaff | +0.148 |
Snape | +0.142 |
transcripts | +0.132 |
Misc | +0.130 |
Porn | +0.130 |
Neg logit contributions | |
ariat | -0.320 |
ombat | -0.232 |
ftime | -0.221 |
ater | -0.219 |
borgh | -0.217 |
Token | point |
Token ID | 966 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ariat | +0.771 |
ombat | +0.548 |
ftime | +0.520 |
ater | +0.517 |
borgh | +0.516 |
Neg logit contributions | |
Chaff | -0.398 |
Snape | -0.384 |
transcripts | -0.369 |
loophole | -0.359 |
tied | -0.357 |
Token | t |
Token ID | 83 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ariat | +3.191 |
ombat | +2.241 |
ater | +2.137 |
ftime | +2.122 |
borgh | +2.103 |
Neg logit contributions | |
Chaff | -1.725 |
Snape | -1.665 |
transcripts | -1.591 |
loophole | -1.555 |
tied | -1.549 |
Token | weet |
Token ID | 7277 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ariat | +0.975 |
ombat | +0.641 |
ftime | +0.601 |
borgh | +0.591 |
adium | +0.581 |
Neg logit contributions | |
Chaff | -0.791 |
Snape | -0.771 |
transcripts | -0.746 |
tied | -0.734 |
beard | -0.726 |
Token | / |
Token ID | 14 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
ariat | +1.187 |
ombat | +0.826 |
ater | +0.778 |
ftime | +0.777 |
borgh | +0.772 |
Neg logit contributions | |
Chaff | -0.707 |
Snape | -0.682 |
transcripts | -0.655 |
tied | -0.641 |
loophole | -0.638 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
ariat | +2.005 |
ombat | +1.426 |
ater | +1.347 |
ftime | +1.347 |
borgh | +1.339 |
Neg logit contributions | |
Chaff | -1.034 |
Snape | -0.994 |
transcripts | -0.953 |
tied | -0.929 |
loophole | -0.922 |
Token | Story |
Token ID | 11605 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ariat | +0.113 |
ombat | +0.081 |
ftime | +0.077 |
ater | +0.076 |
borgh | +0.076 |
Neg logit contributions | |
Chaff | -0.052 |
Snape | -0.051 |
transcripts | -0.048 |
Statement | -0.047 |
tied | -0.047 |
Token | highlights |
Token ID | 11330 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ariat | +3.177 |
ombat | +2.257 |
ater | +2.146 |
ftime | +2.139 |
borgh | +2.121 |
Neg logit contributions | |
Chaff | -1.603 |
Snape | -1.545 |
transcripts | -1.474 |
tied | -1.435 |
loophole | -1.434 |
Token | Secretary |
Token ID | 4986 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ariat | +4.994 |
ombat | +3.540 |
ater | +3.390 |
ftime | +3.348 |
borgh | +3.339 |
Neg logit contributions | |
Chaff | -2.465 |
Snape | -2.388 |
transcripts | -2.301 |
tied | -2.246 |
loophole | -2.244 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ariat | +0.609 |
ombat | +0.429 |
ater | +0.402 |
ftime | +0.401 |
borgh | +0.401 |
Neg logit contributions | |
Chaff | -0.348 |
Snape | -0.336 |
transcripts | -0.322 |
tied | -0.315 |
Misc | -0.313 |
Token | Defense |
Token ID | 5947 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
ariat | +0.646 |
ombat | +0.438 |
ftime | +0.411 |
ater | +0.407 |
borgh | +0.406 |
Neg logit contributions | |
Chaff | -0.450 |
Snape | -0.434 |
transcripts | -0.419 |
Misc | -0.412 |
tied | -0.410 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ariat | +0.414 |
ombat | +0.286 |
ater | +0.267 |
ftime | +0.267 |
borgh | +0.264 |
Neg logit contributions | |
Chaff | -0.263 |
Snape | -0.255 |
transcripts | -0.247 |
tied | -0.241 |
loophole | -0.239 |
Token | Hag |
Token ID | 21375 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ariat | +0.075 |
ombat | +0.057 |
ftime | +0.055 |
ater | +0.054 |
adium | +0.054 |
Neg logit contributions | |
Chaff | -0.019 |
Snape | -0.018 |
tied | -0.015 |
transcripts | -0.015 |
Misc | -0.015 |
Token | ulate |
Token ID | 5039 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ariat | +0.978 |
ombat | +0.642 |
ftime | +0.593 |
borgh | +0.585 |
ater | +0.583 |
Neg logit contributions | |
Chaff | -0.793 |
Snape | -0.768 |
transcripts | -0.741 |
tied | -0.733 |
Misc | -0.729 |
Token | D |
Token ID | 35 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Chaff | +0.482 |
Snape | +0.464 |
transcripts | +0.441 |
Misc | +0.434 |
tied | +0.433 |
Neg logit contributions | |
ariat | -0.893 |
ombat | -0.628 |
ater | -0.592 |
ftime | -0.592 |
borgh | -0.587 |
Token | ensity |
Token ID | 6377 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ariat | +0.443 |
ombat | +0.286 |
ater | +0.266 |
ftime | +0.266 |
borgh | +0.263 |
Neg logit contributions | |
Chaff | -0.372 |
Snape | -0.363 |
transcripts | -0.351 |
tied | -0.345 |
Misc | -0.343 |
Token | Grid |
Token ID | 41339 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ariat | +1.817 |
ombat | +1.294 |
ater | +1.237 |
ftime | +1.228 |
borgh | +1.218 |
Neg logit contributions | |
Chaff | -0.896 |
Snape | -0.864 |
transcripts | -0.828 |
loophole | -0.804 |
tied | -0.800 |
Token | ( |
Token ID | 7 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ariat | +1.850 |
ombat | +1.333 |
ater | +1.269 |
ftime | +1.266 |
borgh | +1.257 |
Neg logit contributions | |
Chaff | -0.835 |
Snape | -0.803 |
transcripts | -0.763 |
tied | -0.742 |
loophole | -0.739 |
Token | Uniform |
Token ID | 35712 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
ariat | +2.095 |
ombat | +1.518 |
ftime | +1.447 |
ater | +1.444 |
borgh | +1.436 |
Neg logit contributions | |
Chaff | -0.891 |
Snape | -0.853 |
transcripts | -0.806 |
tied | -0.790 |
Misc | -0.790 |
Token | Grid |
Token ID | 41339 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ariat | +4.888 |
ombat | +3.475 |
ater | +3.317 |
ftime | +3.270 |
borgh | +3.232 |
Neg logit contributions | |
Chaff | -2.521 |
Snape | -2.452 |
transcripts | -2.369 |
loophole | -2.295 |
pornographic | -2.292 |
Token | < |
Token ID | 27 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ariat | +1.156 |
ombat | +0.815 |
ftime | +0.772 |
borgh | +0.766 |
ater | +0.764 |
Neg logit contributions | |
Chaff | -0.615 |
Snape | -0.592 |
transcripts | -0.567 |
tied | -0.560 |
Misc | -0.558 |
Token | float |
Token ID | 12178 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ariat | +0.276 |
ombat | +0.199 |
ftime | +0.189 |
ater | +0.189 |
borgh | +0.188 |
Neg logit contributions | |
Chaff | -0.125 |
Snape | -0.119 |
transcripts | -0.112 |
Misc | -0.112 |
tied | -0.111 |
Token | > |
Token ID | 1875 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ariat | +3.392 |
ombat | +2.315 |
ater | +2.179 |
ftime | +2.171 |
borgh | +2.162 |
Neg logit contributions | |
Chaff | -2.187 |
Snape | -2.122 |
transcripts | -2.031 |
Misc | -1.994 |
tied | -1.991 |
Token | & |
Token ID | 1222 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ariat | +1.522 |
ombat | +1.073 |
ftime | +1.008 |
ater | +1.006 |
borgh | +1.002 |
Neg logit contributions | |
Chaff | -0.806 |
Snape | -0.781 |
transcripts | -0.750 |
tied | -0.739 |
Misc | -0.732 |
Token | guard |
Token ID | 4860 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Chaff | +0.288 |
Snape | +0.277 |
transcripts | +0.265 |
tied | +0.260 |
loophole | +0.257 |
Neg logit contributions | |
ariat | -0.610 |
ombat | -0.439 |
ftime | -0.415 |
borgh | -0.414 |
ater | -0.413 |
Token | list |
Token ID | 1351 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Chaff | +0.484 |
Snape | +0.466 |
transcripts | +0.458 |
tied | +0.453 |
loophole | +0.442 |
Neg logit contributions | |
ariat | -1.062 |
ombat | -0.778 |
borgh | -0.724 |
ftime | -0.723 |
adium | -0.722 |
Token | and |
Token ID | 290 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Chaff | +0.166 |
Snape | +0.159 |
tied | +0.156 |
transcripts | +0.153 |
needing | +0.151 |
Neg logit contributions | |
ariat | -0.289 |
ombat | -0.204 |
ftime | -0.189 |
ater | -0.189 |
borgh | -0.188 |
Token | made |
Token ID | 925 |
Feature activation | -9.07e-03 |
Pos logit contributions | |
ariat | +0.476 |
ombat | +0.341 |
ftime | +0.321 |
borgh | +0.320 |
ater | +0.319 |
Neg logit contributions | |
Chaff | -0.241 |
Snape | -0.231 |
tied | -0.226 |
transcripts | -0.221 |
loophole | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
ariat | +0.054 |
ombat | +0.038 |
ftime | +0.036 |
borgh | +0.036 |
ater | +0.036 |
Neg logit contributions | |
Chaff | -0.028 |
Snape | -0.027 |
transcripts | -0.026 |
tied | -0.026 |
Porn | -0.026 |
Token | cut |
Token ID | 2005 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Chaff | +0.238 |
Snape | +0.230 |
transcripts | +0.222 |
tied | +0.218 |
loophole | +0.216 |
Neg logit contributions | |
ariat | -0.434 |
ombat | -0.306 |
ftime | -0.289 |
borgh | -0.288 |
ater | -0.287 |
Token | when |
Token ID | 618 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
Chaff | +2.195 |
tied | +2.141 |
Snape | +2.106 |
transcripts | +2.046 |
needing | +2.046 |
Neg logit contributions | |
ariat | -4.144 |
ombat | -2.975 |
adium | -2.779 |
ftime | -2.754 |
borgh | -2.751 |
Token | they |
Token ID | 484 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
ariat | +0.129 |
ombat | +0.092 |
ater | +0.086 |
ftime | +0.086 |
borgh | +0.086 |
Neg logit contributions | |
Chaff | -0.068 |
Snape | -0.066 |
transcripts | -0.063 |
tied | -0.062 |
Misc | -0.061 |
Token | ranked |
Token ID | 10307 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ariat | +0.047 |
ombat | +0.034 |
ftime | +0.032 |
ater | +0.032 |
borgh | +0.032 |
Neg logit contributions | |
Chaff | -0.024 |
Snape | -0.023 |
transcripts | -0.022 |
tied | -0.022 |
loophole | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ariat | +0.202 |
ombat | +0.144 |
ftime | +0.136 |
borgh | +0.134 |
ater | +0.134 |
Neg logit contributions | |
Chaff | -0.107 |
Snape | -0.103 |
tied | -0.099 |
transcripts | -0.098 |
loophole | -0.096 |
Token | Top |
Token ID | 5849 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Chaff | +0.372 |
Snape | +0.358 |
transcripts | +0.344 |
tied | +0.344 |
loophole | +0.336 |
Neg logit contributions | |
ariat | -0.734 |
ombat | -0.528 |
ftime | -0.495 |
borgh | -0.495 |
adium | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Chaff | +0.148 |
Snape | +0.145 |
transcripts | +0.139 |
tied | +0.138 |
Misc | +0.136 |
Neg logit contributions | |
ariat | -0.229 |
ombat | -0.157 |
ftime | -0.147 |
ater | -0.146 |
borgh | -0.146 |
Token | � |
Token ID | 447 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
Chaff | +0.283 |
Snape | +0.275 |
transcripts | +0.251 |
Porn | +0.250 |
Misc | +0.249 |
Neg logit contributions | |
ariat | -0.697 |
ombat | -0.511 |
ftime | -0.487 |
ater | -0.484 |
borgh | -0.479 |
Token | � |
Token ID | 251 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
ariat | +0.162 |
ombat | +0.109 |
ftime | +0.102 |
ater | +0.102 |
adium | +0.101 |
Neg logit contributions | |
Chaff | -0.108 |
Snape | -0.104 |
transcripts | -0.100 |
tied | -0.099 |
loophole | -0.098 |
Token | He |
Token ID | 679 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Chaff | +0.181 |
Snape | +0.175 |
transcripts | +0.163 |
Porn | +0.160 |
Misc | +0.160 |
Neg logit contributions | |
ariat | -0.399 |
ombat | -0.288 |
ater | -0.274 |
ftime | -0.273 |
borgh | -0.271 |
Token | sits |
Token ID | 10718 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Chaff | +0.079 |
Snape | +0.076 |
transcripts | +0.072 |
tied | +0.071 |
loophole | +0.070 |
Neg logit contributions | |
ariat | -0.163 |
ombat | -0.118 |
ftime | -0.111 |
ater | -0.111 |
adium | -0.110 |
Token | back |
Token ID | 736 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Chaff | +0.955 |
Snape | +0.931 |
transcripts | +0.871 |
tied | +0.865 |
poetic | +0.839 |
Neg logit contributions | |
ariat | -2.372 |
ombat | -1.752 |
ftime | -1.661 |
ater | -1.650 |
adium | -1.645 |
Token | on |
Token ID | 319 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Chaff | +2.339 |
Snape | +2.336 |
tied | +2.225 |
transcripts | +2.201 |
poetic | +2.197 |
Neg logit contributions | |
ariat | -4.952 |
ombat | -3.599 |
adium | -3.365 |
ater | -3.345 |
ftime | -3.341 |
Token | his |
Token ID | 465 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Chaff | +1.106 |
Snape | +1.085 |
transcripts | +1.017 |
tied | +0.999 |
Porn | +0.998 |
Neg logit contributions | |
ariat | -2.109 |
ombat | -1.513 |
ftime | -1.427 |
ater | -1.420 |
borgh | -1.416 |
Token | ankles |
Token ID | 42415 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Chaff | +0.470 |
Snape | +0.461 |
transcripts | +0.439 |
tied | +0.433 |
poetic | +0.430 |
Neg logit contributions | |
ariat | -0.792 |
ombat | -0.558 |
ftime | -0.530 |
ater | -0.518 |
adium | -0.515 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ariat | +0.875 |
ombat | +0.612 |
ater | +0.576 |
ftime | +0.576 |
borgh | +0.571 |
Neg logit contributions | |
Chaff | -0.497 |
Snape | -0.485 |
transcripts | -0.462 |
tied | -0.458 |
loophole | -0.451 |
Token | � |
Token ID | 564 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Chaff | +0.526 |
Snape | +0.511 |
transcripts | +0.473 |
Misc | +0.465 |
Porn | +0.465 |
Neg logit contributions | |
ariat | -1.133 |
ombat | -0.819 |
ftime | -0.778 |
ater | -0.776 |
adium | -0.767 |
Token | performances |
Token ID | 13289 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
Chaff | +0.047 |
Snape | +0.045 |
transcripts | +0.043 |
tied | +0.042 |
pornographic | +0.042 |
Neg logit contributions | |
ariat | -0.099 |
ombat | -0.071 |
ftime | -0.067 |
ater | -0.067 |
borgh | -0.067 |
Token | as |
Token ID | 355 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
ariat | +0.252 |
ombat | +0.177 |
ater | +0.166 |
ftime | +0.165 |
borgh | +0.164 |
Neg logit contributions | |
Chaff | -0.148 |
Snape | -0.144 |
transcripts | -0.137 |
tied | -0.137 |
Misc | -0.134 |
Token | two |
Token ID | 734 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
ariat | +0.367 |
ombat | +0.263 |
ftime | +0.248 |
ater | +0.247 |
borgh | +0.247 |
Neg logit contributions | |
Chaff | -0.187 |
Snape | -0.181 |
transcripts | -0.173 |
tied | -0.169 |
Misc | -0.168 |
Token | women |
Token ID | 1466 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Chaff | +0.123 |
Snape | +0.120 |
transcripts | +0.115 |
tied | +0.113 |
pornographic | +0.112 |
Neg logit contributions | |
ariat | -0.230 |
ombat | -0.164 |
ater | -0.153 |
ftime | -0.153 |
borgh | -0.153 |
Token | at |
Token ID | 379 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
Chaff | +0.322 |
Snape | +0.313 |
tied | +0.298 |
transcripts | +0.296 |
needing | +0.289 |
Neg logit contributions | |
ariat | -0.652 |
ombat | -0.470 |
ater | -0.441 |
ftime | -0.441 |
borgh | -0.438 |
Token | opposite |
Token ID | 6697 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Chaff | +0.180 |
Snape | +0.174 |
transcripts | +0.166 |
tied | +0.163 |
pornographic | +0.163 |
Neg logit contributions | |
ariat | -0.315 |
ombat | -0.224 |
ftime | -0.210 |
borgh | -0.209 |
ater | -0.207 |
Token | ends |
Token ID | 5645 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Chaff | +2.095 |
Snape | +2.061 |
transcripts | +1.991 |
pornographic | +1.987 |
tied | +1.968 |
Neg logit contributions | |
ariat | -2.688 |
ombat | -1.836 |
ater | -1.684 |
borgh | -1.671 |
adium | -1.641 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Chaff | +0.441 |
Snape | +0.428 |
transcripts | +0.411 |
tied | +0.402 |
loophole | +0.401 |
Neg logit contributions | |
ariat | -0.707 |
ombat | -0.487 |
ater | -0.460 |
ftime | -0.458 |
borgh | -0.454 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Chaff | +0.404 |
Snape | +0.391 |
transcripts | +0.375 |
pornographic | +0.366 |
tied | +0.365 |
Neg logit contributions | |
ariat | -0.731 |
ombat | -0.520 |
ftime | -0.487 |
ater | -0.486 |
borgh | -0.486 |
Token | gratification |
Token ID | 47459 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Chaff | +0.678 |
Snape | +0.653 |
transcripts | +0.628 |
pornographic | +0.612 |
tied | +0.610 |
Neg logit contributions | |
ariat | -1.376 |
ombat | -0.988 |
ftime | -0.931 |
borgh | -0.928 |
ater | -0.928 |
Token | spectrum |
Token ID | 10958 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ariat | +0.768 |
ombat | +0.555 |
ater | +0.526 |
ftime | +0.526 |
borgh | +0.524 |
Neg logit contributions | |
Chaff | -0.363 |
Snape | -0.349 |
transcripts | -0.332 |
tied | -0.326 |
loophole | -0.326 |
Token | be |
Token ID | 307 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Chaff | +0.184 |
Snape | +0.179 |
transcripts | +0.173 |
tied | +0.171 |
loophole | +0.169 |
Neg logit contributions | |
ariat | -0.332 |
ombat | -0.232 |
ftime | -0.222 |
adium | -0.219 |
borgh | -0.219 |
Token | punished |
Token ID | 16851 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ariat | +0.684 |
ombat | +0.492 |
ftime | +0.472 |
ater | +0.464 |
borgh | +0.464 |
Neg logit contributions | |
Chaff | -0.322 |
Snape | -0.312 |
tied | -0.299 |
transcripts | -0.299 |
loophole | -0.289 |
Token | in |
Token ID | 287 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ariat | +1.671 |
ombat | +1.156 |
ftime | +1.091 |
ater | +1.086 |
borgh | +1.085 |
Neg logit contributions | |
Chaff | -0.982 |
Snape | -0.959 |
transcripts | -0.921 |
tied | -0.910 |
loophole | -0.896 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ariat | +0.793 |
ombat | +0.563 |
ftime | +0.534 |
borgh | +0.531 |
ater | +0.525 |
Neg logit contributions | |
Chaff | -0.430 |
Snape | -0.416 |
transcripts | -0.402 |
tied | -0.393 |
loophole | -0.390 |
Token | severe |
Token ID | 6049 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ariat | +0.744 |
ombat | +0.542 |
ftime | +0.513 |
borgh | +0.510 |
ater | +0.509 |
Neg logit contributions | |
Chaff | -0.349 |
Snape | -0.335 |
transcripts | -0.318 |
tied | -0.316 |
loophole | -0.314 |
Token | manner |
Token ID | 5642 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
Chaff | +0.405 |
Snape | +0.385 |
transcripts | +0.361 |
tied | +0.359 |
loophole | +0.359 |
Neg logit contributions | |
ariat | -1.164 |
ombat | -0.871 |
ftime | -0.831 |
borgh | -0.829 |
ater | -0.827 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Chaff | +1.805 |
Snape | +1.770 |
tied | +1.715 |
transcripts | +1.694 |
loophole | +1.659 |
Neg logit contributions | |
ariat | -3.051 |
ombat | -2.112 |
borgh | -1.995 |
ftime | -1.989 |
adium | -1.984 |
Token | 42 |
Token ID | 3682 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
Chaff | +0.397 |
Snape | +0.383 |
transcripts | +0.367 |
tied | +0.356 |
Misc | +0.355 |
Neg logit contributions | |
ariat | -0.834 |
ombat | -0.595 |
ftime | -0.570 |
borgh | -0.563 |
adium | -0.558 |
Token | ] |
Token ID | 60 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ariat | +0.626 |
ombat | +0.457 |
ater | +0.437 |
ftime | +0.435 |
borgh | +0.432 |
Neg logit contributions | |
Chaff | -0.255 |
Snape | -0.244 |
transcripts | -0.229 |
loophole | -0.223 |
tied | -0.223 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ariat | +1.066 |
ombat | +0.749 |
ater | +0.711 |
ftime | +0.704 |
borgh | +0.699 |
Neg logit contributions | |
Chaff | -0.584 |
Snape | -0.562 |
transcripts | -0.540 |
loophole | -0.528 |
tied | -0.527 |
Token |
|
Token ID | 198 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ariat | +0.681 |
ombat | +0.485 |
ftime | +0.460 |
ater | +0.459 |
borgh | +0.454 |
Neg logit contributions | |
Chaff | -0.348 |
Snape | -0.335 |
transcripts | -0.319 |
tied | -0.312 |
Misc | -0.311 |
Token | : |
Token ID | 25 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
Chaff | +2.539 |
Snape | +2.441 |
transcripts | +2.330 |
tied | +2.294 |
loophole | +2.270 |
Neg logit contributions | |
ariat | -4.729 |
ombat | -3.377 |
ftime | -3.208 |
ater | -3.166 |
borgh | -3.158 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Chaff | +2.071 |
Snape | +1.969 |
transcripts | +1.845 |
Misc | +1.805 |
loophole | +1.804 |
Neg logit contributions | |
ariat | -4.777 |
ombat | -3.514 |
ftime | -3.338 |
borgh | -3.296 |
adium | -3.282 |
Token | staff |
Token ID | 3085 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Chaff | +1.961 |
Snape | +1.880 |
transcripts | +1.844 |
tied | +1.787 |
loophole | +1.764 |
Neg logit contributions | |
ariat | -3.933 |
ombat | -2.813 |
ftime | -2.635 |
borgh | -2.626 |
ater | -2.624 |
Token | are |
Token ID | 389 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Chaff | +1.873 |
Snape | +1.799 |
transcripts | +1.750 |
tied | +1.725 |
loophole | +1.697 |
Neg logit contributions | |
ariat | -3.082 |
ombat | -2.141 |
ftime | -2.030 |
ater | -1.997 |
borgh | -1.992 |
Token | ' |
Token ID | 705 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Chaff | +0.867 |
tied | +0.840 |
transcripts | +0.789 |
Snape | +0.780 |
needing | +0.753 |
Neg logit contributions | |
ariat | -2.992 |
ombat | -2.341 |
borgh | -2.232 |
ftime | -2.227 |
alky | -2.200 |
Token | big |
Token ID | 14261 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Chaff | +1.363 |
Snape | +1.320 |
tied | +1.312 |
transcripts | +1.282 |
Misc | +1.263 |
Neg logit contributions | |
ariat | -2.841 |
ombat | -2.059 |
ftime | -1.945 |
borgh | -1.944 |
adium | -1.914 |
Token | gest |
Token ID | 3495 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Chaff | +1.831 |
Snape | +1.742 |
transcripts | +1.705 |
loophole | +1.657 |
tied | +1.652 |
Neg logit contributions | |
ariat | -3.023 |
ombat | -2.159 |
adium | -2.024 |
ftime | -2.008 |
IUM | -1.982 |
Token | a |
Token ID | 257 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Chaff | +2.738 |
Snape | +2.632 |
transcripts | +2.524 |
loophole | +2.514 |
tied | +2.483 |
Neg logit contributions | |
ariat | -3.613 |
ombat | -2.415 |
ftime | -2.285 |
ater | -2.257 |
adium | -2.242 |
Token | -- |
Token ID | 438 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Chaff | +0.958 |
Snape | +0.906 |
tied | +0.869 |
loophole | +0.865 |
Porn | +0.855 |
Neg logit contributions | |
ariat | -1.520 |
ombat | -1.080 |
ftime | -1.027 |
borgh | -1.022 |
adium | -0.992 |
Token | holes |
Token ID | 28439 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Chaff | +0.724 |
Snape | +0.686 |
transcripts | +0.660 |
loophole | +0.646 |
tied | +0.638 |
Neg logit contributions | |
ariat | -1.841 |
ombat | -1.358 |
ftime | -1.292 |
adium | -1.286 |
ater | -1.281 |
Token | in |
Token ID | 287 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
ariat | +0.701 |
ombat | +0.544 |
ftime | +0.505 |
ater | +0.504 |
alky | +0.504 |
Neg logit contributions | |
Chaff | -0.238 |
Snape | -0.228 |
tied | -0.223 |
transcripts | -0.219 |
loophole | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ariat | +0.352 |
ombat | +0.253 |
ftime | +0.240 |
borgh | +0.238 |
ater | +0.237 |
Neg logit contributions | |
Chaff | -0.182 |
Snape | -0.176 |
transcripts | -0.168 |
tied | -0.166 |
loophole | -0.166 |
Token | housing |
Token ID | 5627 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ariat | +0.196 |
ombat | +0.142 |
ftime | +0.136 |
borgh | +0.135 |
adium | +0.133 |
Neg logit contributions | |
Chaff | -0.094 |
Snape | -0.091 |
transcripts | -0.088 |
loophole | -0.086 |
tied | -0.086 |
Token | market |
Token ID | 1910 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
ariat | +1.231 |
ombat | +0.899 |
ftime | +0.851 |
ater | +0.849 |
borgh | +0.846 |
Neg logit contributions | |
Chaff | -0.554 |
Snape | -0.532 |
transcripts | -0.512 |
loophole | -0.501 |
tied | -0.499 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Chaff | +0.286 |
Snape | +0.278 |
transcripts | +0.269 |
tied | +0.267 |
loophole | +0.263 |
Neg logit contributions | |
ariat | -0.483 |
ombat | -0.338 |
ftime | -0.318 |
ater | -0.317 |
borgh | -0.316 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Chaff | +0.060 |
Snape | +0.057 |
tied | +0.056 |
transcripts | +0.055 |
loophole | +0.055 |
Neg logit contributions | |
ariat | -0.115 |
ombat | -0.084 |
ftime | -0.079 |
borgh | -0.078 |
ater | -0.078 |
Token | economy |
Token ID | 3773 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Chaff | +0.139 |
Snape | +0.133 |
transcripts | +0.129 |
tied | +0.127 |
loophole | +0.127 |
Neg logit contributions | |
ariat | -0.308 |
ombat | -0.226 |
ftime | -0.216 |
borgh | -0.214 |
ater | -0.212 |
Token | as |
Token ID | 355 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Chaff | +0.397 |
Snape | +0.389 |
tied | +0.373 |
transcripts | +0.371 |
needing | +0.365 |
Neg logit contributions | |
ariat | -0.653 |
ombat | -0.454 |
ater | -0.426 |
ftime | -0.425 |
borgh | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Chaff | +0.036 |
Snape | +0.036 |
transcripts | +0.035 |
tied | +0.034 |
Misc | +0.034 |
Neg logit contributions | |
ariat | -0.057 |
ombat | -0.040 |
ftime | -0.038 |
borgh | -0.037 |
ater | -0.037 |
Token | reforms |
Token ID | 12506 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
Chaff | +0.686 |
Snape | +0.660 |
transcripts | +0.642 |
loophole | +0.633 |
tied | +0.629 |
Neg logit contributions | |
ariat | -1.321 |
ombat | -0.960 |
ftime | -0.909 |
borgh | -0.900 |
adium | -0.891 |
Token | take |
Token ID | 1011 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Chaff | +0.047 |
Snape | +0.046 |
transcripts | +0.044 |
tied | +0.043 |
loophole | +0.043 |
Neg logit contributions | |
ariat | -0.091 |
ombat | -0.065 |
ftime | -0.062 |
borgh | -0.062 |
ater | -0.062 |
Token | effect |
Token ID | 1245 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Chaff | +0.216 |
Snape | +0.212 |
transcripts | +0.204 |
tied | +0.201 |
loophole | +0.201 |
Neg logit contributions | |
ariat | -0.298 |
ombat | -0.202 |
ftime | -0.189 |
ater | -0.188 |
borgh | -0.188 |
Token | to |
Token ID | 284 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
ariat | +0.535 |
ombat | +0.381 |
ater | +0.360 |
ftime | +0.360 |
borgh | +0.358 |
Neg logit contributions | |
Chaff | -0.269 |
Snape | -0.262 |
transcripts | -0.249 |
tied | -0.245 |
pornographic | -0.241 |
Token | eat |
Token ID | 4483 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Chaff | +0.250 |
Snape | +0.244 |
transcripts | +0.234 |
tied | +0.231 |
loophole | +0.227 |
Neg logit contributions | |
ariat | -0.463 |
ombat | -0.328 |
ftime | -0.310 |
ater | -0.307 |
adium | -0.306 |
Token | gru |
Token ID | 22848 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
Chaff | +0.121 |
Snape | +0.118 |
transcripts | +0.112 |
tied | +0.111 |
pornographic | +0.109 |
Neg logit contributions | |
ariat | -0.251 |
ombat | -0.181 |
ftime | -0.172 |
borgh | -0.171 |
adium | -0.169 |
Token | el |
Token ID | 417 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ariat | +0.041 |
ombat | +0.028 |
borgh | +0.027 |
ftime | +0.027 |
IUM | +0.027 |
Neg logit contributions | |
Chaff | -0.023 |
Snape | -0.022 |
transcripts | -0.021 |
tied | -0.021 |
Lynd | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Chaff | +0.699 |
Snape | +0.677 |
tied | +0.656 |
transcripts | +0.647 |
beard | +0.632 |
Neg logit contributions | |
ariat | -1.282 |
ombat | -0.906 |
ftime | -0.852 |
borgh | -0.841 |
adium | -0.837 |
Token | months |
Token ID | 1933 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Chaff | +0.389 |
Snape | +0.379 |
transcripts | +0.362 |
tied | +0.356 |
pornographic | +0.351 |
Neg logit contributions | |
ariat | -0.714 |
ombat | -0.509 |
borgh | -0.480 |
ftime | -0.478 |
adium | -0.473 |
Token | at |
Token ID | 379 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Chaff | +0.412 |
Snape | +0.402 |
tied | +0.384 |
transcripts | +0.381 |
needing | +0.374 |
Neg logit contributions | |
ariat | -0.721 |
ombat | -0.505 |
borgh | -0.471 |
ftime | -0.470 |
ater | -0.470 |
Token | a |
Token ID | 257 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
Chaff | +0.673 |
Snape | +0.659 |
transcripts | +0.628 |
tied | +0.622 |
Misc | +0.613 |
Neg logit contributions | |
ariat | -1.081 |
ombat | -0.765 |
borgh | -0.717 |
ater | -0.700 |
adium | -0.699 |
Token | time |
Token ID | 640 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Chaff | +0.324 |
Snape | +0.311 |
tied | +0.299 |
transcripts | +0.295 |
loophole | +0.294 |
Neg logit contributions | |
ariat | -0.502 |
ombat | -0.356 |
borgh | -0.327 |
ater | -0.322 |
adium | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Chaff | +2.039 |
Snape | +2.000 |
tied | +1.931 |
needing | +1.896 |
transcripts | +1.892 |
Neg logit contributions | |
ariat | -3.364 |
ombat | -2.339 |
borgh | -2.172 |
ater | -2.168 |
adium | -2.157 |
Token | The |
Token ID | 383 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
Chaff | +0.349 |
Snape | +0.336 |
Misc | +0.311 |
Porn | +0.308 |
transcripts | +0.307 |
Neg logit contributions | |
ariat | -0.782 |
ombat | -0.570 |
ftime | -0.544 |
ater | -0.536 |
borgh | -0.535 |
Token | enjoying |
Token ID | 13226 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
Chaff | +0.278 |
Snape | +0.271 |
transcripts | +0.257 |
tied | +0.251 |
needing | +0.251 |
Neg logit contributions | |
ariat | -0.560 |
ombat | -0.401 |
ater | -0.380 |
ftime | -0.379 |
borgh | -0.376 |
Token | a |
Token ID | 257 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ariat | +0.334 |
ombat | +0.234 |
ater | +0.221 |
ftime | +0.221 |
borgh | +0.219 |
Neg logit contributions | |
Chaff | -0.189 |
Snape | -0.185 |
transcripts | -0.176 |
tied | -0.172 |
loophole | -0.171 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Chaff | +0.093 |
Snape | +0.091 |
transcripts | +0.086 |
tied | +0.086 |
loophole | +0.085 |
Neg logit contributions | |
ariat | -0.183 |
ombat | -0.130 |
ater | -0.123 |
ftime | -0.122 |
adium | -0.122 |
Token | amount |
Token ID | 2033 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ariat | +1.083 |
ombat | +0.755 |
ater | +0.720 |
borgh | +0.714 |
adium | +0.711 |
Neg logit contributions | |
Chaff | -0.571 |
Snape | -0.560 |
transcripts | -0.535 |
tied | -0.531 |
loophole | -0.529 |
Token | of |
Token ID | 286 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Chaff | +0.376 |
Snape | +0.363 |
transcripts | +0.349 |
loophole | +0.341 |
tied | +0.341 |
Neg logit contributions | |
ariat | -0.591 |
ombat | -0.405 |
ater | -0.382 |
ftime | -0.382 |
borgh | -0.378 |
Token | possession |
Token ID | 7797 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
Chaff | +0.182 |
Snape | +0.178 |
transcripts | +0.169 |
tied | +0.166 |
poetic | +0.165 |
Neg logit contributions | |
ariat | -0.336 |
ombat | -0.236 |
ater | -0.224 |
ftime | -0.222 |
borgh | -0.222 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Chaff | +0.196 |
Snape | +0.192 |
transcripts | +0.181 |
tied | +0.181 |
needing | +0.177 |
Neg logit contributions | |
ariat | -0.337 |
ombat | -0.235 |
ater | -0.221 |
ftime | -0.220 |
borgh | -0.219 |
Token | forcing |
Token ID | 10833 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Chaff | +0.411 |
Snape | +0.404 |
transcripts | +0.381 |
tied | +0.379 |
needing | +0.376 |
Neg logit contributions | |
ariat | -0.769 |
ombat | -0.549 |
ater | -0.518 |
borgh | -0.513 |
ftime | -0.512 |
Token | several |
Token ID | 1811 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ariat | +0.587 |
ombat | +0.420 |
ftime | +0.394 |
borgh | +0.392 |
ater | +0.392 |
Neg logit contributions | |
Chaff | -0.318 |
Snape | -0.312 |
transcripts | -0.296 |
tied | -0.290 |
Lynd | -0.287 |
Token | set |
Token ID | 900 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
Chaff | +0.186 |
Snape | +0.180 |
transcripts | +0.173 |
tied | +0.171 |
Lynd | +0.168 |
Neg logit contributions | |
ariat | -0.348 |
ombat | -0.252 |
ftime | -0.235 |
ater | -0.235 |
adium | -0.232 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ariat | +0.167 |
ombat | +0.122 |
ftime | +0.114 |
adium | +0.114 |
ater | +0.113 |
Neg logit contributions | |
Chaff | -0.072 |
Snape | -0.070 |
transcripts | -0.067 |
tied | -0.066 |
loophole | -0.065 |
Token | ze |
Token ID | 2736 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
ariat | +0.431 |
ombat | +0.252 |
ftime | +0.231 |
borgh | +0.227 |
adium | +0.226 |
Neg logit contributions | |
Chaff | -0.506 |
Snape | -0.500 |
tied | -0.479 |
transcripts | -0.479 |
poetic | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ariat | +0.272 |
ombat | +0.186 |
ftime | +0.176 |
ater | +0.173 |
borgh | +0.173 |
Neg logit contributions | |
Chaff | -0.178 |
Snape | -0.175 |
transcripts | -0.166 |
tied | -0.166 |
loophole | -0.163 |
Token | Spl |
Token ID | 13341 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Chaff | +0.532 |
Snape | +0.515 |
Misc | +0.476 |
Porn | +0.472 |
transcripts | +0.471 |
Neg logit contributions | |
ariat | -1.156 |
ombat | -0.834 |
ftime | -0.805 |
ater | -0.789 |
borgh | -0.782 |
Token | inter |
Token ID | 3849 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Chaff | +0.882 |
Snape | +0.862 |
transcripts | +0.829 |
tied | +0.820 |
Misc | +0.815 |
Neg logit contributions | |
ariat | -0.936 |
ombat | -0.583 |
ftime | -0.541 |
borgh | -0.536 |
adium | -0.534 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Chaff | +0.954 |
Snape | +0.933 |
tied | +0.894 |
transcripts | +0.872 |
Misc | +0.856 |
Neg logit contributions | |
ariat | -1.761 |
ombat | -1.248 |
ftime | -1.183 |
adium | -1.175 |
ater | -1.171 |
Token | curious |
Token ID | 11040 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Chaff | +0.325 |
Snape | +0.313 |
tied | +0.297 |
transcripts | +0.292 |
needing | +0.288 |
Neg logit contributions | |
ariat | -0.694 |
ombat | -0.501 |
ftime | -0.479 |
ater | -0.474 |
borgh | -0.472 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Chaff | +0.042 |
Snape | +0.041 |
transcripts | +0.039 |
tied | +0.039 |
loophole | +0.038 |
Neg logit contributions | |
ariat | -0.075 |
ombat | -0.052 |
ftime | -0.049 |
ater | -0.049 |
borgh | -0.049 |
Token | went |
Token ID | 1816 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Chaff | +0.906 |
Snape | +0.885 |
tied | +0.850 |
transcripts | +0.827 |
loophole | +0.813 |
Neg logit contributions | |
ariat | -1.761 |
ombat | -1.250 |
ftime | -1.195 |
ater | -1.183 |
adium | -1.179 |
Token | to |
Token ID | 284 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
Chaff | +0.431 |
Snape | +0.418 |
tied | +0.399 |
transcripts | +0.393 |
needing | +0.385 |
Neg logit contributions | |
ariat | -0.935 |
ombat | -0.673 |
ftime | -0.644 |
borgh | -0.632 |
ater | -0.628 |
Token | see |
Token ID | 766 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ariat | +0.045 |
ombat | +0.032 |
ftime | +0.031 |
borgh | +0.031 |
ater | +0.030 |
Neg logit contributions | |
Chaff | -0.021 |
Snape | -0.020 |
transcripts | -0.019 |
tied | -0.019 |
Misc | -0.019 |
Token | what |
Token ID | 644 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
ariat | +0.711 |
ombat | +0.507 |
ftime | +0.485 |
borgh | +0.480 |
ater | +0.479 |
Neg logit contributions | |
Chaff | -0.349 |
Snape | -0.338 |
transcripts | -0.320 |
tied | -0.315 |
Misc | -0.313 |
Token | is |
Token ID | 318 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ariat | +0.283 |
ombat | +0.204 |
ftime | +0.194 |
ater | +0.194 |
borgh | +0.193 |
Neg logit contributions | |
Chaff | -0.136 |
Snape | -0.131 |
transcripts | -0.125 |
tied | -0.124 |
loophole | -0.121 |
Token | going |
Token ID | 1016 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ariat | +0.811 |
ombat | +0.584 |
ftime | +0.557 |
ater | +0.554 |
borgh | +0.551 |
Neg logit contributions | |
Chaff | -0.393 |
Snape | -0.378 |
transcripts | -0.363 |
tied | -0.361 |
pornographic | -0.354 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Chaff | +0.428 |
Snape | +0.412 |
transcripts | +0.395 |
tied | +0.386 |
loophole | +0.384 |
Neg logit contributions | |
ariat | -0.815 |
ombat | -0.577 |
ater | -0.548 |
ftime | -0.547 |
borgh | -0.542 |
Token | be |
Token ID | 307 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
Chaff | +0.353 |
Snape | +0.343 |
tied | +0.328 |
transcripts | +0.327 |
loophole | +0.321 |
Neg logit contributions | |
ariat | -0.670 |
ombat | -0.475 |
ftime | -0.453 |
ater | -0.449 |
borgh | -0.446 |
Token | harder |
Token ID | 7069 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
ariat | +0.082 |
ombat | +0.059 |
ftime | +0.056 |
ater | +0.055 |
borgh | +0.055 |
Neg logit contributions | |
Chaff | -0.042 |
Snape | -0.040 |
tied | -0.039 |
transcripts | -0.039 |
pornographic | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
ariat | +0.517 |
ombat | +0.362 |
ater | +0.345 |
borgh | +0.343 |
ftime | +0.341 |
Neg logit contributions | |
Chaff | -0.291 |
Snape | -0.283 |
transcripts | -0.272 |
tied | -0.270 |
needing | -0.265 |
Token | harder |
Token ID | 7069 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Chaff | +0.223 |
Snape | +0.217 |
transcripts | +0.210 |
tied | +0.208 |
needing | +0.204 |
Neg logit contributions | |
ariat | -0.410 |
ombat | -0.292 |
ftime | -0.275 |
borgh | -0.272 |
ater | -0.271 |
Token | on |
Token ID | 319 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ariat | +0.115 |
ombat | +0.081 |
ater | +0.077 |
borgh | +0.077 |
ftime | +0.076 |
Neg logit contributions | |
Chaff | -0.064 |
Snape | -0.062 |
transcripts | -0.060 |
tied | -0.059 |
needing | -0.058 |
Token | players |
Token ID | 1938 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ariat | +0.701 |
ombat | +0.502 |
borgh | +0.473 |
ftime | +0.471 |
ater | +0.471 |
Neg logit contributions | |
Chaff | -0.378 |
Snape | -0.365 |
transcripts | -0.356 |
tied | -0.347 |
Misc | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
Chaff | +0.384 |
Snape | +0.375 |
tied | +0.360 |
transcripts | +0.359 |
needing | +0.355 |
Neg logit contributions | |
ariat | -0.673 |
ombat | -0.473 |
borgh | -0.447 |
ater | -0.447 |
ftime | -0.445 |
Token | manage |
Token ID | 6687 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
Chaff | +0.143 |
Snape | +0.140 |
transcripts | +0.135 |
tied | +0.134 |
loophole | +0.133 |
Neg logit contributions | |
ariat | -0.270 |
ombat | -0.191 |
ftime | -0.182 |
borgh | -0.180 |
ater | -0.179 |
Token | pure |
Token ID | 5899 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
ariat | +1.744 |
ombat | +1.263 |
ftime | +1.198 |
ater | +1.192 |
borgh | +1.186 |
Neg logit contributions | |
Chaff | -0.821 |
Snape | -0.797 |
transcripts | -0.754 |
tied | -0.738 |
poetic | -0.731 |
Token | joy |
Token ID | 8716 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ariat | +0.510 |
ombat | +0.371 |
ftime | +0.353 |
borgh | +0.349 |
ater | +0.349 |
Neg logit contributions | |
Chaff | -0.231 |
Snape | -0.225 |
transcripts | -0.210 |
poetic | -0.209 |
tied | -0.207 |
Token | rose |
Token ID | 8278 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ariat | +1.387 |
ombat | +0.986 |
ftime | +0.932 |
ater | +0.929 |
borgh | +0.926 |
Neg logit contributions | |
Chaff | -0.717 |
Snape | -0.696 |
transcripts | -0.663 |
tied | -0.654 |
loophole | -0.643 |
Token | from |
Token ID | 422 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ariat | +0.116 |
ombat | +0.083 |
ftime | +0.078 |
ater | +0.077 |
borgh | +0.077 |
Neg logit contributions | |
Chaff | -0.058 |
Snape | -0.057 |
transcripts | -0.054 |
tied | -0.054 |
poetic | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
ariat | +1.195 |
ombat | +0.857 |
ftime | +0.813 |
borgh | +0.806 |
ater | +0.804 |
Neg logit contributions | |
Chaff | -0.613 |
Snape | -0.596 |
transcripts | -0.566 |
tied | -0.556 |
loophole | -0.550 |
Token | assembled |
Token ID | 16030 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ariat | +0.554 |
ombat | +0.398 |
ftime | +0.382 |
borgh | +0.377 |
adium | +0.371 |
Neg logit contributions | |
Chaff | -0.286 |
Snape | -0.275 |
transcripts | -0.264 |
tied | -0.258 |
loophole | -0.258 |
Token | masses |
Token ID | 14568 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ariat | +1.414 |
ombat | +1.049 |
ftime | +1.006 |
borgh | +0.999 |
ater | +0.994 |
Neg logit contributions | |
Chaff | -0.581 |
Snape | -0.554 |
transcripts | -0.530 |
tied | -0.516 |
Misc | -0.513 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ariat | +0.769 |
ombat | +0.535 |
ftime | +0.501 |
ater | +0.500 |
borgh | +0.498 |
Neg logit contributions | |
Chaff | -0.472 |
Snape | -0.462 |
transcripts | -0.441 |
tied | -0.440 |
needing | -0.430 |
Token | joined |
Token ID | 5399 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ariat | +0.646 |
ombat | +0.469 |
ftime | +0.445 |
ater | +0.442 |
borgh | +0.441 |
Neg logit contributions | |
Chaff | -0.290 |
Snape | -0.281 |
transcripts | -0.266 |
tied | -0.263 |
poetic | -0.258 |
Token | seconds |
Token ID | 4201 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ariat | +1.232 |
ombat | +0.912 |
ftime | +0.867 |
ater | +0.866 |
borgh | +0.860 |
Neg logit contributions | |
Chaff | -0.460 |
Snape | -0.448 |
transcripts | -0.421 |
tied | -0.411 |
Lynd | -0.403 |
Token | later |
Token ID | 1568 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ariat | +1.533 |
ombat | +1.052 |
ater | +0.981 |
borgh | +0.975 |
adium | +0.975 |
Neg logit contributions | |
Chaff | -1.010 |
Snape | -0.993 |
transcripts | -0.947 |
tied | -0.937 |
loophole | -0.925 |
Token | longer |
Token ID | 2392 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ariat | +1.559 |
ombat | +1.144 |
ftime | +1.084 |
ater | +1.084 |
borgh | +1.079 |
Neg logit contributions | |
Chaff | -0.626 |
Snape | -0.602 |
transcripts | -0.572 |
tied | -0.562 |
loophole | -0.555 |
Token | - |
Token ID | 12 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
ariat | +0.643 |
ombat | +0.445 |
ftime | +0.421 |
borgh | +0.421 |
ater | +0.419 |
Neg logit contributions | |
Chaff | -0.382 |
Snape | -0.374 |
transcripts | -0.362 |
tied | -0.355 |
loophole | -0.351 |
Token | term |
Token ID | 4354 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ariat | +0.232 |
ombat | +0.166 |
ftime | +0.157 |
borgh | +0.157 |
ater | +0.156 |
Neg logit contributions | |
Chaff | -0.111 |
Snape | -0.109 |
transcripts | -0.103 |
tied | -0.102 |
Misc | -0.101 |
Token | actions |
Token ID | 4028 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
ariat | +1.486 |
ombat | +1.078 |
ftime | +1.026 |
ater | +1.023 |
borgh | +1.016 |
Neg logit contributions | |
Chaff | -0.659 |
Snape | -0.636 |
transcripts | -0.612 |
tied | -0.594 |
loophole | -0.589 |
Token | . |
Token ID | 13 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ariat | +0.328 |
ombat | +0.233 |
ftime | +0.220 |
ater | +0.219 |
borgh | +0.218 |
Neg logit contributions | |
Chaff | -0.177 |
Snape | -0.172 |
transcripts | -0.163 |
tied | -0.163 |
Misc | -0.159 |
Token | Duke |
Token ID | 11083 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ariat | +0.276 |
ombat | +0.201 |
ftime | +0.191 |
ater | +0.188 |
borgh | +0.188 |
Neg logit contributions | |
Chaff | -0.127 |
Snape | -0.122 |
transcripts | -0.113 |
Misc | -0.112 |
Porn | -0.111 |
Token | Energy |
Token ID | 6682 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ariat | +0.703 |
ombat | +0.487 |
ftime | +0.461 |
ater | +0.457 |
borgh | +0.454 |
Neg logit contributions | |
Chaff | -0.393 |
Snape | -0.377 |
transcripts | -0.364 |
tied | -0.358 |
Misc | -0.354 |
Token | is |
Token ID | 318 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Chaff | +0.467 |
Snape | +0.447 |
transcripts | +0.432 |
tied | +0.432 |
Misc | +0.419 |
Neg logit contributions | |
ariat | -0.877 |
ombat | -0.619 |
ftime | -0.584 |
ater | -0.581 |
adium | -0.579 |
Token | responsible |
Token ID | 4497 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ariat | +0.955 |
ombat | +0.692 |
ftime | +0.657 |
ater | +0.653 |
borgh | +0.650 |
Neg logit contributions | |
Chaff | -0.441 |
Snape | -0.422 |
tied | -0.408 |
transcripts | -0.398 |
needing | -0.393 |
Token | for |
Token ID | 329 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
ariat | +0.720 |
ombat | +0.492 |
ftime | +0.464 |
ater | +0.463 |
borgh | +0.460 |
Neg logit contributions | |
Chaff | -0.464 |
Snape | -0.451 |
transcripts | -0.433 |
tied | -0.429 |
Lynd | -0.423 |
Token | 21 |
Token ID | 2310 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
ariat | +0.055 |
ombat | +0.040 |
ftime | +0.038 |
borgh | +0.037 |
ater | +0.037 |
Neg logit contributions | |
Chaff | -0.029 |
Snape | -0.028 |
transcripts | -0.027 |
tied | -0.026 |
needing | -0.026 |
Token | G |
Token ID | 402 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ariat | +1.009 |
ombat | +0.725 |
ftime | +0.687 |
borgh | +0.680 |
ater | +0.677 |
Neg logit contributions | |
Chaff | -0.507 |
Snape | -0.485 |
transcripts | -0.463 |
loophole | -0.459 |
tied | -0.459 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ariat | +0.893 |
ombat | +0.620 |
ftime | +0.585 |
borgh | +0.583 |
ater | +0.573 |
Neg logit contributions | |
Chaff | -0.545 |
Snape | -0.529 |
transcripts | -0.512 |
tied | -0.504 |
poetic | -0.497 |
Token | X |
Token ID | 55 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ariat | +1.383 |
ombat | +1.019 |
ftime | +0.972 |
ater | +0.970 |
borgh | +0.967 |
Neg logit contributions | |
Chaff | -0.519 |
Snape | -0.492 |
transcripts | -0.465 |
tied | -0.453 |
loophole | -0.452 |
Token | memory |
Token ID | 4088 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ariat | +0.702 |
ombat | +0.502 |
ftime | +0.476 |
borgh | +0.473 |
ater | +0.468 |
Neg logit contributions | |
Chaff | -0.358 |
Snape | -0.342 |
transcripts | -0.329 |
tied | -0.327 |
loophole | -0.323 |
Token | offers |
Token ID | 4394 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
ariat | +1.839 |
ombat | +1.314 |
ftime | +1.245 |
ater | +1.241 |
borgh | +1.235 |
Neg logit contributions | |
Chaff | -0.928 |
Snape | -0.893 |
transcripts | -0.857 |
tied | -0.842 |
loophole | -0.837 |
Token | a |
Token ID | 257 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ariat | +2.298 |
ombat | +1.616 |
ftime | +1.526 |
borgh | +1.516 |
ater | +1.513 |
Neg logit contributions | |
Chaff | -1.289 |
Snape | -1.244 |
transcripts | -1.194 |
tied | -1.176 |
loophole | -1.163 |
Token | huge |
Token ID | 3236 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ariat | +1.455 |
ombat | +1.037 |
ftime | +0.978 |
ater | +0.975 |
borgh | +0.972 |
Neg logit contributions | |
Chaff | -0.748 |
Snape | -0.720 |
transcripts | -0.686 |
tied | -0.677 |
loophole | -0.674 |
Token | step |
Token ID | 2239 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ariat | +1.897 |
ombat | +1.338 |
ftime | +1.265 |
ater | +1.258 |
borgh | +1.254 |
Neg logit contributions | |
Chaff | -1.024 |
Snape | -0.987 |
transcripts | -0.946 |
loophole | -0.936 |
tied | -0.932 |
Token | up |
Token ID | 510 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ariat | +1.463 |
ombat | +1.046 |
ftime | +0.976 |
ater | +0.974 |
borgh | +0.965 |
Neg logit contributions | |
Chaff | -0.770 |
Snape | -0.750 |
transcripts | -0.710 |
tied | -0.706 |
loophole | -0.701 |
Token | in |
Token ID | 287 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ariat | +1.982 |
ombat | +1.408 |
ater | +1.333 |
ftime | +1.330 |
borgh | +1.316 |
Neg logit contributions | |
Chaff | -1.014 |
Snape | -0.980 |
transcripts | -0.934 |
tied | -0.922 |
loophole | -0.911 |
Token | bandwidth |
Token ID | 19484 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ariat | +1.563 |
ombat | +1.115 |
ftime | +1.058 |
ater | +1.055 |
borgh | +1.051 |
Neg logit contributions | |
Chaff | -0.770 |
Snape | -0.741 |
transcripts | -0.709 |
tied | -0.694 |
loophole | -0.690 |
Token | . |
Token ID | 13 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
ariat | +3.430 |
ombat | +2.358 |
ater | +2.228 |
ftime | +2.219 |
borgh | +2.200 |
Neg logit contributions | |
Chaff | -2.142 |
Snape | -2.074 |
transcripts | -1.992 |
tied | -1.947 |
loophole | -1.945 |
Token | My |
Token ID | 2011 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
Chaff | +0.200 |
Snape | +0.190 |
transcripts | +0.179 |
Misc | +0.177 |
Porn | +0.176 |
Neg logit contributions | |
ariat | -0.442 |
ombat | -0.320 |
ftime | -0.305 |
ater | -0.303 |
adium | -0.301 |
Token | MI |
Token ID | 15789 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ariat | +0.257 |
ombat | +0.185 |
ftime | +0.175 |
borgh | +0.174 |
ater | +0.174 |
Neg logit contributions | |
Chaff | -0.122 |
Snape | -0.117 |
transcripts | -0.112 |
loophole | -0.110 |
tied | -0.109 |
Token | 424 |
Token ID | 40090 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Chaff | +0.085 |
Snape | +0.083 |
transcripts | +0.079 |
tied | +0.077 |
loophole | +0.076 |
Neg logit contributions | |
ariat | -0.175 |
ombat | -0.125 |
ftime | -0.119 |
ater | -0.119 |
borgh | -0.118 |
Token | WR |
Token ID | 18564 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ariat | +0.903 |
ombat | +0.641 |
ater | +0.609 |
ftime | +0.606 |
borgh | +0.602 |
Neg logit contributions | |
Chaff | -0.463 |
Snape | -0.447 |
transcripts | -0.427 |
tied | -0.415 |
loophole | -0.415 |
Token | had |
Token ID | 550 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
ariat | +1.226 |
ombat | +0.865 |
ater | +0.820 |
ftime | +0.819 |
borgh | +0.814 |
Neg logit contributions | |
Chaff | -0.651 |
Snape | -0.627 |
transcripts | -0.602 |
tied | -0.590 |
loophole | -0.587 |
Token | been |
Token ID | 587 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ariat | +0.392 |
ombat | +0.274 |
ftime | +0.260 |
ater | +0.260 |
borgh | +0.259 |
Neg logit contributions | |
Chaff | -0.224 |
Snape | -0.215 |
transcripts | -0.208 |
tied | -0.206 |
Misc | -0.201 |
Token | configured |
Token ID | 17839 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ariat | +0.906 |
ombat | +0.648 |
ftime | +0.620 |
ater | +0.614 |
borgh | +0.613 |
Neg logit contributions | |
Chaff | -0.431 |
Snape | -0.413 |
tied | -0.396 |
transcripts | -0.394 |
loophole | -0.385 |
Token | so |
Token ID | 523 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ariat | +2.104 |
ombat | +1.500 |
ater | +1.426 |
ftime | +1.422 |
borgh | +1.412 |
Neg logit contributions | |
Chaff | -1.032 |
Snape | -0.995 |
transcripts | -0.948 |
tied | -0.926 |
loophole | -0.922 |
Token | long |
Token ID | 890 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ariat | +1.906 |
ombat | +1.387 |
ftime | +1.322 |
ater | +1.319 |
adium | +1.313 |
Neg logit contributions | |
Chaff | -0.797 |
Snape | -0.764 |
transcripts | -0.722 |
tied | -0.710 |
Misc | -0.701 |
Token | ago |
Token ID | 2084 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ariat | +1.314 |
ombat | +0.928 |
ater | +0.877 |
ftime | +0.875 |
borgh | +0.873 |
Neg logit contributions | |
Chaff | -0.702 |
Snape | -0.677 |
transcripts | -0.644 |
tied | -0.638 |
loophole | -0.631 |
Token | iTunes |
Token ID | 4830 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ariat | +0.721 |
ombat | +0.512 |
ftime | +0.483 |
borgh | +0.481 |
adium | +0.480 |
Neg logit contributions | |
Chaff | -0.372 |
Snape | -0.358 |
transcripts | -0.350 |
tied | -0.338 |
loophole | -0.334 |
Token | search |
Token ID | 2989 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
Chaff | +0.778 |
transcripts | +0.742 |
Snape | +0.740 |
tied | +0.714 |
Disclosure | +0.704 |
Neg logit contributions | |
ariat | -1.636 |
ombat | -1.162 |
borgh | -1.116 |
adium | -1.107 |
ftime | -1.105 |
Token | and |
Token ID | 290 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ariat | +0.238 |
ombat | +0.168 |
ater | +0.157 |
borgh | +0.157 |
ftime | +0.157 |
Neg logit contributions | |
Chaff | -0.128 |
Snape | -0.123 |
transcripts | -0.123 |
tied | -0.119 |
loophole | -0.117 |
Token | ranking |
Token ID | 12759 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Chaff | +0.108 |
Snape | +0.103 |
transcripts | +0.101 |
tied | +0.099 |
loophole | +0.097 |
Neg logit contributions | |
ariat | -0.225 |
ombat | -0.162 |
ftime | -0.154 |
borgh | -0.153 |
adium | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Chaff | +0.105 |
Snape | +0.101 |
transcripts | +0.099 |
tied | +0.097 |
loophole | +0.095 |
Neg logit contributions | |
ariat | -0.172 |
ombat | -0.121 |
borgh | -0.113 |
ftime | -0.112 |
ater | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ariat | +0.796 |
ombat | +0.575 |
ater | +0.544 |
ftime | +0.544 |
borgh | +0.542 |
Neg logit contributions | |
Chaff | -0.363 |
Snape | -0.349 |
transcripts | -0.336 |
tied | -0.326 |
loophole | -0.323 |
Token | helps |
Token ID | 5419 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
ariat | +1.067 |
ombat | +0.773 |
ftime | +0.729 |
ater | +0.726 |
borgh | +0.724 |
Neg logit contributions | |
Chaff | -0.509 |
Snape | -0.489 |
transcripts | -0.470 |
tied | -0.458 |
loophole | -0.453 |
Token | other |
Token ID | 584 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
Chaff | +0.209 |
Snape | +0.202 |
transcripts | +0.196 |
tied | +0.192 |
Misc | +0.189 |
Neg logit contributions | |
ariat | -0.383 |
ombat | -0.272 |
ftime | -0.256 |
adium | -0.254 |
ater | -0.254 |
Token | people |
Token ID | 661 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Chaff | +0.031 |
Snape | +0.030 |
transcripts | +0.029 |
tied | +0.028 |
Lynd | +0.028 |
Neg logit contributions | |
ariat | -0.058 |
ombat | -0.042 |
borgh | -0.039 |
ftime | -0.039 |
adium | -0.039 |
Token | discover |
Token ID | 7073 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
ariat | +0.127 |
ombat | +0.091 |
ftime | +0.086 |
borgh | +0.085 |
ater | +0.085 |
Neg logit contributions | |
Chaff | -0.067 |
Snape | -0.065 |
transcripts | -0.063 |
tied | -0.062 |
loophole | -0.061 |
Token | this |
Token ID | 428 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ariat | +0.468 |
ombat | +0.334 |
ftime | +0.316 |
borgh | +0.314 |
ater | +0.313 |
Neg logit contributions | |
Chaff | -0.243 |
Snape | -0.234 |
transcripts | -0.227 |
tied | -0.220 |
Misc | -0.218 |
Token | can |
Token ID | 460 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ariat | +2.210 |
ombat | +1.570 |
ater | +1.490 |
ftime | +1.487 |
borgh | +1.475 |
Neg logit contributions | |
Chaff | -1.130 |
Snape | -1.091 |
transcripts | -1.040 |
tied | -1.017 |
loophole | -1.012 |
Token | now |
Token ID | 783 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ariat | +1.727 |
ombat | +1.219 |
ater | +1.156 |
ftime | +1.155 |
borgh | +1.146 |
Neg logit contributions | |
Chaff | -0.908 |
Snape | -0.878 |
transcripts | -0.838 |
tied | -0.825 |
loophole | -0.820 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ariat | +0.753 |
ombat | +0.530 |
ftime | +0.504 |
ater | +0.504 |
borgh | +0.500 |
Neg logit contributions | |
Chaff | -0.390 |
Snape | -0.378 |
transcripts | -0.362 |
tied | -0.358 |
loophole | -0.354 |
Token |
|
Token ID | 198 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
Chaff | +0.435 |
Snape | +0.420 |
transcripts | +0.398 |
tied | +0.390 |
Misc | +0.390 |
Neg logit contributions | |
ariat | -0.881 |
ombat | -0.631 |
ftime | -0.599 |
ater | -0.596 |
borgh | -0.590 |
Token | be |
Token ID | 1350 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
Chaff | +0.310 |
Snape | +0.302 |
transcripts | +0.287 |
beard | +0.287 |
tied | +0.286 |
Neg logit contributions | |
ariat | -0.566 |
ombat | -0.394 |
ftime | -0.375 |
ater | -0.370 |
adium | -0.368 |
Token | done |
Token ID | 1760 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
ariat | +0.329 |
ombat | +0.240 |
ftime | +0.230 |
ater | +0.228 |
borgh | +0.227 |
Neg logit contributions | |
Chaff | -0.131 |
Snape | -0.126 |
tied | -0.121 |
transcripts | -0.119 |
loophole | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
ariat | +4.104 |
ombat | +2.883 |
ater | +2.737 |
ftime | +2.721 |
borgh | +2.698 |
Neg logit contributions | |
Chaff | -2.258 |
Snape | -2.177 |
transcripts | -2.085 |
loophole | -2.027 |
tied | -2.024 |
Token | This |
Token ID | 770 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
ariat | +0.243 |
ombat | +0.176 |
ftime | +0.169 |
ater | +0.167 |
borgh | +0.165 |
Neg logit contributions | |
Chaff | -0.111 |
Snape | -0.106 |
transcripts | -0.099 |
Misc | -0.098 |
Porn | -0.098 |
Token | can |
Token ID | 460 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ariat | +0.161 |
ombat | +0.115 |
ater | +0.110 |
ftime | +0.109 |
adium | +0.108 |
Neg logit contributions | |
Chaff | -0.081 |
Snape | -0.078 |
transcripts | -0.074 |
loophole | -0.074 |
tied | -0.074 |
Token | cut |
Token ID | 2005 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ariat | +1.349 |
ombat | +0.947 |
ater | +0.900 |
ftime | +0.899 |
adium | +0.893 |
Neg logit contributions | |
Chaff | -0.738 |
Snape | -0.714 |
tied | -0.682 |
transcripts | -0.682 |
loophole | -0.675 |
Token | down |
Token ID | 866 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Chaff | +0.057 |
Snape | +0.055 |
transcripts | +0.052 |
tied | +0.051 |
Misc | +0.051 |
Neg logit contributions | |
ariat | -0.145 |
ombat | -0.107 |
ftime | -0.103 |
ater | -0.102 |
borgh | -0.101 |
Token | Follow |
Token ID | 7155 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
ariat | +0.661 |
ombat | +0.471 |
ftime | +0.443 |
borgh | +0.441 |
ater | +0.441 |
Neg logit contributions | |
Chaff | -0.339 |
Snape | -0.324 |
transcripts | -0.310 |
tied | -0.303 |
Statement | -0.300 |
Token | Justin |
Token ID | 10799 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ariat | +2.376 |
ombat | +1.731 |
ater | +1.653 |
ftime | +1.647 |
borgh | +1.635 |
Neg logit contributions | |
Chaff | -0.978 |
Snape | -0.938 |
transcripts | -0.888 |
tied | -0.861 |
loophole | -0.860 |
Token | on |
Token ID | 319 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ariat | +1.995 |
ombat | +1.427 |
ater | +1.369 |
ftime | +1.362 |
borgh | +1.354 |
Neg logit contributions | |
Chaff | -0.899 |
Snape | -0.873 |
transcripts | -0.835 |
loophole | -0.819 |
pornographic | -0.809 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ariat | +0.795 |
ombat | +0.580 |
ftime | +0.560 |
ater | +0.554 |
borgh | +0.553 |
Neg logit contributions | |
Chaff | -0.297 |
Snape | -0.285 |
transcripts | -0.263 |
Porn | -0.261 |
Misc | -0.259 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
Chaff | +0.083 |
Snape | +0.080 |
transcripts | +0.076 |
Misc | +0.075 |
tied | +0.074 |
Neg logit contributions | |
ariat | -0.176 |
ombat | -0.125 |
ftime | -0.119 |
adium | -0.118 |
ater | -0.118 |
Token | by |
Token ID | 1525 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Chaff | +0.082 |
Snape | +0.080 |
transcripts | +0.075 |
Statement | +0.074 |
tied | +0.074 |
Neg logit contributions | |
ariat | -0.177 |
ombat | -0.127 |
ftime | -0.120 |
ater | -0.120 |
borgh | -0.119 |
Token | Julia |
Token ID | 22300 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ariat | +3.869 |
ombat | +2.752 |
ater | +2.615 |
ftime | +2.608 |
borgh | +2.587 |
Neg logit contributions | |
Chaff | -1.942 |
Snape | -1.872 |
transcripts | -1.784 |
tied | -1.738 |
loophole | -1.734 |
Token | Py |
Token ID | 9485 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Chaff | +0.486 |
Snape | +0.466 |
transcripts | +0.434 |
Misc | +0.433 |
Porn | +0.428 |
Neg logit contributions | |
ariat | -0.956 |
ombat | -0.683 |
ftime | -0.647 |
ater | -0.642 |
borgh | -0.637 |
Token | per |
Token ID | 525 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Chaff | +1.470 |
Snape | +1.435 |
beard | +1.378 |
transcripts | +1.372 |
tied | +1.357 |
Neg logit contributions | |
ariat | -2.238 |
ombat | -1.494 |
ftime | -1.413 |
borgh | -1.401 |
IUM | -1.392 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Chaff | +1.054 |
Snape | +1.009 |
transcripts | +0.965 |
tied | +0.945 |
Lynd | +0.942 |
Neg logit contributions | |
ariat | -1.961 |
ombat | -1.391 |
ftime | -1.310 |
adium | -1.284 |
ater | -1.281 |
Token |
|
Token ID | 198 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
Chaff | +0.326 |
Snape | +0.314 |
transcripts | +0.296 |
tied | +0.292 |
Misc | +0.291 |
Neg logit contributions | |
ariat | -0.684 |
ombat | -0.491 |
ftime | -0.469 |
ater | -0.464 |
borgh | -0.459 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ariat | +1.463 |
ombat | +1.046 |
ftime | +0.984 |
borgh | +0.977 |
adium | +0.970 |
Neg logit contributions | |
Chaff | -0.783 |
Snape | -0.762 |
tied | -0.719 |
transcripts | -0.719 |
Misc | -0.707 |
Token | rest |
Token ID | 1334 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ariat | +1.583 |
ombat | +1.124 |
ftime | +1.058 |
borgh | +1.048 |
adium | +1.044 |
Neg logit contributions | |
Chaff | -0.867 |
Snape | -0.839 |
transcripts | -0.797 |
tied | -0.796 |
loophole | -0.783 |
Token | . |
Token ID | 13 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ariat | +2.783 |
ombat | +1.939 |
ftime | +1.819 |
ater | +1.816 |
borgh | +1.807 |
Neg logit contributions | |
Chaff | -1.662 |
Snape | -1.614 |
transcripts | -1.540 |
tied | -1.526 |
Misc | -1.502 |
Token | As |
Token ID | 1081 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ariat | +1.746 |
ombat | +1.268 |
ftime | +1.201 |
ater | +1.196 |
adium | +1.187 |
Neg logit contributions | |
Chaff | -0.783 |
Snape | -0.750 |
transcripts | -0.703 |
Misc | -0.691 |
tied | -0.688 |
Token | soon |
Token ID | 2582 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ariat | +2.059 |
ombat | +1.462 |
ftime | +1.364 |
ater | +1.355 |
borgh | +1.354 |
Neg logit contributions | |
Chaff | -1.129 |
Snape | -1.098 |
transcripts | -1.041 |
tied | -1.030 |
Misc | -1.018 |
Token | as |
Token ID | 355 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
ariat | +2.930 |
ombat | +2.049 |
ater | +1.932 |
ftime | +1.929 |
borgh | +1.915 |
Neg logit contributions | |
Chaff | -1.688 |
Snape | -1.633 |
transcripts | -1.564 |
tied | -1.530 |
loophole | -1.523 |
Token | we |
Token ID | 356 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ariat | +4.160 |
ombat | +2.967 |
ater | +2.812 |
ftime | +2.808 |
borgh | +2.786 |
Neg logit contributions | |
Chaff | -2.089 |
Snape | -2.016 |
transcripts | -1.919 |
tied | -1.876 |
loophole | -1.868 |
Token | have |
Token ID | 423 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ariat | +0.972 |
ombat | +0.682 |
ftime | +0.645 |
ater | +0.641 |
adium | +0.638 |
Neg logit contributions | |
Chaff | -0.556 |
Snape | -0.538 |
transcripts | -0.514 |
tied | -0.511 |
loophole | -0.503 |
Token | reached |
Token ID | 4251 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ariat | +0.066 |
ombat | +0.047 |
ftime | +0.045 |
adium | +0.044 |
borgh | +0.044 |
Neg logit contributions | |
Chaff | -0.031 |
Snape | -0.030 |
tied | -0.030 |
transcripts | -0.029 |
labelled | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
ariat | +1.697 |
ombat | +1.198 |
ftime | +1.136 |
borgh | +1.122 |
ater | +1.118 |
Neg logit contributions | |
Chaff | -0.974 |
Snape | -0.943 |
transcripts | -0.908 |
tied | -0.898 |
Misc | -0.883 |
Token | boil |
Token ID | 20667 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ariat | +0.483 |
ombat | +0.344 |
ftime | +0.323 |
ater | +0.322 |
adium | +0.321 |
Neg logit contributions | |
Chaff | -0.263 |
Snape | -0.254 |
tied | -0.241 |
transcripts | -0.240 |
loophole | -0.238 |
Token | this |
Token ID | 428 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ariat | +0.241 |
ombat | +0.174 |
ftime | +0.167 |
adium | +0.165 |
borgh | +0.164 |
Neg logit contributions | |
Chaff | -0.112 |
Snape | -0.110 |
transcripts | -0.106 |
Misc | -0.102 |
Lynd | -0.102 |
Token | article |
Token ID | 2708 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
Chaff | +0.404 |
Snape | +0.396 |
transcripts | +0.383 |
Misc | +0.378 |
Porn | +0.376 |
Neg logit contributions | |
ariat | -0.826 |
ombat | -0.595 |
ftime | -0.563 |
borgh | -0.560 |
adium | -0.560 |
Token | Santos |
Token ID | 28458 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
Chaff | +0.270 |
Snape | +0.267 |
transcripts | +0.255 |
tied | +0.251 |
Porn | +0.246 |
Neg logit contributions | |
ariat | -0.560 |
ombat | -0.404 |
ftime | -0.382 |
borgh | -0.381 |
adium | -0.380 |
Token | Tour |
Token ID | 9852 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ariat | +0.033 |
ombat | +0.023 |
ftime | +0.022 |
ater | +0.022 |
adium | +0.022 |
Neg logit contributions | |
Chaff | -0.017 |
Snape | -0.017 |
transcripts | -0.016 |
tied | -0.016 |
Misc | -0.016 |
Token | Down |
Token ID | 5588 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ariat | +2.172 |
ombat | +1.550 |
ater | +1.472 |
ftime | +1.469 |
borgh | +1.452 |
Neg logit contributions | |
Chaff | -1.099 |
Snape | -1.057 |
transcripts | -1.013 |
tied | -0.987 |
loophole | -0.982 |
Token | Under |
Token ID | 4698 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ariat | +0.593 |
ombat | +0.416 |
ater | +0.394 |
ftime | +0.392 |
borgh | +0.391 |
Neg logit contributions | |
Chaff | -0.331 |
Snape | -0.321 |
transcripts | -0.307 |
tied | -0.303 |
Misc | -0.302 |
Token | Stage |
Token ID | 15371 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ariat | +3.988 |
ombat | +2.825 |
ater | +2.685 |
ftime | +2.675 |
borgh | +2.653 |
Neg logit contributions | |
Chaff | -2.055 |
Snape | -1.982 |
transcripts | -1.889 |
loophole | -1.841 |
tied | -1.839 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ariat | +2.578 |
ombat | +1.828 |
ater | +1.734 |
ftime | +1.726 |
borgh | +1.717 |
Neg logit contributions | |
Chaff | -1.338 |
Snape | -1.290 |
transcripts | -1.238 |
tied | -1.207 |
Misc | -1.200 |
Token | Results |
Token ID | 15691 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ariat | +1.140 |
ombat | +0.809 |
ater | +0.763 |
ftime | +0.761 |
borgh | +0.758 |
Neg logit contributions | |
Chaff | -0.597 |
Snape | -0.575 |
transcripts | -0.551 |
tied | -0.540 |
Misc | -0.536 |
Token | : |
Token ID | 25 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
ariat | +1.382 |
ombat | +0.987 |
ater | +0.934 |
ftime | +0.930 |
borgh | +0.927 |
Neg logit contributions | |
Chaff | -0.696 |
Snape | -0.671 |
transcripts | -0.638 |
tied | -0.626 |
Misc | -0.625 |
Token | Un |
Token ID | 791 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ariat | +0.550 |
ombat | +0.393 |
ftime | +0.372 |
ater | +0.372 |
borgh | +0.369 |
Neg logit contributions | |
Chaff | -0.276 |
Snape | -0.266 |
transcripts | -0.252 |
Misc | -0.248 |
tied | -0.248 |
Token | - |
Token ID | 12 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ariat | +1.872 |
ombat | +1.252 |
ftime | +1.172 |
ater | +1.159 |
borgh | +1.153 |
Neg logit contributions | |
Chaff | -1.363 |
Snape | -1.322 |
transcripts | -1.286 |
tied | -1.254 |
Misc | -1.247 |
Token | ethyl |
Token ID | 21610 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ariat | +1.445 |
ombat | +0.981 |
ftime | +0.918 |
ater | +0.915 |
borgh | +0.902 |
Neg logit contributions | |
Chaff | -0.968 |
Snape | -0.936 |
transcripts | -0.904 |
tied | -0.889 |
loophole | -0.883 |
Token | - |
Token ID | 12 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
ariat | +2.481 |
ombat | +1.717 |
ater | +1.608 |
ftime | +1.607 |
borgh | +1.590 |
Neg logit contributions | |
Chaff | -1.536 |
Snape | -1.485 |
transcripts | -1.433 |
tied | -1.401 |
Misc | -1.396 |
Token | N |
Token ID | 45 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ariat | +3.806 |
ombat | +2.721 |
ater | +2.586 |
ftime | +2.581 |
borgh | +2.558 |
Neg logit contributions | |
Chaff | -1.829 |
Snape | -1.759 |
transcripts | -1.681 |
tied | -1.636 |
loophole | -1.627 |
Token | -( |
Token ID | 30420 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ariat | +2.139 |
ombat | +1.438 |
ftime | +1.356 |
ater | +1.347 |
borgh | +1.343 |
Neg logit contributions | |
Chaff | -1.484 |
Snape | -1.437 |
transcripts | -1.394 |
tied | -1.365 |
loophole | -1.355 |
Token | t |
Token ID | 83 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ariat | +3.028 |
ombat | +2.164 |
ftime | +2.048 |
ater | +2.045 |
borgh | +2.034 |
Neg logit contributions | |
Chaff | -1.423 |
Snape | -1.370 |
transcripts | -1.318 |
tied | -1.287 |
loophole | -1.268 |
Token | et |
Token ID | 316 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ariat | +3.212 |
ombat | +2.013 |
ftime | +1.863 |
ater | +1.853 |
borgh | +1.830 |
Neg logit contributions | |
Chaff | -2.995 |
Snape | -2.926 |
transcripts | -2.848 |
tied | -2.793 |
loophole | -2.778 |
Token | rah |
Token ID | 11392 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ariat | +1.992 |
ombat | +1.279 |
ftime | +1.181 |
borgh | +1.163 |
ater | +1.160 |
Neg logit contributions | |
Chaff | -1.754 |
Snape | -1.713 |
transcripts | -1.662 |
tied | -1.638 |
Porn | -1.628 |
Token | yd |
Token ID | 5173 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ariat | +2.670 |
ombat | +1.914 |
ater | +1.816 |
ftime | +1.813 |
borgh | +1.804 |
Neg logit contributions | |
Chaff | -1.244 |
Snape | -1.204 |
transcripts | -1.147 |
tied | -1.118 |
loophole | -1.106 |
Token | ro |
Token ID | 305 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
ariat | +3.987 |
ombat | +2.675 |
ater | +2.516 |
ftime | +2.505 |
borgh | +2.481 |
Neg logit contributions | |
Chaff | -2.835 |
Snape | -2.753 |
transcripts | -2.652 |
tied | -2.597 |
loophole | -2.594 |
Token | - |
Token ID | 12 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ariat | +2.879 |
ombat | +1.954 |
ftime | +1.836 |
ater | +1.834 |
borgh | +1.810 |
Neg logit contributions | |
Chaff | -1.921 |
Snape | -1.860 |
transcripts | -1.793 |
tied | -1.758 |
loophole | -1.749 |