Token | holes |
Token ID | 28439 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
| +1.034 |
USS | +1.004 |
romeda | +0.996 |
Span | +0.989 |
Tempest | +0.987 |
Neg logit contributions | |
ijk | -0.397 |
�� | -0.377 |
ruct | -0.324 |
ld | -0.311 |
phe | -0.293 |
Token | in |
Token ID | 287 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
| +1.097 |
USS | +1.029 |
Span | +1.028 |
romeda | +1.014 |
Tempest | +0.988 |
Neg logit contributions | |
ijk | -1.468 |
�� | -1.464 |
ruct | -1.341 |
ld | -1.340 |
phe | -1.284 |
Token | American |
Token ID | 1605 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
| +0.469 |
USS | +0.452 |
Span | +0.452 |
Tempest | +0.438 |
romeda | +0.435 |
Neg logit contributions | |
ijk | -0.480 |
�� | -0.470 |
ruct | -0.432 |
ld | -0.426 |
phe | -0.410 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
| +0.409 |
USS | +0.395 |
Tempest | +0.387 |
Span | +0.386 |
romeda | +0.383 |
Neg logit contributions | |
ijk | -0.311 |
�� | -0.301 |
ld | -0.266 |
ruct | -0.263 |
phe | -0.259 |
Token | ' |
Token ID | 6 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ijk | +1.007 |
�� | +0.967 |
ruct | +0.914 |
ld | +0.908 |
elephants | +0.865 |
Neg logit contributions | |
| -0.833 |
USS | -0.800 |
romeda | -0.795 |
Span | -0.793 |
Tempest | -0.781 |
Token | MORE |
Token ID | 12011 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
ijk | +0.467 |
�� | +0.449 |
ruct | +0.427 |
ld | +0.424 |
elephants | +0.405 |
Neg logit contributions | |
| -0.339 |
USS | -0.325 |
romeda | -0.323 |
Span | -0.321 |
Tempest | -0.316 |
Token | completed |
Token ID | 5668 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ijk | +3.920 |
ld | +3.618 |
�� | +3.557 |
ruct | +3.441 |
elephants | +3.430 |
Neg logit contributions | |
USS | -4.403 |
| -4.352 |
romeda | -4.345 |
Span | -4.290 |
Tempest | -4.218 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ijk | +1.174 |
�� | +1.117 |
ruct | +1.054 |
ld | +1.052 |
elephants | +0.992 |
Neg logit contributions | |
| -1.264 |
USS | -1.231 |
romeda | -1.228 |
Span | -1.219 |
Tempest | -1.203 |
Token | swing |
Token ID | 9628 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ijk | +1.005 |
�� | +0.957 |
ld | +0.910 |
ruct | +0.900 |
elephants | +0.849 |
Neg logit contributions | |
| -1.103 |
romeda | -1.081 |
USS | -1.079 |
Span | -1.062 |
Tempest | -1.051 |
Token | through |
Token ID | 832 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
| +1.356 |
USS | +1.294 |
Span | +1.290 |
romeda | +1.289 |
Tempest | +1.267 |
Neg logit contributions | |
ijk | -1.553 |
�� | -1.495 |
ruct | -1.403 |
ld | -1.388 |
phe | -1.337 |
Token | North |
Token ID | 2258 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ijk | +0.485 |
�� | +0.464 |
ld | +0.437 |
ruct | +0.437 |
elephants | +0.414 |
Neg logit contributions | |
| -0.456 |
USS | -0.441 |
romeda | -0.440 |
Span | -0.436 |
Tempest | -0.430 |
Token | holes |
Token ID | 28439 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
| +0.649 |
USS | +0.632 |
romeda | +0.628 |
Span | +0.624 |
Tempest | +0.622 |
Neg logit contributions | |
ijk | -0.245 |
�� | -0.230 |
ruct | -0.199 |
ld | -0.193 |
phe | -0.178 |
Token | in |
Token ID | 287 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
| +0.867 |
USS | +0.814 |
Span | +0.812 |
romeda | +0.800 |
Tempest | +0.781 |
Neg logit contributions | |
ijk | -1.159 |
�� | -1.153 |
ruct | -1.056 |
ld | -1.054 |
phe | -1.011 |
Token | American |
Token ID | 1605 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
| +0.145 |
USS | +0.140 |
Span | +0.139 |
Tempest | +0.135 |
romeda | +0.135 |
Neg logit contributions | |
ijk | -0.153 |
�� | -0.150 |
ruct | -0.139 |
ld | -0.136 |
phe | -0.131 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
| +0.190 |
USS | +0.183 |
Tempest | +0.180 |
Span | +0.179 |
romeda | +0.177 |
Neg logit contributions | |
ijk | -0.165 |
�� | -0.160 |
ld | -0.143 |
ruct | -0.142 |
phe | -0.140 |
Token | ' |
Token ID | 6 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ijk | +1.030 |
�� | +0.991 |
ruct | +0.934 |
ld | +0.927 |
elephants | +0.884 |
Neg logit contributions | |
| -0.840 |
USS | -0.806 |
romeda | -0.799 |
Span | -0.799 |
Tempest | -0.786 |
Token | MORE |
Token ID | 12011 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ijk | +0.520 |
�� | +0.501 |
ruct | +0.474 |
ld | +0.471 |
elephants | +0.451 |
Neg logit contributions | |
| -0.369 |
USS | -0.353 |
romeda | -0.350 |
Span | -0.350 |
Tempest | -0.344 |
Token | as |
Token ID | 355 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ijk | +3.348 |
�� | +3.160 |
ld | +3.039 |
ruct | +2.971 |
elephants | +2.880 |
Neg logit contributions | |
| -3.597 |
USS | -3.568 |
romeda | -3.533 |
Span | -3.507 |
Tempest | -3.453 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ijk | +0.794 |
�� | +0.760 |
ld | +0.716 |
ruct | +0.711 |
elephants | +0.679 |
Neg logit contributions | |
| -0.862 |
USS | -0.838 |
romeda | -0.837 |
Span | -0.830 |
Tempest | -0.819 |
Token | 68 |
Token ID | 8257 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
| +0.174 |
USS | +0.170 |
romeda | +0.170 |
Span | +0.168 |
Tempest | +0.166 |
Neg logit contributions | |
ijk | -0.138 |
�� | -0.131 |
ld | -0.124 |
ruct | -0.122 |
elephants | -0.115 |
Token | - |
Token ID | 12 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ijk | +0.050 |
�� | +0.048 |
ruct | +0.045 |
ld | +0.045 |
elephants | +0.043 |
Neg logit contributions | |
| -0.044 |
USS | -0.042 |
Span | -0.042 |
romeda | -0.042 |
Tempest | -0.041 |
Token | year |
Token ID | 1941 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ijk | +0.547 |
�� | +0.516 |
ld | +0.475 |
ruct | +0.473 |
phe | +0.437 |
Neg logit contributions | |
| -0.891 |
USS | -0.869 |
romeda | -0.866 |
Span | -0.863 |
Tempest | -0.855 |
Token | . |
Token ID | 13 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
| +0.008 |
USS | +0.008 |
Span | +0.008 |
romeda | +0.008 |
Tempest | +0.008 |
Neg logit contributions | |
ijk | -0.009 |
�� | -0.009 |
ruct | -0.008 |
ld | -0.008 |
phe | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ijk | +0.067 |
�� | +0.065 |
ruct | +0.061 |
ld | +0.061 |
elephants | +0.059 |
Neg logit contributions | |
| -0.048 |
USS | -0.045 |
Span | -0.045 |
romeda | -0.045 |
Tempest | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
| +0.249 |
romeda | +0.245 |
USS | +0.243 |
Span | +0.240 |
Tempest | +0.237 |
Neg logit contributions | |
ijk | -0.335 |
�� | -0.313 |
ld | -0.307 |
ruct | -0.305 |
phe | -0.288 |
Token | Twitter |
Token ID | 14254 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
| +0.160 |
USS | +0.155 |
Span | +0.153 |
romeda | +0.152 |
Tempest | +0.150 |
Neg logit contributions | |
ijk | -0.168 |
�� | -0.162 |
ruct | -0.151 |
ld | -0.149 |
elephants | -0.144 |
Token | : |
Token ID | 25 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ijk | +0.880 |
�� | +0.839 |
ld | +0.793 |
ruct | +0.791 |
elephants | +0.749 |
Neg logit contributions | |
| -0.837 |
USS | -0.805 |
romeda | -0.804 |
Span | -0.794 |
Tempest | -0.787 |
Token | @ |
Token ID | 2488 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
ijk | +1.676 |
�� | +1.599 |
ld | +1.519 |
ruct | +1.511 |
elephants | +1.432 |
Neg logit contributions | |
| -1.590 |
USS | -1.534 |
romeda | -1.528 |
Span | -1.506 |
Tempest | -1.489 |
Token | brand |
Token ID | 17938 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ijk | +3.644 |
�� | +3.418 |
ld | +3.358 |
ruct | +3.277 |
phe | +3.105 |
Neg logit contributions | |
| -3.416 |
romeda | -3.282 |
USS | -3.238 |
Span | -3.233 |
Tempest | -3.228 |
Token | t |
Token ID | 83 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ijk | +0.626 |
�� | +0.594 |
ruct | +0.561 |
ld | +0.560 |
phe | +0.527 |
Neg logit contributions | |
| -0.625 |
USS | -0.603 |
Span | -0.599 |
romeda | -0.598 |
Tempest | -0.591 |
Token | st |
Token ID | 301 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
ijk | +0.094 |
�� | +0.089 |
ruct | +0.084 |
ld | +0.083 |
elephants | +0.079 |
Neg logit contributions | |
| -0.101 |
USS | -0.097 |
romeda | -0.096 |
Span | -0.096 |
Tempest | -0.095 |
Token | rib |
Token ID | 822 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
| +0.280 |
USS | +0.271 |
romeda | +0.269 |
Span | +0.268 |
Tempest | +0.265 |
Neg logit contributions | |
ijk | -0.273 |
�� | -0.259 |
ruct | -0.245 |
ld | -0.244 |
phe | -0.229 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
| +0.247 |
USS | +0.236 |
romeda | +0.233 |
Span | +0.232 |
Tempest | +0.230 |
Neg logit contributions | |
ijk | -0.420 |
�� | -0.403 |
ld | -0.385 |
ruct | -0.385 |
elephants | -0.367 |
Token | than |
Token ID | 621 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ijk | +0.110 |
�� | +0.106 |
ld | +0.099 |
ruct | +0.099 |
elephants | +0.094 |
Neg logit contributions | |
| -0.115 |
USS | -0.112 |
romeda | -0.111 |
Span | -0.110 |
Tempest | -0.108 |
Token | 10 |
Token ID | 838 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ijk | +0.248 |
�� | +0.239 |
ld | +0.224 |
ruct | +0.224 |
elephants | +0.213 |
Neg logit contributions | |
| -0.241 |
romeda | -0.234 |
USS | -0.233 |
Span | -0.231 |
Tempest | -0.228 |
Token | years |
Token ID | 812 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
| +0.332 |
USS | +0.318 |
romeda | +0.317 |
Span | +0.314 |
Tempest | +0.309 |
Neg logit contributions | |
ijk | -0.416 |
�� | -0.402 |
ld | -0.378 |
ruct | -0.378 |
elephants | -0.361 |
Token | in |
Token ID | 287 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
| +0.002 |
USS | +0.002 |
romeda | +0.002 |
Span | +0.002 |
Tempest | +0.002 |
Neg logit contributions | |
ijk | -0.002 |
�� | -0.002 |
ruct | -0.002 |
ld | -0.002 |
elephants | -0.002 |
Token | prison |
Token ID | 3770 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
| +0.337 |
USS | +0.328 |
Span | +0.325 |
romeda | +0.325 |
Tempest | +0.322 |
Neg logit contributions | |
ijk | -0.165 |
�� | -0.155 |
ruct | -0.140 |
ld | -0.138 |
phe | -0.126 |
Token | MORE |
Token ID | 12011 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ijk | +0.017 |
�� | +0.016 |
ruct | +0.015 |
ld | +0.015 |
phe | +0.014 |
Neg logit contributions | |
| -0.015 |
USS | -0.015 |
Span | -0.015 |
romeda | -0.015 |
Tempest | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ijk | +3.264 |
�� | +3.106 |
ld | +2.996 |
ruct | +2.910 |
elephants | +2.844 |
Neg logit contributions | |
| -3.597 |
USS | -3.561 |
romeda | -3.543 |
Span | -3.486 |
Tempest | -3.428 |
Token | tick |
Token ID | 4378 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ijk | +1.159 |
�� | +1.103 |
ld | +1.046 |
ruct | +1.036 |
elephants | +0.988 |
Neg logit contributions | |
| -1.274 |
USS | -1.233 |
romeda | -1.227 |
Span | -1.224 |
Tempest | -1.206 |
Token | ed |
Token ID | 276 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ijk | +1.272 |
�� | +1.215 |
ld | +1.142 |
ruct | +1.141 |
elephants | +1.077 |
Neg logit contributions | |
| -1.321 |
USS | -1.282 |
romeda | -1.274 |
Span | -1.272 |
Tempest | -1.253 |
Token | through |
Token ID | 832 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ijk | +1.968 |
�� | +1.896 |
ld | +1.804 |
ruct | +1.801 |
elephants | +1.728 |
Neg logit contributions | |
| -1.303 |
USS | -1.257 |
romeda | -1.254 |
Span | -1.246 |
Tempest | -1.216 |
Token | her |
Token ID | 607 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ijk | +1.148 |
�� | +1.094 |
ld | +1.030 |
ruct | +1.025 |
elephants | +0.973 |
Neg logit contributions | |
| -1.262 |
USS | -1.225 |
romeda | -1.221 |
Span | -1.213 |
Tempest | -1.198 |
Token | holes |
Token ID | 28439 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
| +0.534 |
USS | +0.521 |
romeda | +0.517 |
Span | +0.514 |
Tempest | +0.512 |
Neg logit contributions | |
ijk | -0.196 |
�� | -0.185 |
ruct | -0.159 |
ld | -0.154 |
phe | -0.142 |
Token | in |
Token ID | 287 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
| +0.833 |
USS | +0.782 |
Span | +0.780 |
romeda | +0.768 |
Tempest | +0.747 |
Neg logit contributions | |
ijk | -1.137 |
�� | -1.134 |
ruct | -1.035 |
ld | -1.033 |
phe | -0.994 |
Token | American |
Token ID | 1605 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
| +0.109 |
USS | +0.106 |
Span | +0.105 |
Tempest | +0.102 |
romeda | +0.101 |
Neg logit contributions | |
ijk | -0.113 |
�� | -0.111 |
ruct | -0.102 |
ld | -0.100 |
phe | -0.096 |
Token | politics |
Token ID | 4819 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
| +0.288 |
USS | +0.279 |
Tempest | +0.273 |
Span | +0.272 |
romeda | +0.269 |
Neg logit contributions | |
ijk | -0.263 |
�� | -0.257 |
ld | -0.228 |
ruct | -0.226 |
phe | -0.223 |
Token | ' |
Token ID | 6 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ijk | +0.992 |
�� | +0.958 |
ruct | +0.897 |
ld | +0.889 |
elephants | +0.850 |
Neg logit contributions | |
| -0.785 |
USS | -0.751 |
Span | -0.746 |
romeda | -0.743 |
Tempest | -0.732 |
Token | MORE |
Token ID | 12011 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
ijk | +0.574 |
�� | +0.553 |
ruct | +0.524 |
ld | +0.521 |
elephants | +0.498 |
Neg logit contributions | |
| -0.409 |
USS | -0.391 |
romeda | -0.388 |
Span | -0.387 |
Tempest | -0.381 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ijk | +3.061 |
�� | +2.877 |
ld | +2.760 |
ruct | +2.721 |
elephants | +2.628 |
Neg logit contributions | |
| -3.569 |
romeda | -3.530 |
USS | -3.519 |
Span | -3.470 |
Tempest | -3.410 |
Token | told |
Token ID | 1297 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ijk | +1.636 |
�� | +1.547 |
ld | +1.486 |
ruct | +1.472 |
elephants | +1.404 |
Neg logit contributions | |
| -1.782 |
USS | -1.752 |
romeda | -1.738 |
Span | -1.719 |
Tempest | -1.699 |
Token | 77 |
Token ID | 8541 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ijk | +0.670 |
�� | +0.641 |
ruct | +0.602 |
ld | +0.601 |
elephants | +0.569 |
Neg logit contributions | |
| -0.668 |
USS | -0.644 |
romeda | -0.642 |
Span | -0.637 |
Tempest | -0.630 |
Token | WA |
Token ID | 15543 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
| +0.320 |
USS | +0.309 |
Span | +0.306 |
romeda | +0.306 |
Tempest | +0.303 |
Neg logit contributions | |
ijk | -0.331 |
�� | -0.317 |
ruct | -0.300 |
ld | -0.295 |
elephants | -0.279 |
Token | BC |
Token ID | 2749 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ijk | +0.129 |
�� | +0.123 |
ruct | +0.115 |
ld | +0.115 |
elephants | +0.108 |
Neg logit contributions | |
| -0.141 |
USS | -0.136 |
romeda | -0.136 |
Span | -0.135 |
Tempest | -0.133 |
Token | has |
Token ID | 468 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ijk | +0.218 |
�� | +0.208 |
ruct | +0.196 |
ld | +0.195 |
elephants | +0.184 |
Neg logit contributions | |
| -0.232 |
romeda | -0.226 |
USS | -0.226 |
Span | -0.224 |
Tempest | -0.221 |
Token | been |
Token ID | 587 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
| +0.131 |
USS | +0.127 |
romeda | +0.126 |
Span | +0.125 |
Tempest | +0.124 |
Neg logit contributions | |
ijk | -0.142 |
�� | -0.137 |
ruct | -0.129 |
ld | -0.128 |
elephants | -0.121 |
Token | issued |
Token ID | 4884 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
| +0.210 |
USS | +0.205 |
romeda | +0.205 |
Span | +0.203 |
Tempest | +0.200 |
Neg logit contributions | |
ijk | -0.212 |
�� | -0.202 |
ruct | -0.191 |
ld | -0.191 |
elephants | -0.180 |
Token | ; |
Token ID | 26 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ijk | +0.063 |
�� | +0.060 |
ruct | +0.056 |
ld | +0.056 |
elephants | +0.053 |
Neg logit contributions | |
| -0.066 |
USS | -0.065 |
romeda | -0.064 |
Span | -0.064 |
Tempest | -0.063 |
Token | ii |
Token ID | 21065 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
| +0.307 |
Span | +0.291 |
USS | +0.290 |
romeda | +0.288 |
Tempest | +0.287 |
Neg logit contributions | |
ijk | -0.309 |
�� | -0.296 |
ruct | -0.275 |
ld | -0.272 |
phe | -0.261 |
Token | ) |
Token ID | 8 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ijk | +0.595 |
�� | +0.567 |
ruct | +0.545 |
ld | +0.544 |
elephants | +0.514 |
Neg logit contributions | |
| -0.454 |
USS | -0.438 |
romeda | -0.436 |
Span | -0.432 |
Tempest | -0.424 |
Token | require |
Token ID | 2421 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ijk | +2.973 |
�� | +2.818 |
ld | +2.692 |
ruct | +2.680 |
elephants | +2.525 |
Neg logit contributions | |
romeda | -3.587 |
USS | -3.582 |
| -3.559 |
Span | -3.487 |
Tempest | -3.451 |
Token | that |
Token ID | 326 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ijk | +0.323 |
�� | +0.308 |
ruct | +0.289 |
ld | +0.288 |
elephants | +0.273 |
Neg logit contributions | |
| -0.328 |
USS | -0.317 |
romeda | -0.315 |
Span | -0.314 |
Tempest | -0.310 |
Token | policies |
Token ID | 4788 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ijk | +0.374 |
�� | +0.357 |
ruct | +0.334 |
ld | +0.333 |
elephants | +0.316 |
Neg logit contributions | |
| -0.410 |
USS | -0.397 |
romeda | -0.395 |
Span | -0.393 |
Tempest | -0.388 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ijk | +0.332 |
�� | +0.317 |
ruct | +0.299 |
ld | +0.299 |
elephants | +0.283 |
Neg logit contributions | |
| -0.338 |
USS | -0.329 |
romeda | -0.328 |
Span | -0.326 |
Tempest | -0.322 |
Token | procedures |
Token ID | 9021 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
| +0.130 |
USS | +0.125 |
romeda | +0.124 |
Span | +0.124 |
Tempest | +0.122 |
Neg logit contributions | |
ijk | -0.148 |
�� | -0.142 |
ruct | -0.134 |
ld | -0.133 |
elephants | -0.127 |
Token | ? |
Token ID | 30 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
| +0.123 |
USS | +0.119 |
romeda | +0.118 |
Span | +0.118 |
Tempest | +0.116 |
Neg logit contributions | |
ijk | -0.130 |
�� | -0.124 |
ruct | -0.117 |
ld | -0.116 |
elephants | -0.110 |
Token | Chinese |
Token ID | 3999 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ijk | +0.034 |
�� | +0.033 |
ruct | +0.031 |
ld | +0.031 |
elephants | +0.029 |
Neg logit contributions | |
| -0.027 |
USS | -0.026 |
romeda | -0.026 |
Span | -0.026 |
Tempest | -0.025 |
Token | production |
Token ID | 3227 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
ijk | +0.370 |
�� | +0.352 |
ruct | +0.332 |
ld | +0.331 |
elephants | +0.316 |
Neg logit contributions | |
| -0.357 |
USS | -0.345 |
romeda | -0.344 |
Span | -0.340 |
Tempest | -0.334 |
Token | value |
Token ID | 1988 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ijk | +0.713 |
�� | +0.675 |
ruct | +0.638 |
ld | +0.638 |
elephants | +0.607 |
Neg logit contributions | |
| -0.726 |
USS | -0.710 |
romeda | -0.708 |
Span | -0.701 |
Tempest | -0.685 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ijk | +1.071 |
�� | +1.014 |
ruct | +0.960 |
ld | +0.958 |
elephants | +0.910 |
Neg logit contributions | |
| -1.052 |
USS | -1.025 |
romeda | -1.020 |
Span | -1.012 |
Tempest | -0.990 |
Token | | |
Token ID | 930 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
ijk | +1.611 |
�� | +1.534 |
ruct | +1.471 |
ld | +1.467 |
elephants | +1.387 |
Neg logit contributions | |
| -1.270 |
USS | -1.242 |
romeda | -1.237 |
Span | -1.221 |
Tempest | -1.192 |
Token | I |
Token ID | 314 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
ijk | +3.515 |
�� | +3.289 |
ld | +3.209 |
ruct | +3.200 |
phe | +2.989 |
Neg logit contributions | |
| -2.969 |
romeda | -2.871 |
USS | -2.866 |
Span | -2.810 |
Tempest | -2.744 |
Token | thought |
Token ID | 1807 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ijk | +0.649 |
�� | +0.615 |
ld | +0.588 |
ruct | +0.587 |
phe | +0.550 |
Neg logit contributions | |
| -0.641 |
USS | -0.618 |
romeda | -0.617 |
Span | -0.614 |
Tempest | -0.601 |
Token | he |
Token ID | 339 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ijk | +0.708 |
�� | +0.675 |
ruct | +0.640 |
ld | +0.639 |
elephants | +0.609 |
Neg logit contributions | |
| -0.619 |
USS | -0.601 |
romeda | -0.593 |
Span | -0.590 |
Tempest | -0.578 |
Token | had |
Token ID | 550 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
| +0.085 |
USS | +0.082 |
romeda | +0.082 |
Span | +0.082 |
Tempest | +0.081 |
Neg logit contributions | |
ijk | -0.080 |
�� | -0.076 |
ruct | -0.072 |
ld | -0.072 |
elephants | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ijk | +0.360 |
�� | +0.343 |
ruct | +0.322 |
ld | +0.321 |
elephants | +0.304 |
Neg logit contributions | |
| -0.390 |
USS | -0.377 |
romeda | -0.375 |
Span | -0.373 |
Tempest | -0.368 |
Token | @ |
Token ID | 2488 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
| +0.499 |
USS | +0.479 |
romeda | +0.476 |
Span | +0.474 |
Tempest | +0.467 |
Neg logit contributions | |
ijk | -0.628 |
�� | -0.604 |
ruct | -0.571 |
ld | -0.568 |
elephants | -0.541 |
Token | Master |
Token ID | 18254 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ijk | +3.206 |
�� | +3.030 |
ld | +2.919 |
ruct | +2.897 |
phe | +2.742 |
Neg logit contributions | |
| -2.903 |
romeda | -2.801 |
Span | -2.775 |
USS | -2.771 |
Tempest | -2.720 |
Token | D |
Token ID | 35 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ijk | +0.178 |
�� | +0.172 |
ruct | +0.162 |
ld | +0.161 |
elephants | +0.153 |
Neg logit contributions | |
| -0.152 |
USS | -0.146 |
romeda | -0.145 |
Span | -0.145 |
Tempest | -0.143 |
Token | al |
Token ID | 282 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ijk | +0.928 |
�� | +0.864 |
ld | +0.821 |
ruct | +0.816 |
phe | +0.763 |
Neg logit contributions | |
| -1.010 |
USS | -0.975 |
Span | -0.975 |
romeda | -0.959 |
Tempest | -0.959 |
Token | K |
Token ID | 42 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ijk | +1.665 |
�� | +1.574 |
ld | +1.500 |
ruct | +1.487 |
phe | +1.411 |
Neg logit contributions | |
| -1.446 |
Span | -1.393 |
USS | -1.388 |
romeda | -1.385 |
Tempest | -1.367 |
Token | | |
Token ID | 930 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ijk | +0.981 |
�� | +0.936 |
ld | +0.891 |
ruct | +0.890 |
phe | +0.845 |
Neg logit contributions | |
| -0.746 |
USS | -0.715 |
romeda | -0.715 |
Span | -0.710 |
Tempest | -0.694 |
Token | Technical |
Token ID | 20671 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ijk | +3.334 |
�� | +3.109 |
ld | +3.046 |
ruct | +3.024 |
elephants | +2.819 |
Neg logit contributions | |
| -3.010 |
USS | -2.957 |
romeda | -2.940 |
Span | -2.871 |
Tempest | -2.791 |
Token | Director |
Token ID | 5890 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ijk | +1.866 |
�� | +1.749 |
ruct | +1.660 |
ld | +1.660 |
elephants | +1.562 |
Neg logit contributions | |
| -1.946 |
romeda | -1.896 |
USS | -1.894 |
Span | -1.865 |
Tempest | -1.834 |
Token | at |
Token ID | 379 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ijk | +0.295 |
�� | +0.281 |
ruct | +0.267 |
ld | +0.265 |
elephants | +0.252 |
Neg logit contributions | |
| -0.254 |
USS | -0.246 |
romeda | -0.243 |
Span | -0.242 |
Tempest | -0.238 |
Token | Wave |
Token ID | 17084 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
| +0.974 |
USS | +0.931 |
Span | +0.928 |
romeda | +0.925 |
Tempest | +0.920 |
Neg logit contributions | |
ijk | -1.050 |
�� | -1.009 |
ruct | -0.947 |
ld | -0.938 |
elephants | -0.895 |
Token | form |
Token ID | 687 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ijk | +0.225 |
�� | +0.216 |
ruct | +0.202 |
ld | +0.201 |
elephants | +0.191 |
Neg logit contributions | |
| -0.222 |
USS | -0.214 |
romeda | -0.213 |
Span | -0.213 |
Tempest | -0.210 |
Token | 00 |
Token ID | 405 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
ijk | +0.330 |
�� | +0.308 |
ld | +0.299 |
ruct | +0.297 |
phe | +0.278 |
Neg logit contributions | |
| -0.317 |
romeda | -0.310 |
USS | -0.304 |
Span | -0.304 |
Tempest | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
| +0.005 |
USS | +0.005 |
romeda | +0.005 |
Span | +0.005 |
Tempest | +0.005 |
Neg logit contributions | |
ijk | -0.006 |
�� | -0.005 |
ruct | -0.005 |
ld | -0.005 |
elephants | -0.005 |
Token | Delivery |
Token ID | 28682 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
| +0.030 |
USS | +0.029 |
romeda | +0.029 |
Span | +0.028 |
Tempest | +0.028 |
Neg logit contributions | |
ijk | -0.039 |
�� | -0.037 |
ld | -0.035 |
ruct | -0.035 |
elephants | -0.034 |
Token | : |
Token ID | 25 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
| +0.858 |
USS | +0.812 |
Span | +0.806 |
romeda | +0.803 |
Tempest | +0.791 |
Neg logit contributions | |
ijk | -1.522 |
�� | -1.472 |
ruct | -1.401 |
ld | -1.394 |
phe | -1.336 |
Token | V |
Token ID | 569 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
| +0.109 |
USS | +0.106 |
romeda | +0.105 |
Span | +0.104 |
Tempest | +0.102 |
Neg logit contributions | |
ijk | -0.120 |
�� | -0.116 |
ruct | -0.110 |
ld | -0.109 |
elephants | -0.104 |
Token | aries |
Token ID | 3166 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ijk | +0.579 |
�� | +0.545 |
ruct | +0.516 |
ld | +0.515 |
phe | +0.480 |
Neg logit contributions | |
| -0.695 |
romeda | -0.678 |
USS | -0.673 |
Span | -0.670 |
Tempest | -0.665 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ijk | +3.203 |
�� | +3.062 |
ruct | +2.921 |
ld | +2.899 |
elephants | +2.814 |
Neg logit contributions | |
romeda | -3.050 |
USS | -2.998 |
| -2.980 |
Tempest | -2.828 |
Span | -2.822 |
Token | email |
Token ID | 3053 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ijk | +1.137 |
�� | +1.094 |
ruct | +1.037 |
ld | +1.036 |
elephants | +0.979 |
Neg logit contributions | |
| -1.009 |
romeda | -0.983 |
USS | -0.973 |
Span | -0.961 |
Tempest | -0.950 |
Token | address |
Token ID | 2209 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
| +1.132 |
USS | +1.088 |
romeda | +1.082 |
Span | +1.081 |
Tempest | +1.070 |
Neg logit contributions | |
ijk | -0.959 |
�� | -0.914 |
ruct | -0.852 |
ld | -0.843 |
elephants | -0.797 |
Token | Thank |
Token ID | 6952 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
| +0.475 |
USS | +0.460 |
romeda | +0.459 |
Span | +0.454 |
Tempest | +0.446 |
Neg logit contributions | |
ijk | -0.545 |
�� | -0.523 |
ld | -0.493 |
ruct | -0.493 |
elephants | -0.468 |
Token | you |
Token ID | 345 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
| +0.086 |
USS | +0.083 |
Span | +0.083 |
romeda | +0.082 |
Tempest | +0.080 |
Neg logit contributions | |
ijk | -0.111 |
�� | -0.107 |
ruct | -0.103 |
ld | -0.102 |
elephants | -0.097 |
Token | lla |
Token ID | 8466 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
| +0.844 |
USS | +0.822 |
Span | +0.819 |
romeda | +0.806 |
Tempest | +0.804 |
Neg logit contributions | |
ijk | -0.577 |
�� | -0.528 |
ld | -0.511 |
ruct | -0.501 |
phe | -0.464 |
Token | , |
Token ID | 11 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
ijk | +0.606 |
�� | +0.579 |
ruct | +0.544 |
ld | +0.541 |
elephants | +0.512 |
Neg logit contributions | |
| -0.615 |
USS | -0.592 |
romeda | -0.588 |
Span | -0.587 |
Tempest | -0.579 |
Token | you |
Token ID | 345 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ijk | +0.480 |
�� | +0.454 |
ruct | +0.431 |
ld | +0.431 |
elephants | +0.408 |
Neg logit contributions | |
| -0.477 |
USS | -0.462 |
Span | -0.456 |
romeda | -0.456 |
Tempest | -0.448 |
Token | should |
Token ID | 815 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ijk | +1.280 |
�� | +1.208 |
ld | +1.155 |
ruct | +1.151 |
elephants | +1.096 |
Neg logit contributions | |
| -1.228 |
USS | -1.191 |
romeda | -1.177 |
Span | -1.177 |
Tempest | -1.158 |
Token | und |
Token ID | 3318 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ijk | +1.258 |
�� | +1.157 |
ld | +1.139 |
ruct | +1.122 |
elephants | +1.073 |
Neg logit contributions | |
| -1.233 |
USS | -1.220 |
romeda | -1.194 |
Span | -1.191 |
Tempest | -1.181 |
Token | ress |
Token ID | 601 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
ijk | +0.932 |
�� | +0.860 |
ruct | +0.838 |
ld | +0.838 |
elephants | +0.778 |
Neg logit contributions | |
| -0.883 |
USS | -0.852 |
Span | -0.846 |
romeda | -0.845 |
Tempest | -0.844 |
Token | too |
Token ID | 1165 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ijk | +3.159 |
�� | +2.956 |
ld | +2.886 |
ruct | +2.859 |
elephants | +2.736 |
Neg logit contributions | |
| -3.121 |
USS | -3.050 |
Span | -3.011 |
romeda | -2.959 |
Tempest | -2.928 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ijk | +0.781 |
�� | +0.745 |
ld | +0.706 |
ruct | +0.704 |
elephants | +0.668 |
Neg logit contributions | |
| -0.702 |
USS | -0.675 |
Span | -0.667 |
romeda | -0.666 |
Tempest | -0.658 |
Token | You |
Token ID | 921 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ijk | +1.006 |
�� | +0.945 |
ld | +0.921 |
ruct | +0.920 |
Chow | +0.867 |
Neg logit contributions | |
| -0.837 |
USS | -0.822 |
romeda | -0.821 |
Span | -0.794 |
Tempest | -0.778 |
Token | might |
Token ID | 1244 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ijk | +0.233 |
�� | +0.223 |
ruct | +0.209 |
ld | +0.207 |
elephants | +0.196 |
Neg logit contributions | |
| -0.244 |
USS | -0.236 |
romeda | -0.234 |
Span | -0.234 |
Tempest | -0.231 |
Token | think |
Token ID | 892 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ijk | +0.506 |
�� | +0.482 |
ruct | +0.453 |
ld | +0.450 |
elephants | +0.425 |
Neg logit contributions | |
| -0.541 |
USS | -0.523 |
romeda | -0.520 |
Span | -0.519 |
Tempest | -0.512 |
Token | has |
Token ID | 468 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
| +0.336 |
USS | +0.324 |
romeda | +0.321 |
Span | +0.321 |
Tempest | +0.317 |
Neg logit contributions | |
ijk | -0.340 |
�� | -0.325 |
ruct | -0.306 |
ld | -0.303 |
phe | -0.287 |
Token | been |
Token ID | 587 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
| +0.523 |
USS | +0.503 |
romeda | +0.501 |
Span | +0.500 |
Tempest | +0.493 |
Neg logit contributions | |
ijk | -0.509 |
�� | -0.488 |
ruct | -0.458 |
ld | -0.452 |
phe | -0.429 |
Token | told |
Token ID | 1297 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ijk | +0.133 |
�� | +0.127 |
ruct | +0.119 |
ld | +0.118 |
elephants | +0.112 |
Neg logit contributions | |
| -0.138 |
USS | -0.133 |
romeda | -0.132 |
Span | -0.132 |
Tempest | -0.130 |
Token | again |
Token ID | 757 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
ijk | +1.440 |
�� | +1.369 |
ld | +1.292 |
ruct | +1.289 |
elephants | +1.224 |
Neg logit contributions | |
| -1.498 |
USS | -1.463 |
romeda | -1.450 |
Span | -1.442 |
Tempest | -1.424 |
Token | and |
Token ID | 290 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ijk | +0.078 |
�� | +0.074 |
ruct | +0.070 |
ld | +0.069 |
elephants | +0.066 |
Neg logit contributions | |
| -0.073 |
USS | -0.070 |
romeda | -0.069 |
Span | -0.069 |
Tempest | -0.068 |
Token | again |
Token ID | 757 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
ijk | +0.547 |
�� | +0.523 |
ruct | +0.491 |
ld | +0.490 |
elephants | +0.464 |
Neg logit contributions | |
| -0.572 |
USS | -0.556 |
romeda | -0.551 |
Span | -0.549 |
Tempest | -0.541 |
Token | over |
Token ID | 625 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ijk | +3.017 |
�� | +2.858 |
ld | +2.708 |
ruct | +2.689 |
elephants | +2.564 |
Neg logit contributions | |
| -3.286 |
USS | -3.258 |
romeda | -3.227 |
Span | -3.191 |
Tempest | -3.162 |
Token | the |
Token ID | 262 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
ijk | +0.284 |
�� | +0.272 |
ruct | +0.256 |
ld | +0.253 |
elephants | +0.241 |
Neg logit contributions | |
| -0.261 |
USS | -0.251 |
Span | -0.249 |
romeda | -0.249 |
Tempest | -0.246 |
Token | course |
Token ID | 1781 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ijk | +0.517 |
�� | +0.490 |
ruct | +0.453 |
ld | +0.449 |
elephants | +0.420 |
Neg logit contributions | |
| -0.736 |
USS | -0.714 |
romeda | -0.709 |
Span | -0.709 |
Tempest | -0.701 |
Token | of |
Token ID | 286 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ijk | +1.626 |
ld | +1.482 |
�� | +1.473 |
ruct | +1.469 |
—- | +1.375 |
Neg logit contributions | |
romeda | -1.574 |
| -1.548 |
USS | -1.544 |
Span | -1.524 |
Tempest | -1.503 |
Token | the |
Token ID | 262 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ijk | +0.273 |
�� | +0.261 |
ruct | +0.245 |
ld | +0.243 |
elephants | +0.230 |
Neg logit contributions | |
| -0.276 |
USS | -0.266 |
romeda | -0.264 |
Span | -0.263 |
Tempest | -0.260 |
Token | be |
Token ID | 307 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ijk | +0.474 |
�� | +0.446 |
ruct | +0.420 |
ld | +0.420 |
elephants | +0.397 |
Neg logit contributions | |
| -0.550 |
USS | -0.537 |
romeda | -0.530 |
Span | -0.528 |
Tempest | -0.522 |
Token | stored |
Token ID | 8574 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ijk | +0.099 |
�� | +0.094 |
ruct | +0.089 |
ld | +0.089 |
elephants | +0.084 |
Neg logit contributions | |
| -0.095 |
USS | -0.092 |
romeda | -0.091 |
Span | -0.091 |
Tempest | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
ijk | +0.244 |
�� | +0.232 |
ruct | +0.221 |
ld | +0.220 |
elephants | +0.208 |
Neg logit contributions | |
| -0.230 |
USS | -0.223 |
romeda | -0.221 |
Span | -0.219 |
Tempest | -0.216 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
| +0.052 |
USS | +0.050 |
romeda | +0.050 |
Span | +0.050 |
Tempest | +0.049 |
Neg logit contributions | |
ijk | -0.049 |
�� | -0.047 |
ruct | -0.044 |
ld | -0.044 |
elephants | -0.041 |
Token | S |
Token ID | 311 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ijk | +0.193 |
�� | +0.183 |
ld | +0.175 |
ruct | +0.175 |
elephants | +0.165 |
Neg logit contributions | |
| -0.168 |
USS | -0.161 |
romeda | -0.161 |
Span | -0.158 |
Tempest | -0.156 |
Token | 3 |
Token ID | 18 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ijk | +0.696 |
�� | +0.658 |
ruct | +0.614 |
ld | +0.610 |
elephants | +0.569 |
Neg logit contributions | |
| -0.943 |
USS | -0.909 |
romeda | -0.908 |
Span | -0.904 |
Tempest | -0.896 |
Token | bucket |
Token ID | 19236 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ijk | +2.698 |
�� | +2.516 |
ruct | +2.356 |
ld | +2.355 |
elephants | +2.179 |
Neg logit contributions | |
| -3.602 |
USS | -3.536 |
romeda | -3.489 |
Span | -3.401 |
Nanto | -3.391 |
Token | . |
Token ID | 13 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ijk | +0.188 |
�� | +0.180 |
ruct | +0.170 |
ld | +0.169 |
elephants | +0.160 |
Neg logit contributions | |
| -0.175 |
USS | -0.169 |
romeda | -0.167 |
Span | -0.167 |
Tempest | -0.164 |
Token | As |
Token ID | 1081 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
| +0.417 |
USS | +0.403 |
romeda | +0.399 |
Span | +0.394 |
Tempest | +0.387 |
Neg logit contributions | |
ijk | -0.539 |
�� | -0.513 |
ruct | -0.492 |
ld | -0.490 |
elephants | -0.465 |
Token | the |
Token ID | 262 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
ijk | +0.021 |
�� | +0.020 |
ld | +0.019 |
ruct | +0.019 |
elephants | +0.018 |
Neg logit contributions | |
| -0.019 |
USS | -0.018 |
romeda | -0.018 |
Span | -0.018 |
Tempest | -0.017 |
Token | input |
Token ID | 5128 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
| +0.057 |
USS | +0.055 |
romeda | +0.054 |
Span | +0.054 |
Tempest | +0.053 |
Neg logit contributions | |
ijk | -0.067 |
�� | -0.064 |
ruct | -0.060 |
ld | -0.060 |
elephants | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ijk | +0.427 |
�� | +0.408 |
ruct | +0.384 |
ld | +0.383 |
elephants | +0.362 |
Neg logit contributions | |
| -0.420 |
USS | -0.407 |
romeda | -0.404 |
Span | -0.402 |
Tempest | -0.397 |
Token | open |
Token ID | 1280 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ijk | +0.171 |
�� | +0.163 |
ruct | +0.155 |
ld | +0.154 |
elephants | +0.147 |
Neg logit contributions | |
| -0.151 |
USS | -0.146 |
romeda | -0.146 |
Span | -0.144 |
Tempest | -0.143 |
Token | meetings |
Token ID | 8292 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
| +0.299 |
USS | +0.290 |
romeda | +0.288 |
Span | +0.287 |
Tempest | +0.284 |
Neg logit contributions | |
ijk | -0.229 |
�� | -0.217 |
ruct | -0.202 |
ld | -0.201 |
elephants | -0.188 |
Token | ; |
Token ID | 26 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
ijk | +0.213 |
�� | +0.204 |
ruct | +0.192 |
ld | +0.190 |
elephants | +0.181 |
Neg logit contributions | |
| -0.206 |
USS | -0.199 |
romeda | -0.198 |
Span | -0.197 |
Tempest | -0.195 |
Token | iii |
Token ID | 46955 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
| +0.005 |
Span | +0.005 |
USS | +0.005 |
romeda | +0.005 |
Tempest | +0.005 |
Neg logit contributions | |
ijk | -0.006 |
�� | -0.006 |
ruct | -0.005 |
ld | -0.005 |
phe | -0.005 |
Token | ) |
Token ID | 8 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
ijk | +0.962 |
�� | +0.906 |
ld | +0.885 |
ruct | +0.881 |
—- | +0.834 |
Neg logit contributions | |
| -0.745 |
romeda | -0.730 |
USS | -0.724 |
Span | -0.714 |
Tempest | -0.703 |
Token | provide |
Token ID | 2148 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
ijk | +2.607 |
�� | +2.441 |
ld | +2.348 |
ruct | +2.331 |
elephants | +2.198 |
Neg logit contributions | |
USS | -3.583 |
romeda | -3.572 |
| -3.555 |
Span | -3.501 |
Tempest | -3.453 |
Token | for |
Token ID | 329 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ijk | +0.565 |
�� | +0.540 |
ruct | +0.506 |
ld | +0.503 |
elephants | +0.476 |
Neg logit contributions | |
| -0.598 |
USS | -0.578 |
romeda | -0.574 |
Span | -0.573 |
Tempest | -0.565 |
Token | public |
Token ID | 1171 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ijk | +0.400 |
�� | +0.382 |
ruct | +0.358 |
ld | +0.355 |
elephants | +0.336 |
Neg logit contributions | |
| -0.446 |
USS | -0.431 |
romeda | -0.429 |
Span | -0.428 |
Tempest | -0.422 |
Token | monitoring |
Token ID | 9904 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
| +0.847 |
USS | +0.817 |
Span | +0.813 |
romeda | +0.808 |
Tempest | +0.802 |
Neg logit contributions | |
ijk | -0.675 |
�� | -0.642 |
ruct | -0.594 |
ld | -0.582 |
phe | -0.554 |
Token | and |
Token ID | 290 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ijk | +0.692 |
�� | +0.662 |
ruct | +0.627 |
ld | +0.623 |
elephants | +0.593 |
Neg logit contributions | |
| -0.612 |
USS | -0.593 |
romeda | -0.590 |
Span | -0.586 |
Tempest | -0.577 |
Token | : |
Token ID | 25 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ijk | +0.175 |
�� | +0.168 |
ruct | +0.158 |
ld | +0.157 |
elephants | +0.149 |
Neg logit contributions | |
| -0.151 |
USS | -0.145 |
Span | -0.144 |
romeda | -0.144 |
Tempest | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
| +0.649 |
Span | +0.616 |
USS | +0.615 |
romeda | +0.612 |
Tempest | +0.603 |
Neg logit contributions | |
ijk | -0.929 |
�� | -0.896 |
ruct | -0.846 |
ld | -0.841 |
phe | -0.808 |
Token |
|
Token ID | 198 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
| +0.550 |
romeda | +0.537 |
USS | +0.535 |
Span | +0.528 |
Tempest | +0.521 |
Neg logit contributions | |
ijk | -0.745 |
�� | -0.699 |
ld | -0.681 |
ruct | -0.681 |
phe | -0.640 |
Token | pub |
Token ID | 12984 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
| +0.472 |
USS | +0.454 |
romeda | +0.451 |
Span | +0.450 |
Tempest | +0.444 |
Neg logit contributions | |
ijk | -0.498 |
�� | -0.478 |
ruct | -0.449 |
ld | -0.445 |
elephants | -0.424 |
Token | struct |
Token ID | 2878 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
| +0.003 |
USS | +0.003 |
romeda | +0.003 |
Span | +0.003 |
Tempest | +0.003 |
Neg logit contributions | |
ijk | -0.003 |
�� | -0.003 |
ruct | -0.003 |
ld | -0.003 |
elephants | -0.003 |
Token | Guard |
Token ID | 4932 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
| +1.210 |
USS | +1.156 |
Span | +1.153 |
romeda | +1.150 |
Tempest | +1.134 |
Neg logit contributions | |
ijk | -1.498 |
�� | -1.442 |
ruct | -1.360 |
ld | -1.351 |
phe | -1.288 |
Token | { |
Token ID | 1391 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ijk | +4.072 |
�� | +3.935 |
ruct | +3.742 |
ld | +3.728 |
elephants | +3.556 |
Neg logit contributions | |
| -2.198 |
romeda | -2.148 |
USS | -2.124 |
Span | -2.056 |
Tempest | -2.048 |
Token | ... |
Token ID | 2644 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ijk | +0.286 |
�� | +0.272 |
ruct | +0.259 |
ld | +0.257 |
elephants | +0.245 |
Neg logit contributions | |
| -0.252 |
USS | -0.248 |
romeda | -0.246 |
Span | -0.240 |
Tempest | -0.238 |
Token | } |
Token ID | 1782 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
| +0.586 |
USS | +0.564 |
romeda | +0.560 |
Span | +0.555 |
Tempest | +0.547 |
Neg logit contributions | |
ijk | -0.871 |
�� | -0.839 |
ruct | -0.798 |
ld | -0.793 |
elephants | -0.759 |
Token | pub |
Token ID | 2240 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
| +1.427 |
Span | +1.359 |
USS | +1.356 |
romeda | +1.341 |
Tempest | +1.332 |
Neg logit contributions | |
ijk | -1.915 |
�� | -1.853 |
ruct | -1.743 |
ld | -1.731 |
phe | -1.668 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
| +0.466 |
USS | +0.448 |
romeda | +0.445 |
Span | +0.445 |
Tempest | +0.438 |
Neg logit contributions | |
ijk | -0.537 |
�� | -0.515 |
ruct | -0.486 |
ld | -0.483 |
elephants | -0.459 |
Token | argument |
Token ID | 49140 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ijk | +0.151 |
�� | +0.139 |
ruct | +0.129 |
ld | +0.129 |
phe | +0.118 |
Neg logit contributions | |
| -0.274 |
USS | -0.267 |
Span | -0.266 |
romeda | -0.266 |
Tempest | -0.263 |
Token | (" |
Token ID | 7203 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
| +0.756 |
USS | +0.725 |
romeda | +0.721 |
Span | +0.720 |
Tempest | +0.709 |
Neg logit contributions | |
ijk | -0.866 |
�� | -0.826 |
ruct | -0.785 |
ld | -0.784 |
elephants | -0.741 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ijk | +0.765 |
�� | +0.705 |
ld | +0.695 |
ruct | +0.682 |
phe | +0.651 |
Neg logit contributions | |
| -0.749 |
Span | -0.732 |
USS | -0.732 |
romeda | -0.729 |
Tempest | -0.722 |
Token | i |
Token ID | 72 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ijk | +0.757 |
ld | +0.680 |
�� | +0.674 |
ruct | +0.662 |
phe | +0.621 |
Neg logit contributions | |
| -0.833 |
Span | -0.815 |
USS | -0.815 |
romeda | -0.811 |
Tempest | -0.805 |
Token | ", |
Token ID | 1600 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ijk | +2.657 |
ld | +2.452 |
ruct | +2.444 |
�� | +2.410 |
phe | +2.310 |
Neg logit contributions | |
| -1.526 |
Tempest | -1.484 |
USS | -1.481 |
romeda | -1.478 |
Span | -1.453 |
Token | " |
Token ID | 366 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
| +0.122 |
USS | +0.121 |
romeda | +0.120 |
Span | +0.117 |
Tempest | +0.116 |
Neg logit contributions | |
ijk | -0.165 |
�� | -0.155 |
ld | -0.152 |
ruct | -0.151 |
elephants | -0.144 |
Token | -- |
Token ID | 438 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
ijk | +3.239 |
ld | +3.030 |
�� | +2.948 |
ruct | +2.890 |
—- | +2.884 |
Neg logit contributions | |
| -2.954 |
Span | -2.927 |
Nanto | -2.877 |
romeda | -2.864 |
Tempest | -2.846 |
Token | images |
Token ID | 17566 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
| +0.503 |
USS | +0.487 |
Span | +0.485 |
romeda | +0.484 |
Tempest | +0.479 |
Neg logit contributions | |
ijk | -0.461 |
�� | -0.436 |
ld | -0.411 |
ruct | -0.411 |
phe | -0.385 |
Token | ", |
Token ID | 1600 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ijk | +2.609 |
ld | +2.395 |
ruct | +2.392 |
�� | +2.349 |
phe | +2.258 |
Neg logit contributions | |
| -1.527 |
Tempest | -1.477 |
romeda | -1.470 |
USS | -1.468 |
Span | -1.442 |
Token | required |
Token ID | 2672 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ijk | +0.117 |
�� | +0.112 |
ruct | +0.105 |
ld | +0.104 |
elephants | +0.098 |
Neg logit contributions | |
| -0.126 |
USS | -0.122 |
romeda | -0.121 |
Span | -0.121 |
Tempest | -0.119 |
Token | = |
Token ID | 28 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
| +0.263 |
romeda | +0.257 |
USS | +0.256 |
Span | +0.255 |
Tempest | +0.253 |
Neg logit contributions | |
ijk | -0.122 |
�� | -0.110 |
ruct | -0.103 |
ld | -0.102 |
phe | -0.092 |
Token | Wall |
Token ID | 5007 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
ijk | +0.015 |
�� | +0.015 |
ruct | +0.014 |
ld | +0.014 |
phe | +0.013 |
Neg logit contributions | |
| -0.013 |
USS | -0.012 |
romeda | -0.012 |
Span | -0.012 |
Tempest | -0.012 |
Token | Paper |
Token ID | 42950 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
ijk | +2.366 |
�� | +2.259 |
ld | +2.142 |
ruct | +2.109 |
phe | +1.992 |
Neg logit contributions | |
| -2.715 |
USS | -2.664 |
romeda | -2.658 |
Tempest | -2.626 |
Span | -2.598 |
Token | - |
Token ID | 532 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ijk | +0.835 |
�� | +0.806 |
ld | +0.763 |
ruct | +0.761 |
phe | +0.715 |
Neg logit contributions | |
| -0.691 |
romeda | -0.666 |
USS | -0.660 |
Tempest | -0.652 |
Span | -0.651 |
Token | Error |
Token ID | 12331 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
| +0.154 |
USS | +0.147 |
romeda | +0.147 |
Span | +0.146 |
Tempest | +0.144 |
Neg logit contributions | |
ijk | -0.187 |
�� | -0.180 |
ruct | -0.171 |
ld | -0.170 |
phe | -0.161 |
Token | Action |
Token ID | 12502 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ijk | +1.214 |
�� | +1.184 |
ld | +1.137 |
ruct | +1.135 |
phe | +1.098 |
Neg logit contributions | |
| -0.454 |
USS | -0.427 |
romeda | -0.425 |
Span | -0.410 |
Tempest | -0.410 |
Token | Stop |
Token ID | 13707 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
ijk | +0.103 |
�� | +0.100 |
ruct | +0.092 |
ld | +0.092 |
phe | +0.086 |
Neg logit contributions | |
| -0.141 |
USS | -0.138 |
romeda | -0.137 |
Span | -0.135 |
Tempest | -0.135 |
Token | ). |
Token ID | 737 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ijk | +3.603 |
�� | +3.553 |
ruct | +3.340 |
ld | +3.336 |
phe | +3.169 |
Neg logit contributions | |
| -2.485 |
romeda | -2.423 |
Tempest | -2.408 |
USS | -2.382 |
Span | -2.356 |
Token | Wall |
Token ID | 22401 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ijk | +1.382 |
�� | +1.331 |
ld | +1.263 |
ruct | +1.257 |
phe | +1.180 |
Neg logit contributions | |
| -1.254 |
romeda | -1.207 |
USS | -1.202 |
Span | -1.193 |
Tempest | -1.186 |
Token | Paper |
Token ID | 42950 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ijk | +1.705 |
�� | +1.624 |
ld | +1.532 |
ruct | +1.529 |
phe | +1.430 |
Neg logit contributions | |
| -1.869 |
USS | -1.826 |
romeda | -1.818 |
Tempest | -1.800 |
Span | -1.788 |
Token | if |
Token ID | 611 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ijk | +0.793 |
�� | +0.765 |
ld | +0.725 |
ruct | +0.724 |
phe | +0.677 |
Neg logit contributions | |
| -0.676 |
romeda | -0.653 |
USS | -0.648 |
Tempest | -0.642 |
Span | -0.636 |
Token | ( |
Token ID | 357 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
| +0.453 |
USS | +0.437 |
Span | +0.435 |
romeda | +0.434 |
Tempest | +0.428 |
Neg logit contributions | |
ijk | -0.421 |
�� | -0.402 |
ruct | -0.376 |
ld | -0.373 |
elephants | -0.353 |
Token | Metroid |
Token ID | 45430 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ijk | +0.478 |
�� | +0.458 |
ruct | +0.431 |
ld | +0.428 |
elephants | +0.406 |
Neg logit contributions | |
| -0.452 |
USS | -0.435 |
romeda | -0.433 |
Span | -0.431 |
Tempest | -0.425 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
| +0.363 |
USS | +0.350 |
romeda | +0.347 |
Span | +0.347 |
Tempest | +0.342 |
Neg logit contributions | |
ijk | -0.372 |
�� | -0.356 |
ruct | -0.335 |
ld | -0.333 |
elephants | -0.315 |
Token | I |
Token ID | 314 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ijk | +0.108 |
�� | +0.103 |
ruct | +0.098 |
ld | +0.097 |
elephants | +0.093 |
Neg logit contributions | |
| -0.096 |
USS | -0.093 |
romeda | -0.092 |
Span | -0.092 |
Tempest | -0.090 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ijk | +0.215 |
�� | +0.202 |
ld | +0.194 |
ruct | +0.193 |
elephants | +0.182 |
Neg logit contributions | |
| -0.221 |
USS | -0.215 |
Span | -0.213 |
romeda | -0.213 |
Tempest | -0.210 |
Token | , |
Token ID | 11 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ijk | +1.106 |
�� | +1.052 |
ruct | +0.996 |
ld | +0.993 |
elephants | +0.942 |
Neg logit contributions | |
| -1.079 |
USS | -1.050 |
romeda | -1.031 |
Span | -1.028 |
Tempest | -1.012 |
Token | ' |
Token ID | 705 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
ijk | +0.185 |
�� | +0.177 |
ruct | +0.168 |
ld | +0.167 |
elephants | +0.160 |
Neg logit contributions | |
| -0.153 |
USS | -0.148 |
romeda | -0.147 |
Span | -0.146 |
Tempest | -0.144 |
Token | I |
Token ID | 40 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ijk | +3.232 |
�� | +3.023 |
ld | +2.955 |
ruct | +2.905 |
phe | +2.738 |
Neg logit contributions | |
| -2.931 |
romeda | -2.849 |
Span | -2.826 |
USS | -2.798 |
Tempest | -2.776 |
Token | want |
Token ID | 765 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ijk | +0.621 |
�� | +0.583 |
ld | +0.562 |
ruct | +0.559 |
elephants | +0.527 |
Neg logit contributions | |
| -0.627 |
USS | -0.609 |
romeda | -0.603 |
Span | -0.603 |
Tempest | -0.594 |
Token | to |
Token ID | 284 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
ijk | +0.841 |
�� | +0.803 |
ruct | +0.754 |
ld | +0.749 |
elephants | +0.708 |
Neg logit contributions | |
| -0.895 |
USS | -0.864 |
romeda | -0.858 |
Span | -0.856 |
Tempest | -0.845 |
Token | make |
Token ID | 787 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ijk | +0.549 |
�� | +0.510 |
ld | +0.494 |
ruct | +0.492 |
elephants | +0.466 |
Neg logit contributions | |
| -0.605 |
USS | -0.593 |
romeda | -0.582 |
Span | -0.580 |
Tempest | -0.572 |
Token | something |
Token ID | 1223 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ijk | +0.783 |
�� | +0.742 |
ruct | +0.699 |
ld | +0.696 |
elephants | +0.658 |
Neg logit contributions | |
| -0.891 |
USS | -0.864 |
romeda | -0.855 |
Span | -0.853 |
Tempest | -0.840 |
Token | things |
Token ID | 1243 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
| +0.744 |
USS | +0.709 |
romeda | +0.703 |
Span | +0.701 |
Tempest | +0.688 |
Neg logit contributions | |
ijk | -1.255 |
�� | -1.211 |
ruct | -1.154 |
ld | -1.148 |
elephants | -1.102 |
Token | are |
Token ID | 389 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ijk | +0.183 |
�� | +0.170 |
ruct | +0.164 |
ld | +0.164 |
elephants | +0.154 |
Neg logit contributions | |
| -0.192 |
USS | -0.188 |
romeda | -0.186 |
Span | -0.186 |
Tempest | -0.184 |
Token | moving |
Token ID | 3867 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
| +0.167 |
USS | +0.163 |
Span | +0.162 |
romeda | +0.161 |
Tempest | +0.160 |
Neg logit contributions | |
ijk | -0.155 |
�� | -0.143 |
ld | -0.138 |
ruct | -0.138 |
elephants | -0.130 |
Token | along |
Token ID | 1863 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
| +1.165 |
USS | +1.129 |
romeda | +1.122 |
Span | +1.120 |
Tempest | +1.107 |
Neg logit contributions | |
ijk | -0.974 |
�� | -0.923 |
ruct | -0.865 |
ld | -0.860 |
elephants | -0.810 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
ijk | +0.186 |
�� | +0.171 |
ruct | +0.169 |
ld | +0.168 |
phe | +0.157 |
Neg logit contributions | |
| -0.178 |
romeda | -0.175 |
USS | -0.173 |
Span | -0.172 |
Tempest | -0.170 |
Token | @ |
Token ID | 2488 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
| +0.499 |
USS | +0.479 |
romeda | +0.476 |
Span | +0.474 |
Tempest | +0.467 |
Neg logit contributions | |
ijk | -0.628 |
�� | -0.604 |
ruct | -0.571 |
ld | -0.568 |
elephants | -0.541 |
Token | Master |
Token ID | 18254 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ijk | +3.206 |
�� | +3.030 |
ld | +2.919 |
ruct | +2.897 |
phe | +2.742 |
Neg logit contributions | |
| -2.903 |
romeda | -2.801 |
Span | -2.775 |
USS | -2.771 |
Tempest | -2.720 |
Token | D |
Token ID | 35 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ijk | +0.178 |
�� | +0.172 |
ruct | +0.162 |
ld | +0.161 |
elephants | +0.153 |
Neg logit contributions | |
| -0.152 |
USS | -0.146 |
romeda | -0.145 |
Span | -0.145 |
Tempest | -0.143 |
Token | al |
Token ID | 282 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ijk | +0.928 |
�� | +0.864 |
ld | +0.821 |
ruct | +0.816 |
phe | +0.763 |
Neg logit contributions | |
| -1.010 |
USS | -0.975 |
Span | -0.975 |
romeda | -0.959 |
Tempest | -0.959 |
Token | K |
Token ID | 42 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ijk | +1.665 |
�� | +1.574 |
ld | +1.500 |
ruct | +1.487 |
phe | +1.411 |
Neg logit contributions | |
| -1.446 |
Span | -1.393 |
USS | -1.388 |
romeda | -1.385 |
Tempest | -1.367 |
Token | | |
Token ID | 930 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ijk | +0.981 |
�� | +0.936 |
ld | +0.891 |
ruct | +0.890 |
phe | +0.845 |
Neg logit contributions | |
| -0.746 |
USS | -0.715 |
romeda | -0.715 |
Span | -0.710 |
Tempest | -0.694 |
Token | there |
Token ID | 612 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
ijk | +0.815 |
�� | +0.775 |
ruct | +0.733 |
ld | +0.732 |
elephants | +0.693 |
Neg logit contributions | |
| -0.828 |
USS | -0.805 |
romeda | -0.798 |
Span | -0.792 |
Tempest | -0.782 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ijk | +0.290 |
�� | +0.278 |
ruct | +0.260 |
ld | +0.258 |
elephants | +0.244 |
Neg logit contributions | |
| -0.288 |
USS | -0.276 |
Span | -0.275 |
romeda | -0.275 |
Tempest | -0.271 |
Token | thinking |
Token ID | 3612 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ijk | +1.202 |
�� | +1.150 |
ruct | +1.087 |
ld | +1.084 |
elephants | +1.031 |
Neg logit contributions | |
| -1.060 |
USS | -1.024 |
romeda | -1.013 |
Span | -1.008 |
Tempest | -0.996 |
Token | like |
Token ID | 588 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ijk | +1.859 |
�� | +1.766 |
ld | +1.663 |
ruct | +1.663 |
elephants | +1.572 |
Neg logit contributions | |
| -1.984 |
USS | -1.937 |
romeda | -1.923 |
Span | -1.900 |
Tempest | -1.879 |
Token | , |
Token ID | 11 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ijk | +1.231 |
�� | +1.178 |
ruct | +1.106 |
ld | +1.096 |
elephants | +1.037 |
Neg logit contributions | |
| -1.242 |
USS | -1.195 |
Span | -1.188 |
romeda | -1.188 |
Tempest | -1.171 |
Token | " |
Token ID | 366 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ijk | +1.382 |
�� | +1.325 |
ruct | +1.260 |
ld | +1.258 |
elephants | +1.202 |
Neg logit contributions | |
| -1.026 |
USS | -0.990 |
romeda | -0.981 |
Span | -0.973 |
Tempest | -0.958 |
Token | Okay |
Token ID | 16454 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ijk | +3.279 |
�� | +3.083 |
ld | +3.002 |
ruct | +2.954 |
phe | +2.798 |
Neg logit contributions | |
| -2.808 |
romeda | -2.744 |
Span | -2.688 |
USS | -2.675 |
Tempest | -2.657 |
Token | , |
Token ID | 11 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ijk | +0.892 |
�� | +0.857 |
ruct | +0.801 |
ld | +0.791 |
phe | +0.752 |
Neg logit contributions | |
| -0.910 |
USS | -0.875 |
Span | -0.871 |
romeda | -0.870 |
Tempest | -0.858 |
Token | focus |
Token ID | 2962 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ijk | +0.282 |
�� | +0.270 |
ruct | +0.256 |
ld | +0.254 |
elephants | +0.242 |
Neg logit contributions | |
| -0.247 |
USS | -0.238 |
romeda | -0.236 |
Span | -0.236 |
Tempest | -0.232 |
Token | Ol |
Token ID | 6544 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ijk | +2.186 |
�� | +2.071 |
ld | +1.983 |
ruct | +1.982 |
elephants | +1.885 |
Neg logit contributions | |
| -1.892 |
USS | -1.838 |
romeda | -1.834 |
Span | -1.804 |
Tempest | -1.779 |
Token | af |
Token ID | 1878 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ijk | +0.315 |
�� | +0.298 |
ruct | +0.284 |
ld | +0.283 |
phe | +0.267 |
Neg logit contributions | |
| -0.287 |
USS | -0.277 |
romeda | -0.275 |
Span | -0.274 |
Tempest | -0.270 |
Token | � |
Token ID | 247 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ijk | +0.181 |
�� | +0.172 |
ruct | +0.160 |
ld | +0.160 |
elephants | +0.149 |
Neg logit contributions | |
| -0.231 |
USS | -0.224 |
romeda | -0.223 |
Span | -0.223 |
Tempest | -0.220 |
Token | s |
Token ID | 82 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
| +0.224 |
USS | +0.218 |
romeda | +0.216 |
Span | +0.215 |
Tempest | +0.211 |
Neg logit contributions | |
ijk | -0.281 |
�� | -0.264 |
ld | -0.255 |
ruct | -0.255 |
elephants | -0.241 |
Token | Silver |
Token ID | 7698 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
| +0.084 |
USS | +0.081 |
romeda | +0.080 |
Span | +0.080 |
Tempest | +0.079 |
Neg logit contributions | |
ijk | -0.088 |
�� | -0.085 |
ruct | -0.080 |
ld | -0.079 |
elephants | -0.075 |
Token | Phantom |
Token ID | 14407 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
| +0.692 |
Span | +0.658 |
USS | +0.658 |
Tempest | +0.654 |
romeda | +0.644 |
Neg logit contributions | |
ijk | -0.800 |
�� | -0.766 |
ld | -0.718 |
ruct | -0.717 |
elephants | -0.674 |
Token | falls |
Token ID | 8953 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
| +0.652 |
USS | +0.625 |
Span | +0.622 |
romeda | +0.618 |
Tempest | +0.614 |
Neg logit contributions | |
ijk | -0.667 |
�� | -0.640 |
ruct | -0.600 |
ld | -0.596 |
elephants | -0.564 |
Token | into |
Token ID | 656 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
| +0.114 |
USS | +0.110 |
romeda | +0.110 |
Span | +0.109 |
Tempest | +0.108 |
Neg logit contributions | |
ijk | -0.103 |
�� | -0.098 |
ruct | -0.092 |
ld | -0.091 |
elephants | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ijk | +2.834 |
�� | +2.694 |
ruct | +2.569 |
ld | +2.527 |
elephants | +2.408 |
Neg logit contributions | |
| -3.145 |
USS | -3.132 |
romeda | -3.117 |
Span | -3.042 |
Tempest | -3.004 |
Token | latter |
Token ID | 6846 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
ijk | +0.355 |
�� | +0.338 |
ruct | +0.319 |
ld | +0.316 |
elephants | +0.301 |
Neg logit contributions | |
| -0.352 |
USS | -0.341 |
romeda | -0.338 |
Span | -0.336 |
Tempest | -0.332 |
Token | category |
Token ID | 6536 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ijk | +0.751 |
�� | +0.720 |
ruct | +0.675 |
ld | +0.670 |
elephants | +0.635 |
Neg logit contributions | |
| -0.746 |
USS | -0.719 |
romeda | -0.714 |
Span | -0.713 |
Tempest | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ijk | +0.518 |
�� | +0.497 |
ruct | +0.468 |
ld | +0.464 |
elephants | +0.440 |
Neg logit contributions | |
| -0.477 |
USS | -0.457 |
romeda | -0.454 |
Span | -0.454 |
Tempest | -0.447 |
Token | I |
Token ID | 314 |
Feature activation | +2.55e-04 |
Pos logit contributions | |
ijk | +0.934 |
�� | +0.892 |
ruct | +0.851 |
ld | +0.846 |
phe | +0.802 |
Neg logit contributions | |
| -0.809 |
romeda | -0.790 |
USS | -0.789 |
Span | -0.770 |
Tempest | -0.758 |
Token | a |
Token ID | 64 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ijk | +1.376 |
ld | +1.228 |
ruct | +1.212 |
�� | +1.193 |
phe | +1.114 |
Neg logit contributions | |
| -2.003 |
USS | -1.972 |
Span | -1.960 |
romeda | -1.950 |
Tempest | -1.932 |
Token | ech |
Token ID | 3055 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ijk | +0.169 |
�� | +0.153 |
ruct | +0.146 |
ld | +0.145 |
phe | +0.132 |
Neg logit contributions | |
| -0.305 |
USS | -0.298 |
Span | -0.297 |
romeda | -0.295 |
Tempest | -0.293 |
Token | says |
Token ID | 1139 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
| +0.213 |
USS | +0.207 |
romeda | +0.204 |
Span | +0.203 |
Tempest | +0.201 |
Neg logit contributions | |
ijk | -0.221 |
�� | -0.210 |
ld | -0.199 |
ruct | -0.198 |
elephants | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
ijk | +0.061 |
�� | +0.058 |
ruct | +0.055 |
ld | +0.055 |
elephants | +0.052 |
Neg logit contributions | |
| -0.060 |
USS | -0.058 |
romeda | -0.058 |
Span | -0.058 |
Tempest | -0.057 |
Token | ' |
Token ID | 705 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
ijk | +0.760 |
�� | +0.731 |
ruct | +0.692 |
ld | +0.688 |
elephants | +0.657 |
Neg logit contributions | |
| -0.568 |
USS | -0.544 |
romeda | -0.540 |
Span | -0.538 |
Tempest | -0.530 |
Token | Thank |
Token ID | 6952 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
ijk | +0.226 |
�� | +0.216 |
ld | +0.206 |
ruct | +0.206 |
elephants | +0.195 |
Neg logit contributions | |
| -0.186 |
USS | -0.179 |
romeda | -0.179 |
Span | -0.177 |
Tempest | -0.174 |
Token | you |
Token ID | 345 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
| +2.809 |
Tempest | +2.607 |
USS | +2.593 |
Span | +2.568 |
romeda | +2.546 |
Neg logit contributions | |
ijk | -5.019 |
�� | -4.861 |
ruct | -4.519 |
ld | -4.412 |
phe | -4.305 |
Token | for |
Token ID | 329 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ijk | +0.136 |
�� | +0.129 |
ld | +0.122 |
ruct | +0.122 |
elephants | +0.115 |
Neg logit contributions | |
| -0.135 |
USS | -0.131 |
romeda | -0.130 |
Span | -0.129 |
Tempest | -0.127 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
| +0.077 |
USS | +0.075 |
romeda | +0.074 |
Span | +0.074 |
Tempest | +0.072 |
Neg logit contributions | |
ijk | -0.082 |
�� | -0.078 |
ruct | -0.074 |
ld | -0.074 |
elephants | -0.070 |
Token | information |
Token ID | 1321 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ijk | +0.115 |
�� | +0.110 |
ruct | +0.104 |
ld | +0.103 |
elephants | +0.098 |
Neg logit contributions | |
| -0.105 |
USS | -0.101 |
romeda | -0.101 |
Span | -0.100 |
Tempest | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
| +0.539 |
USS | +0.521 |
romeda | +0.518 |
Span | +0.516 |
Tempest | +0.507 |
Neg logit contributions | |
ijk | -0.593 |
�� | -0.567 |
ruct | -0.536 |
ld | -0.535 |
elephants | -0.507 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
| +0.537 |
USS | +0.512 |
romeda | +0.511 |
Span | +0.510 |
Tempest | +0.501 |
Neg logit contributions | |
ijk | -0.574 |
�� | -0.552 |
ruct | -0.518 |
ld | -0.511 |
elephants | -0.487 |
Token |
|
Token ID | 198 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ijk | +0.036 |
�� | +0.034 |
ruct | +0.033 |
ld | +0.033 |
phe | +0.031 |
Neg logit contributions | |
| -0.029 |
romeda | -0.028 |
USS | -0.028 |
Span | -0.028 |
Tempest | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ijk | +0.216 |
�� | +0.208 |
ruct | +0.197 |
ld | +0.196 |
elephants | +0.188 |
Neg logit contributions | |
| -0.152 |
USS | -0.146 |
romeda | -0.145 |
Span | -0.144 |
Tempest | -0.142 |
Token | 27 |
Token ID | 1983 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ijk | +0.180 |
�� | +0.172 |
ruct | +0.162 |
ld | +0.162 |
phe | +0.153 |
Neg logit contributions | |
| -0.169 |
romeda | -0.162 |
Span | -0.162 |
USS | -0.161 |
Tempest | -0.159 |
Token | " |
Token ID | 366 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ijk | +0.554 |
�� | +0.534 |
ld | +0.504 |
ruct | +0.502 |
elephants | +0.478 |
Neg logit contributions | |
| -0.491 |
USS | -0.477 |
romeda | -0.473 |
Span | -0.471 |
Tempest | -0.463 |
Token | 4 |
Token ID | 604 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
| +0.675 |
USS | +0.650 |
romeda | +0.646 |
Span | +0.644 |
Tempest | +0.635 |
Neg logit contributions | |
ijk | -0.722 |
�� | -0.692 |
ruct | -0.652 |
ld | -0.647 |
elephants | -0.615 |
Token | ms |
Token ID | 907 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
| +3.535 |
USS | +3.369 |
Span | +3.343 |
romeda | +3.334 |
Tempest | +3.308 |
Neg logit contributions | |
ijk | -4.209 |
�� | -4.019 |
ruct | -3.806 |
ld | -3.766 |
elephants | -3.591 |
Token | G |
Token ID | 402 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
| +0.464 |
USS | +0.451 |
romeda | +0.446 |
Span | +0.442 |
Tempest | +0.437 |
Neg logit contributions | |
ijk | -0.543 |
�� | -0.521 |
ruct | -0.490 |
ld | -0.490 |
elephants | -0.466 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
| +0.419 |
USS | +0.404 |
romeda | +0.402 |
Span | +0.401 |
Tempest | +0.397 |
Neg logit contributions | |
ijk | -0.389 |
�� | -0.371 |
ruct | -0.347 |
ld | -0.346 |
elephants | -0.325 |
Token | G |
Token ID | 38 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
| +0.126 |
USS | +0.121 |
romeda | +0.120 |
Span | +0.119 |
Tempest | +0.118 |
Neg logit contributions | |
ijk | -0.141 |
�� | -0.135 |
ld | -0.127 |
ruct | -0.127 |
elephants | -0.121 |
Token | AU |
Token ID | 27548 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
| +0.461 |
USS | +0.445 |
romeda | +0.440 |
Span | +0.440 |
Tempest | +0.433 |
Neg logit contributions | |
ijk | -0.533 |
�� | -0.512 |
ruct | -0.481 |
ld | -0.480 |
elephants | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
| +0.402 |
romeda | +0.396 |
USS | +0.392 |
Span | +0.388 |
Tempest | +0.382 |
Neg logit contributions | |
ijk | -0.534 |
�� | -0.497 |
ld | -0.489 |
ruct | -0.488 |
phe | -0.459 |
Token | Enc |
Token ID | 27195 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
| +0.353 |
USS | +0.340 |
romeda | +0.338 |
Span | +0.337 |
Tempest | +0.332 |
Neg logit contributions | |
ijk | -0.381 |
�� | -0.365 |
ruct | -0.344 |
ld | -0.342 |
elephants | -0.324 |
Token | ryption |
Token ID | 13168 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ijk | +0.084 |
�� | +0.079 |
ruct | +0.075 |
ld | +0.074 |
elephants | +0.068 |
Neg logit contributions | |
| -0.114 |
USS | -0.111 |
romeda | -0.110 |
Span | -0.110 |
Tempest | -0.109 |
Token | details |
Token ID | 3307 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ijk | +0.432 |
�� | +0.410 |
ruct | +0.387 |
ld | +0.384 |
elephants | +0.366 |
Neg logit contributions | |
| -0.440 |
USS | -0.428 |
romeda | -0.426 |
Span | -0.422 |
Tempest | -0.415 |
Token | [ |
Token ID | 685 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ijk | +0.368 |
�� | +0.351 |
ruct | +0.329 |
ld | +0.328 |
elephants | +0.310 |
Neg logit contributions | |
| -0.395 |
USS | -0.383 |
romeda | -0.381 |
Span | -0.379 |
Tempest | -0.374 |
Token | edit |
Token ID | 4370 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
| +0.234 |
USS | +0.227 |
romeda | +0.227 |
Span | +0.226 |
Tempest | +0.223 |
Neg logit contributions | |
ijk | -0.202 |
�� | -0.191 |
ruct | -0.181 |
ld | -0.180 |
elephants | -0.168 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
| +3.132 |
USS | +2.879 |
Span | +2.863 |
Tempest | +2.806 |
romeda | +2.792 |
Neg logit contributions | |
ijk | -4.657 |
�� | -4.642 |
ruct | -4.234 |
ld | -4.171 |
elephants | -4.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ijk | +2.253 |
ld | +2.066 |
ruct | +2.047 |
�� | +2.005 |
—- | +1.939 |
Neg logit contributions | |
romeda | -1.917 |
USS | -1.883 |
| -1.882 |
Span | -1.846 |
Tempest | -1.828 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
| +0.078 |
romeda | +0.077 |
USS | +0.076 |
Span | +0.075 |
Tempest | +0.074 |
Neg logit contributions | |
ijk | -0.103 |
�� | -0.095 |
ld | -0.094 |
ruct | -0.094 |
phe | -0.088 |
Token | WE |
Token ID | 8845 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
| +0.002 |
USS | +0.002 |
romeda | +0.002 |
Span | +0.002 |
Tempest | +0.002 |
Neg logit contributions | |
ijk | -0.002 |
�� | -0.002 |
ruct | -0.002 |
ld | -0.002 |
elephants | -0.002 |
Token | P |
Token ID | 47 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
| +0.034 |
romeda | +0.033 |
USS | +0.033 |
Span | +0.032 |
Tempest | +0.032 |
Neg logit contributions | |
ijk | -0.031 |
�� | -0.029 |
ld | -0.028 |
ruct | -0.027 |
phe | -0.026 |
Token | 2015 |
Token ID | 4626 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
| +0.177 |
USS | +0.172 |
Span | +0.169 |
romeda | +0.169 |
Tempest | +0.167 |
Neg logit contributions | |
ijk | -0.161 |
�� | -0.155 |
ruct | -0.145 |
ld | -0.143 |
elephants | -0.136 |
Token | – |
Token ID | 1906 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ijk | +0.015 |
�� | +0.014 |
ruct | +0.013 |
ld | +0.013 |
elephants | +0.012 |
Neg logit contributions | |
| -0.026 |
USS | -0.025 |
Span | -0.025 |
romeda | -0.025 |
Tempest | -0.025 |
Token | 16 |
Token ID | 1433 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
| +0.527 |
USS | +0.505 |
romeda | +0.491 |
Span | +0.489 |
Tempest | +0.482 |
Neg logit contributions | |
ijk | -0.689 |
�� | -0.668 |
ruct | -0.627 |
ld | -0.615 |
elephants | -0.599 |
Token | season |
Token ID | 1622 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
| +0.437 |
USS | +0.420 |
Span | +0.419 |
romeda | +0.414 |
Tempest | +0.412 |
Neg logit contributions | |
ijk | -0.459 |
�� | -0.444 |
ruct | -0.414 |
ld | -0.409 |
phe | -0.391 |
Token | [ |
Token ID | 685 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ijk | +0.433 |
�� | +0.415 |
ruct | +0.389 |
ld | +0.385 |
elephants | +0.366 |
Neg logit contributions | |
| -0.436 |
USS | -0.420 |
Span | -0.417 |
romeda | -0.416 |
Tempest | -0.411 |
Token | edit |
Token ID | 4370 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
| +1.301 |
USS | +1.256 |
romeda | +1.247 |
Span | +1.246 |
Tempest | +1.230 |
Neg logit contributions | |
ijk | -1.165 |
�� | -1.116 |
ruct | -1.040 |
ld | -1.031 |
elephants | -0.976 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
| +3.080 |
USS | +2.829 |
Span | +2.817 |
Tempest | +2.743 |
romeda | +2.722 |
Neg logit contributions | |
�� | -4.700 |
ijk | -4.682 |
ruct | -4.256 |
ld | -4.187 |
elephants | -4.130 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ijk | +0.258 |
�� | +0.242 |
ruct | +0.235 |
ld | +0.234 |
phe | +0.221 |
Neg logit contributions | |
| -0.191 |
romeda | -0.186 |
USS | -0.185 |
Span | -0.182 |
Tempest | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
| +1.120 |
USS | +1.073 |
romeda | +1.067 |
Span | +1.062 |
Tempest | +1.044 |
Neg logit contributions | |
ijk | -1.599 |
�� | -1.535 |
ruct | -1.462 |
ld | -1.455 |
elephants | -1.388 |
Token | On |
Token ID | 2202 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
| +1.079 |
USS | +1.058 |
Span | +1.025 |
romeda | +1.021 |
Tempest | +1.013 |
Neg logit contributions | |
ijk | -1.022 |
�� | -0.992 |
ruct | -0.923 |
ld | -0.904 |
elephants | -0.879 |
Token | June |
Token ID | 2795 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
| +0.208 |
USS | +0.201 |
romeda | +0.200 |
Span | +0.199 |
Tempest | +0.196 |
Neg logit contributions | |
ijk | -0.226 |
�� | -0.216 |
ruct | -0.204 |
ld | -0.203 |
elephants | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
| +0.160 |
romeda | +0.159 |
USS | +0.157 |
Span | +0.155 |
Tempest | +0.153 |
Neg logit contributions | |
ijk | -0.208 |
�� | -0.191 |
ld | -0.191 |
ruct | -0.189 |
—- | -0.179 |
Token | The |
Token ID | 464 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
| +0.291 |
romeda | +0.279 |
USS | +0.279 |
Span | +0.277 |
Tempest | +0.273 |
Neg logit contributions | |
ijk | -0.316 |
�� | -0.302 |
ruct | -0.285 |
ld | -0.284 |
phe | -0.269 |
Token | Two |
Token ID | 4930 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ijk | +0.162 |
�� | +0.154 |
ruct | +0.144 |
ld | +0.142 |
elephants | +0.134 |
Neg logit contributions | |
| -0.208 |
USS | -0.201 |
romeda | -0.200 |
Span | -0.200 |
Tempest | -0.198 |
Token | Towers |
Token ID | 29031 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
| +0.598 |
USS | +0.582 |
romeda | +0.580 |
Span | +0.575 |
Tempest | +0.568 |
Neg logit contributions | |
ijk | -0.392 |
�� | -0.369 |
ld | -0.342 |
ruct | -0.342 |
elephants | -0.318 |
Token | [ |
Token ID | 685 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
| +0.032 |
USS | +0.031 |
romeda | +0.031 |
Span | +0.030 |
Tempest | +0.030 |
Neg logit contributions | |
ijk | -0.039 |
�� | -0.038 |
ruct | -0.036 |
ld | -0.036 |
elephants | -0.034 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
| +0.720 |
USS | +0.696 |
romeda | +0.693 |
Span | +0.690 |
Tempest | +0.681 |
Neg logit contributions | |
ijk | -0.630 |
�� | -0.599 |
ruct | -0.561 |
ld | -0.558 |
elephants | -0.524 |
Token | ] |
Token ID | 2361 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
| +3.076 |
Span | +2.842 |
USS | +2.837 |
Tempest | +2.786 |
romeda | +2.760 |
Neg logit contributions | |
ijk | -4.597 |
�� | -4.503 |
ruct | -4.178 |
ld | -4.097 |
phe | -4.033 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ijk | +0.495 |
�� | +0.458 |
ld | +0.453 |
ruct | +0.452 |
—- | +0.425 |
Neg logit contributions | |
| -0.383 |
romeda | -0.380 |
USS | -0.373 |
Span | -0.368 |
Tempest | -0.363 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
| +0.684 |
romeda | +0.666 |
USS | +0.664 |
Span | +0.655 |
Tempest | +0.646 |
Neg logit contributions | |
ijk | -0.934 |
�� | -0.879 |
ld | -0.854 |
ruct | -0.853 |
phe | -0.805 |
Token | Or |
Token ID | 5574 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
| +1.005 |
USS | +0.973 |
Span | +0.956 |
romeda | +0.952 |
Tempest | +0.942 |
Neg logit contributions | |
ijk | -1.134 |
�� | -1.093 |
ruct | -1.026 |
ld | -1.012 |
elephants | -0.972 |
Token | cs |
Token ID | 6359 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ijk | +0.162 |
�� | +0.155 |
ld | +0.149 |
ruct | +0.148 |
phe | +0.142 |
Neg logit contributions | |
| -0.107 |
USS | -0.103 |
Span | -0.102 |
romeda | -0.101 |
Tempest | -0.099 |
Token | em |
Token ID | 368 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
| +0.281 |
USS | +0.272 |
romeda | +0.271 |
Span | +0.271 |
Tempest | +0.268 |
Neg logit contributions | |
ijk | -0.210 |
�� | -0.197 |
ruct | -0.185 |
ld | -0.184 |
phe | -0.171 |
Token | orative |
Token ID | 36478 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
| +0.326 |
USS | +0.315 |
Span | +0.314 |
romeda | +0.313 |
Tempest | +0.310 |
Neg logit contributions | |
ijk | -0.217 |
�� | -0.208 |
ruct | -0.188 |
ld | -0.188 |
elephants | -0.176 |
Token | bank |
Token ID | 3331 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
| +0.790 |
USS | +0.758 |
Span | +0.754 |
romeda | +0.752 |
Tempest | +0.742 |
Neg logit contributions | |
ijk | -0.844 |
�� | -0.811 |
ruct | -0.763 |
ld | -0.757 |
phe | -0.717 |
Token | notes |
Token ID | 17815 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
| +1.539 |
USS | +1.485 |
romeda | +1.480 |
Span | +1.476 |
Tempest | +1.461 |
Neg logit contributions | |
ijk | -0.953 |
�� | -0.909 |
ruct | -0.834 |
ld | -0.818 |
elephants | -0.759 |
Token | [ |
Token ID | 685 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ijk | +0.834 |
�� | +0.791 |
ruct | +0.744 |
ld | +0.742 |
elephants | +0.703 |
Neg logit contributions | |
| -0.864 |
USS | -0.842 |
romeda | -0.837 |
Span | -0.830 |
Tempest | -0.821 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
| +0.908 |
USS | +0.877 |
romeda | +0.871 |
Span | +0.870 |
Tempest | +0.859 |
Neg logit contributions | |
ijk | -0.807 |
�� | -0.771 |
ruct | -0.720 |
ld | -0.715 |
elephants | -0.675 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
| +3.015 |
USS | +2.780 |
Span | +2.762 |
Tempest | +2.702 |
romeda | +2.679 |
Neg logit contributions | |
ijk | -4.580 |
�� | -4.578 |
ruct | -4.167 |
ld | -4.102 |
elephants | -4.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ijk | +1.450 |
�� | +1.351 |
ruct | +1.322 |
ld | +1.318 |
phe | +1.241 |
Neg logit contributions | |
| -1.103 |
romeda | -1.090 |
USS | -1.074 |
Span | -1.060 |
Tempest | -1.050 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
| +0.127 |
romeda | +0.125 |
USS | +0.124 |
Span | +0.122 |
Tempest | +0.120 |
Neg logit contributions | |
ijk | -0.169 |
�� | -0.157 |
ld | -0.154 |
ruct | -0.154 |
phe | -0.145 |
Token | $ |
Token ID | 3 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
| +0.100 |
USS | +0.096 |
Span | +0.095 |
romeda | +0.095 |
Tempest | +0.094 |
Neg logit contributions | |
ijk | -0.101 |
�� | -0.097 |
ruct | -0.091 |
ld | -0.090 |
elephants | -0.086 |
Token | 25 |
Token ID | 1495 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
ijk | +0.008 |
�� | +0.008 |
ruct | +0.007 |
ld | +0.007 |
elephants | +0.007 |
Neg logit contributions | |
| -0.010 |
USS | -0.009 |
romeda | -0.009 |
Span | -0.009 |
Tempest | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
| +0.135 |
USS | +0.131 |
romeda | +0.129 |
Span | +0.129 |
Tempest | +0.127 |
Neg logit contributions | |
ijk | -0.132 |
�� | -0.126 |
ruct | -0.118 |
ld | -0.118 |
elephants | -0.112 |
Token | terms |
Token ID | 2846 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
ijk | +0.302 |
�� | +0.289 |
ruct | +0.272 |
ld | +0.270 |
elephants | +0.256 |
Neg logit contributions | |
| -0.309 |
USS | -0.299 |
romeda | -0.298 |
Span | -0.296 |
Tempest | -0.292 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
| +0.672 |
USS | +0.652 |
romeda | +0.649 |
Span | +0.643 |
Tempest | +0.634 |
Neg logit contributions | |
ijk | -0.785 |
�� | -0.743 |
ruct | -0.711 |
ld | -0.709 |
elephants | -0.673 |
Token | micro |
Token ID | 4580 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
| +0.103 |
USS | +0.100 |
romeda | +0.099 |
Span | +0.098 |
Tempest | +0.097 |
Neg logit contributions | |
ijk | -0.103 |
�� | -0.098 |
ruct | -0.093 |
ld | -0.092 |
elephants | -0.088 |
Token | - |
Token ID | 12 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ijk | +0.311 |
�� | +0.300 |
ruct | +0.282 |
ld | +0.282 |
elephants | +0.267 |
Neg logit contributions | |
| -0.284 |
USS | -0.275 |
romeda | -0.273 |
Span | -0.272 |
Tempest | -0.268 |
Token | and |
Token ID | 290 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
| +0.521 |
USS | +0.502 |
romeda | +0.498 |
Span | +0.497 |
Tempest | +0.490 |
Neg logit contributions | |
ijk | -0.535 |
�� | -0.512 |
ruct | -0.480 |
ld | -0.476 |
elephants | -0.453 |
Token | macro |
Token ID | 15021 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
| +3.857 |
romeda | +3.655 |
Span | +3.642 |
USS | +3.625 |
Tempest | +3.574 |
Neg logit contributions | |
ijk | -3.618 |
�� | -3.468 |
ld | -3.204 |
ruct | -3.189 |
phe | -3.052 |
Token | - |
Token ID | 12 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
| +0.468 |
USS | +0.451 |
romeda | +0.448 |
Span | +0.447 |
Tempest | +0.441 |
Neg logit contributions | |
ijk | -0.505 |
�� | -0.485 |
ruct | -0.457 |
ld | -0.455 |
elephants | -0.432 |
Token | level |
Token ID | 5715 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ijk | +0.374 |
�� | +0.358 |
ruct | +0.339 |
ld | +0.337 |
phe | +0.319 |
Neg logit contributions | |
| -0.351 |
USS | -0.338 |
romeda | -0.337 |
Span | -0.337 |
Tempest | -0.332 |
Token | retrieval |
Token ID | 45069 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
ijk | +0.110 |
�� | +0.105 |
ruct | +0.099 |
ld | +0.099 |
elephants | +0.094 |
Neg logit contributions | |
| -0.110 |
USS | -0.106 |
romeda | -0.105 |
Span | -0.105 |
Tempest | -0.103 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ijk | +0.459 |
�� | +0.437 |
ruct | +0.413 |
ld | +0.410 |
elephants | +0.389 |
Neg logit contributions | |
| -0.478 |
USS | -0.463 |
romeda | -0.461 |
Span | -0.457 |
Tempest | -0.453 |
Token | source |
Token ID | 2723 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ijk | +0.421 |
�� | +0.401 |
ruct | +0.380 |
ld | +0.380 |
elephants | +0.360 |
Neg logit contributions | |
| -0.402 |
USS | -0.388 |
romeda | -0.387 |
Span | -0.382 |
Tempest | -0.378 |
Token | : |
Token ID | 25 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
| +0.156 |
USS | +0.151 |
romeda | +0.150 |
Span | +0.149 |
Tempest | +0.147 |
Neg logit contributions | |
ijk | -0.164 |
�� | -0.156 |
ruct | -0.148 |
ld | -0.148 |
elephants | -0.140 |
Token |
|
Token ID | 198 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
| +0.135 |
USS | +0.129 |
romeda | +0.128 |
Span | +0.128 |
Tempest | +0.126 |
Neg logit contributions | |
ijk | -0.179 |
�� | -0.172 |
ruct | -0.163 |
ld | -0.162 |
elephants | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ijk | +0.393 |
�� | +0.361 |
ld | +0.361 |
ruct | +0.358 |
—- | +0.338 |
Neg logit contributions | |
| -0.304 |
romeda | -0.302 |
USS | -0.298 |
Span | -0.295 |
Tempest | -0.290 |
Token | " |
Token ID | 1 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ijk | +0.113 |
�� | +0.108 |
ruct | +0.102 |
ld | +0.102 |
phe | +0.096 |
Neg logit contributions | |
| -0.107 |
romeda | -0.103 |
USS | -0.103 |
Span | -0.103 |
Tempest | -0.101 |
Token | In |
Token ID | 554 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
ijk | +0.400 |
�� | +0.383 |
ruct | +0.361 |
ld | +0.361 |
phe | +0.340 |
Neg logit contributions | |
| -0.371 |
romeda | -0.356 |
USS | -0.355 |
Span | -0.353 |
Tempest | -0.349 |
Token | the |
Token ID | 262 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
| +3.653 |
USS | +3.533 |
Span | +3.514 |
romeda | +3.452 |
Tempest | +3.427 |
Neg logit contributions | |
ijk | -3.723 |
�� | -3.591 |
ruct | -3.350 |
ld | -3.280 |
elephants | -3.130 |
Token | event |
Token ID | 1785 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
| +0.212 |
USS | +0.205 |
romeda | +0.204 |
Span | +0.202 |
Tempest | +0.200 |
Neg logit contributions | |
ijk | -0.217 |
�� | -0.206 |
ruct | -0.194 |
ld | -0.194 |
elephants | -0.184 |
Token | that |
Token ID | 326 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
| +0.115 |
USS | +0.111 |
romeda | +0.110 |
Span | +0.110 |
Tempest | +0.108 |
Neg logit contributions | |
ijk | -0.135 |
�� | -0.129 |
ruct | -0.122 |
ld | -0.121 |
elephants | -0.115 |
Token | this |
Token ID | 428 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
| +0.255 |
USS | +0.246 |
romeda | +0.244 |
Span | +0.243 |
Tempest | +0.240 |
Neg logit contributions | |
ijk | -0.253 |
�� | -0.242 |
ruct | -0.227 |
ld | -0.226 |
elephants | -0.215 |
Token | does |
Token ID | 857 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
| +0.049 |
USS | +0.047 |
romeda | +0.047 |
Span | +0.046 |
Tempest | +0.046 |
Neg logit contributions | |
ijk | -0.048 |
�� | -0.046 |
ruct | -0.044 |
ld | -0.043 |
elephants | -0.041 |
Token | fulfill |
Token ID | 14658 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
| +0.777 |
USS | +0.764 |
romeda | +0.759 |
Span | +0.751 |
Tempest | +0.743 |
Neg logit contributions | |
ijk | -0.692 |
�� | -0.648 |
ld | -0.619 |
ruct | -0.619 |
elephants | -0.585 |
Token | that |
Token ID | 326 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
| +0.827 |
USS | +0.792 |
Span | +0.787 |
romeda | +0.786 |
Tempest | +0.777 |
Neg logit contributions | |
ijk | -0.879 |
�� | -0.843 |
ruct | -0.792 |
ld | -0.785 |
phe | -0.746 |
Token | in |
Token ID | 287 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
| +0.134 |
USS | +0.129 |
Span | +0.129 |
romeda | +0.128 |
Tempest | +0.127 |
Neg logit contributions | |
ijk | -0.114 |
�� | -0.109 |
ruct | -0.101 |
ld | -0.100 |
phe | -0.095 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ijk | +1.089 |
�� | +1.025 |
ruct | +0.992 |
ld | +0.988 |
elephants | +0.935 |
Neg logit contributions | |
| -1.164 |
romeda | -1.140 |
USS | -1.138 |
Span | -1.126 |
Tempest | -1.111 |
Token | - |
Token ID | 12 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ijk | +1.135 |
�� | +1.078 |
ld | +1.023 |
ruct | +1.023 |
elephants | +0.965 |
Neg logit contributions | |
| -1.154 |
romeda | -1.124 |
USS | -1.118 |
Span | -1.115 |
Tempest | -1.094 |
Token | and |
Token ID | 290 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ijk | +0.077 |
�� | +0.073 |
ruct | +0.069 |
ld | +0.069 |
phe | +0.065 |
Neg logit contributions | |
| -0.083 |
romeda | -0.081 |
USS | -0.080 |
Span | -0.080 |
Tempest | -0.079 |
Token | gas |
Token ID | 3623 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
| +3.098 |
USS | +2.882 |
romeda | +2.857 |
Span | +2.857 |
Tempest | +2.826 |
Neg logit contributions | |
ijk | -4.348 |
�� | -4.211 |
ruct | -3.923 |
ld | -3.899 |
phe | -3.733 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ijk | +0.953 |
�� | +0.906 |
ruct | +0.864 |
ld | +0.862 |
elephants | +0.818 |
Neg logit contributions | |
| -0.915 |
romeda | -0.894 |
USS | -0.890 |
Span | -0.886 |
Tempest | -0.869 |
Token | related |
Token ID | 5363 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ijk | +0.199 |
�� | +0.188 |
ruct | +0.181 |
ld | +0.180 |
phe | +0.170 |
Neg logit contributions | |
| -0.201 |
romeda | -0.196 |
USS | -0.194 |
Span | -0.194 |
Tempest | -0.191 |
Token | matters |
Token ID | 6067 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ijk | +1.456 |
�� | +1.354 |
ld | +1.318 |
ruct | +1.311 |
elephants | +1.257 |
Neg logit contributions | |
| -1.444 |
romeda | -1.430 |
USS | -1.423 |
Span | -1.401 |
Tempest | -1.372 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ijk | +0.360 |
�� | +0.345 |
ruct | +0.325 |
ld | +0.323 |
elephants | +0.307 |
Neg logit contributions | |
| -0.320 |
USS | -0.308 |
romeda | -0.306 |
Span | -0.305 |
Tempest | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
| +1.192 |
USS | +1.143 |
romeda | +1.139 |
Span | +1.138 |
Tempest | +1.122 |
Neg logit contributions | |
ijk | -1.200 |
�� | -1.150 |
ruct | -1.076 |
ld | -1.068 |
phe | -1.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
| +0.643 |
USS | +0.622 |
romeda | +0.618 |
Span | +0.611 |
Tempest | +0.603 |
Neg logit contributions | |
ijk | -0.813 |
�� | -0.781 |
ruct | -0.742 |
ld | -0.738 |
elephants | -0.701 |
Token |
|
Token ID | 198 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
| +0.445 |
romeda | +0.434 |
USS | +0.432 |
Span | +0.427 |
Tempest | +0.421 |
Neg logit contributions | |
ijk | -0.601 |
�� | -0.564 |
ld | -0.549 |
ruct | -0.548 |
phe | -0.517 |
Token | 27 |
Token ID | 1983 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
| +0.497 |
romeda | +0.479 |
Span | +0.477 |
USS | +0.477 |
Tempest | +0.471 |
Neg logit contributions | |
ijk | -0.503 |
�� | -0.481 |
ruct | -0.453 |
ld | -0.452 |
phe | -0.425 |
Token | " |
Token ID | 366 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
| +0.562 |
USS | +0.534 |
romeda | +0.530 |
Span | +0.530 |
Tempest | +0.520 |
Neg logit contributions | |
ijk | -0.856 |
�� | -0.824 |
ruct | -0.784 |
ld | -0.778 |
elephants | -0.746 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
| +0.726 |
USS | +0.700 |
romeda | +0.695 |
Span | +0.693 |
Tempest | +0.682 |
Neg logit contributions | |
ijk | -0.837 |
�� | -0.805 |
ruct | -0.759 |
ld | -0.755 |
elephants | -0.717 |
Token | ms |
Token ID | 907 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
| +2.790 |
USS | +2.627 |
romeda | +2.604 |
Span | +2.599 |
Tempest | +2.560 |
Neg logit contributions | |
ijk | -4.508 |
�� | -4.345 |
ruct | -4.155 |
ld | -4.046 |
elephants | -3.937 |
Token | G |
Token ID | 402 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
| +0.370 |
USS | +0.352 |
romeda | +0.349 |
Span | +0.349 |
Tempest | +0.343 |
Neg logit contributions | |
ijk | -0.583 |
�� | -0.561 |
ruct | -0.533 |
ld | -0.530 |
elephants | -0.508 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
| +0.307 |
USS | +0.297 |
romeda | +0.295 |
Span | +0.295 |
Tempest | +0.290 |
Neg logit contributions | |
ijk | -0.279 |
�� | -0.266 |
ruct | -0.250 |
ld | -0.246 |
elephants | -0.235 |
Token | G |
Token ID | 38 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
| +0.588 |
romeda | +0.569 |
Span | +0.564 |
USS | +0.564 |
Tempest | +0.555 |
Neg logit contributions | |
ijk | -0.600 |
�� | -0.568 |
ld | -0.543 |
ruct | -0.542 |
phe | -0.508 |
Token | AU |
Token ID | 27548 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
| +0.077 |
USS | +0.072 |
romeda | +0.071 |
Span | +0.070 |
Tempest | +0.068 |
Neg logit contributions | |
ijk | -0.254 |
�� | -0.247 |
ruct | -0.237 |
ld | -0.236 |
elephants | -0.229 |
Token | M |
Token ID | 44 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ijk | +0.522 |
�� | +0.496 |
ruct | +0.468 |
ld | +0.467 |
phe | +0.440 |
Neg logit contributions | |
| -0.515 |
romeda | -0.497 |
USS | -0.494 |
Span | -0.494 |
Tempest | -0.487 |
Token | oom |
Token ID | 4207 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
ijk | +0.165 |
�� | +0.159 |
ruct | +0.144 |
ld | +0.143 |
elephants | +0.134 |
Neg logit contributions | |
| -0.258 |
USS | -0.251 |
romeda | -0.249 |
Span | -0.248 |
Tempest | -0.246 |
Token | in |
Token ID | 259 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ijk | +0.721 |
�� | +0.695 |
ruct | +0.652 |
ld | +0.647 |
elephants | +0.617 |
Neg logit contributions | |
| -0.635 |
USS | -0.609 |
Span | -0.605 |
romeda | -0.605 |
Tempest | -0.596 |
Token | World |
Token ID | 2159 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ijk | +0.024 |
�� | +0.022 |
ruct | +0.021 |
ld | +0.021 |
elephants | +0.020 |
Neg logit contributions | |
| -0.023 |
USS | -0.022 |
romeda | -0.022 |
Span | -0.022 |
Tempest | -0.022 |
Token | [ |
Token ID | 685 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
| +0.395 |
USS | +0.380 |
Span | +0.378 |
romeda | +0.377 |
Tempest | +0.372 |
Neg logit contributions | |
ijk | -0.391 |
�� | -0.376 |
ruct | -0.352 |
ld | -0.349 |
elephants | -0.330 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
| +0.491 |
USS | +0.474 |
romeda | +0.474 |
Span | +0.472 |
Tempest | +0.466 |
Neg logit contributions | |
ijk | -0.421 |
�� | -0.397 |
ruct | -0.375 |
ld | -0.373 |
elephants | -0.349 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
| +2.930 |
USS | +2.701 |
Span | +2.682 |
Tempest | +2.621 |
romeda | +2.606 |
Neg logit contributions | |
�� | -4.445 |
ijk | -4.438 |
ruct | -4.040 |
ld | -3.971 |
elephants | -3.911 |
Token |
|
Token ID | 198 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ijk | +1.633 |
ld | +1.498 |
ruct | +1.484 |
�� | +1.472 |
—- | +1.404 |
Neg logit contributions | |
romeda | -1.334 |
| -1.319 |
USS | -1.304 |
Span | -1.279 |
Tempest | -1.272 |
Token |
|
Token ID | 198 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ijk | +0.233 |
ld | +0.214 |
�� | +0.213 |
ruct | +0.212 |
—- | +0.200 |
Neg logit contributions | |
| -0.179 |
romeda | -0.179 |
USS | -0.176 |
Span | -0.174 |
Tempest | -0.172 |
Token | M |
Token ID | 44 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ijk | +0.033 |
�� | +0.032 |
ruct | +0.030 |
ld | +0.030 |
elephants | +0.028 |
Neg logit contributions | |
| -0.033 |
USS | -0.032 |
romeda | -0.032 |
Span | -0.032 |
Tempest | -0.031 |
Token | oom |
Token ID | 4207 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
ijk | +0.082 |
�� | +0.079 |
ruct | +0.071 |
ld | +0.071 |
elephants | +0.067 |
Neg logit contributions | |
| -0.126 |
USS | -0.123 |
romeda | -0.122 |
Span | -0.122 |
Tempest | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
| +0.494 |
USS | +0.473 |
romeda | +0.472 |
Span | +0.471 |
Tempest | +0.466 |
Neg logit contributions | |
ijk | -0.460 |
�� | -0.440 |
ruct | -0.410 |
ld | -0.406 |
phe | -0.384 |
Token | marketing |
Token ID | 7124 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ijk | +0.575 |
�� | +0.548 |
ruct | +0.517 |
ld | +0.516 |
elephants | +0.488 |
Neg logit contributions | |
| -0.614 |
USS | -0.596 |
romeda | -0.590 |
Span | -0.589 |
Tempest | -0.579 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ijk | +0.420 |
�� | +0.402 |
ruct | +0.377 |
ld | +0.374 |
elephants | +0.355 |
Neg logit contributions | |
| -0.418 |
USS | -0.402 |
romeda | -0.400 |
Span | -0.399 |
Tempest | -0.394 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ijk | +0.305 |
�� | +0.293 |
ruct | +0.276 |
ld | +0.274 |
elephants | +0.260 |
Neg logit contributions | |
| -0.283 |
USS | -0.272 |
romeda | -0.270 |
Span | -0.270 |
Tempest | -0.266 |
Token | more |
Token ID | 517 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ijk | +0.107 |
�� | +0.103 |
ld | +0.097 |
ruct | +0.097 |
elephants | +0.093 |
Neg logit contributions | |
| -0.086 |
USS | -0.083 |
romeda | -0.082 |
Span | -0.082 |
Tempest | -0.080 |
Token | confident |
Token ID | 6563 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
| +0.455 |
USS | +0.439 |
romeda | +0.436 |
Span | +0.434 |
Tempest | +0.427 |
Neg logit contributions | |
ijk | -0.500 |
�� | -0.479 |
ruct | -0.452 |
ld | -0.450 |
elephants | -0.428 |
Token | we |
Token ID | 356 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
| +2.975 |
Span | +2.783 |
USS | +2.774 |
romeda | +2.767 |
Tempest | +2.748 |
Neg logit contributions | |
ijk | -4.273 |
�� | -4.140 |
ruct | -3.837 |
ld | -3.797 |
phe | -3.681 |
Token | are |
Token ID | 389 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ijk | +0.304 |
�� | +0.287 |
ld | +0.274 |
ruct | +0.273 |
elephants | +0.259 |
Neg logit contributions | |
| -0.305 |
USS | -0.298 |
romeda | -0.295 |
Span | -0.294 |
Tempest | -0.290 |
Token | in |
Token ID | 287 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ijk | +0.489 |
�� | +0.468 |
ruct | +0.442 |
ld | +0.441 |
elephants | +0.418 |
Neg logit contributions | |
| -0.454 |
USS | -0.440 |
romeda | -0.436 |
Span | -0.434 |
Tempest | -0.427 |
Token | the |
Token ID | 262 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
ijk | +1.041 |
�� | +1.002 |
ld | +0.952 |
ruct | +0.950 |
elephants | +0.902 |
Neg logit contributions | |
| -1.096 |
USS | -1.070 |
romeda | -1.063 |
Span | -1.047 |
Tempest | -1.030 |
Token | product |
Token ID | 1720 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ijk | +0.692 |
�� | +0.657 |
ruct | +0.628 |
ld | +0.625 |
elephants | +0.598 |
Neg logit contributions | |
| -0.722 |
USS | -0.703 |
romeda | -0.701 |
Span | -0.690 |
Tempest | -0.678 |
Token | Theme |
Token ID | 47863 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
| +0.033 |
romeda | +0.032 |
USS | +0.032 |
Span | +0.032 |
Tempest | +0.031 |
Neg logit contributions | |
ijk | -0.035 |
�� | -0.033 |
ruct | -0.032 |
ld | -0.031 |
phe | -0.030 |
Token | parks |
Token ID | 14860 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ijk | +0.955 |
�� | +0.902 |
ruct | +0.846 |
ld | +0.843 |
elephants | +0.802 |
Neg logit contributions | |
| -1.219 |
romeda | -1.194 |
USS | -1.190 |
Span | -1.170 |
Tempest | -1.158 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ijk | +0.556 |
�� | +0.530 |
ruct | +0.498 |
ld | +0.496 |
elephants | +0.470 |
Neg logit contributions | |
| -0.572 |
USS | -0.553 |
romeda | -0.550 |
Span | -0.548 |
Tempest | -0.540 |
Token | displays |
Token ID | 11298 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
| +0.245 |
USS | +0.238 |
romeda | +0.237 |
Span | +0.236 |
Tempest | +0.233 |
Neg logit contributions | |
ijk | -0.200 |
�� | -0.189 |
ruct | -0.177 |
ld | -0.176 |
elephants | -0.167 |
Token | [ |
Token ID | 685 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ijk | +0.763 |
�� | +0.726 |
ruct | +0.683 |
ld | +0.681 |
elephants | +0.645 |
Neg logit contributions | |
| -0.800 |
USS | -0.776 |
romeda | -0.773 |
Span | -0.768 |
Tempest | -0.759 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
ijk | +0.169 |
�� | +0.158 |
ruct | +0.151 |
ld | +0.150 |
elephants | +0.140 |
Neg logit contributions | |
| -0.201 |
romeda | -0.195 |
USS | -0.195 |
Span | -0.194 |
Tempest | -0.191 |
Token | ] |
Token ID | 2361 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
| +2.748 |
USS | +2.552 |
Span | +2.527 |
Tempest | +2.472 |
romeda | +2.466 |
Neg logit contributions | |
ijk | -4.122 |
�� | -4.118 |
ruct | -3.750 |
ld | -3.695 |
elephants | -3.629 |
Token |
|
Token ID | 198 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
ijk | +2.627 |
ld | +2.412 |
ruct | +2.381 |
�� | +2.315 |
—- | +2.260 |
Neg logit contributions | |
romeda | -2.277 |
| -2.224 |
USS | -2.219 |
Span | -2.179 |
Tempest | -2.159 |
Token |
|
Token ID | 198 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
ijk | +0.746 |
ld | +0.687 |
ruct | +0.680 |
�� | +0.678 |
—- | +0.643 |
Neg logit contributions | |
romeda | -0.589 |
| -0.586 |
USS | -0.578 |
Span | -0.570 |
Tempest | -0.564 |
Token | M |
Token ID | 44 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ijk | +0.522 |
�� | +0.496 |
ruct | +0.468 |
ld | +0.467 |
phe | +0.440 |
Neg logit contributions | |
| -0.515 |
romeda | -0.497 |
USS | -0.494 |
Span | -0.494 |
Tempest | -0.487 |
Token | oom |
Token ID | 4207 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
ijk | +0.165 |
�� | +0.159 |
ruct | +0.144 |
ld | +0.143 |
elephants | +0.134 |
Neg logit contributions | |
| -0.258 |
USS | -0.251 |
romeda | -0.249 |
Span | -0.248 |
Tempest | -0.246 |
Token | [ |
Token ID | 58 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ijk | +0.996 |
�� | +0.942 |
ruct | +0.870 |
ld | +0.864 |
elephants | +0.800 |
Neg logit contributions | |
| -1.512 |
USS | -1.468 |
romeda | -1.463 |
Span | -1.455 |
Tempest | -1.444 |
Token | Table |
Token ID | 8655 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ijk | +0.596 |
�� | +0.569 |
ld | +0.539 |
ruct | +0.535 |
phe | +0.508 |
Neg logit contributions | |
| -0.501 |
romeda | -0.485 |
USS | -0.483 |
Tempest | -0.476 |
Span | -0.474 |
Token | [ |
Token ID | 58 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
| +2.677 |
USS | +2.580 |
Span | +2.576 |
romeda | +2.506 |
Tempest | +2.503 |
Neg logit contributions | |
ijk | -2.108 |
�� | -1.973 |
ruct | -1.844 |
ld | -1.800 |
elephants | -1.762 |
Token | Table |
Token ID | 10962 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
ijk | +0.122 |
�� | +0.117 |
ld | +0.111 |
ruct | +0.111 |
elephants | +0.106 |
Neg logit contributions | |
| -0.076 |
USS | -0.073 |
romeda | -0.073 |
Span | -0.071 |
Tempest | -0.071 |
Token | [ |
Token ID | 58 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
| +0.748 |
USS | +0.724 |
Span | +0.721 |
romeda | +0.713 |
Tempest | +0.706 |
Neg logit contributions | |
ijk | -0.531 |
�� | -0.502 |
ruct | -0.465 |
ld | -0.456 |
elephants | -0.436 |
Token | graph |
Token ID | 4823 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
| +0.750 |
USS | +0.722 |
Span | +0.717 |
romeda | +0.715 |
Tempest | +0.704 |
Neg logit contributions | |
ijk | -0.806 |
�� | -0.774 |
ruct | -0.729 |
ld | -0.722 |
elephants | -0.688 |
Token | List |
Token ID | 8053 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
| +3.351 |
Span | +3.227 |
USS | +3.225 |
romeda | +3.140 |
Tempest | +3.113 |
Neg logit contributions | |
ijk | -3.436 |
�� | -3.294 |
ruct | -3.089 |
ld | -3.025 |
elephants | -2.952 |
Token | [[ |
Token ID | 30109 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
| +1.857 |
USS | +1.780 |
Span | +1.775 |
romeda | +1.751 |
Tempest | +1.731 |
Neg logit contributions | |
ijk | -1.917 |
�� | -1.844 |
ruct | -1.723 |
ld | -1.702 |
elephants | -1.641 |
Token | # |
Token ID | 2 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
| +0.802 |
USS | +0.772 |
Span | +0.768 |
romeda | +0.764 |
Tempest | +0.752 |
Neg logit contributions | |
ijk | -0.808 |
�� | -0.776 |
ruct | -0.730 |
ld | -0.720 |
elephants | -0.688 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
| +0.383 |
USS | +0.368 |
Span | +0.365 |
romeda | +0.364 |
Tempest | +0.358 |
Neg logit contributions | |
ijk | -0.439 |
�� | -0.421 |
ruct | -0.397 |
ld | -0.394 |
elephants | -0.375 |
Token | 1 |
Token ID | 352 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
| +1.202 |
USS | +1.154 |
Span | +1.148 |
romeda | +1.142 |
Tempest | +1.125 |
Neg logit contributions | |
ijk | -1.320 |
�� | -1.268 |
ruct | -1.195 |
ld | -1.183 |
elephants | -1.129 |
Token | Jon |
Token ID | 18219 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
| +0.453 |
USS | +0.437 |
romeda | +0.433 |
Span | +0.432 |
Tempest | +0.426 |
Neg logit contributions | |
ijk | -0.476 |
�� | -0.456 |
ruct | -0.428 |
ld | -0.425 |
elephants | -0.404 |
Token | Chest |
Token ID | 25544 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ijk | +0.355 |
�� | +0.340 |
ruct | +0.320 |
ld | +0.318 |
elephants | +0.301 |
Neg logit contributions | |
| -0.352 |
USS | -0.339 |
romeda | -0.337 |
Span | -0.336 |
Tempest | -0.331 |
Token | o |
Token ID | 78 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
| +1.385 |
USS | +1.349 |
romeda | +1.339 |
Span | +1.337 |
Tempest | +1.324 |
Neg logit contributions | |
ijk | -0.709 |
�� | -0.675 |
ruct | -0.610 |
ld | -0.594 |
elephants | -0.552 |
Token | can |
Token ID | 460 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
ijk | +1.169 |
�� | +1.113 |
ld | +1.045 |
ruct | +1.044 |
elephants | +0.981 |
Neg logit contributions | |
| -1.215 |
USS | -1.180 |
romeda | -1.171 |
Span | -1.166 |
Tempest | -1.152 |
Token | be |
Token ID | 307 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
| +0.457 |
Span | +0.437 |
romeda | +0.436 |
USS | +0.433 |
Tempest | +0.432 |
Neg logit contributions | |
ijk | -0.445 |
�� | -0.428 |
ruct | -0.398 |
ld | -0.389 |
phe | -0.374 |
Token | reached |
Token ID | 4251 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
| +0.785 |
USS | +0.763 |
Span | +0.762 |
romeda | +0.760 |
Tempest | +0.753 |
Neg logit contributions | |
ijk | -0.360 |
�� | -0.337 |
ruct | -0.298 |
ld | -0.292 |
elephants | -0.270 |
Token | at |
Token ID | 379 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
| +2.875 |
Span | +2.754 |
USS | +2.705 |
romeda | +2.704 |
Tempest | +2.693 |
Neg logit contributions | |
ijk | -3.843 |
�� | -3.795 |
ruct | -3.518 |
ld | -3.461 |
elephants | -3.338 |
Token | j |
Token ID | 474 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
| +0.716 |
USS | +0.677 |
romeda | +0.671 |
Span | +0.669 |
Tempest | +0.657 |
Neg logit contributions | |
ijk | -1.314 |
�� | -1.272 |
ruct | -1.212 |
ld | -1.204 |
elephants | -1.156 |
Token | on |
Token ID | 261 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
| +0.140 |
USS | +0.137 |
Span | +0.137 |
romeda | +0.136 |
Tempest | +0.135 |
Neg logit contributions | |
ijk | -0.163 |
�� | -0.155 |
ld | -0.151 |
ruct | -0.150 |
phe | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ijk | +0.279 |
�� | +0.267 |
ld | +0.254 |
ruct | +0.253 |
phe | +0.240 |
Neg logit contributions | |
| -0.256 |
USS | -0.248 |
Span | -0.246 |
romeda | -0.244 |
Tempest | -0.242 |
Token | chest |
Token ID | 46713 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
| +0.851 |
USS | +0.832 |
Span | +0.828 |
romeda | +0.820 |
Tempest | +0.819 |
Neg logit contributions | |
ijk | -0.771 |
�� | -0.730 |
ld | -0.694 |
ruct | -0.694 |
phe | -0.655 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ijk | +1.267 |
�� | +1.202 |
ruct | +1.158 |
ld | +1.152 |
phe | +1.091 |
Neg logit contributions | |
| -1.002 |
USS | -0.973 |
romeda | -0.970 |
Span | -0.951 |
Tempest | -0.930 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ijk | +1.519 |
ld | +1.405 |
ruct | +1.388 |
�� | +1.357 |
—- | +1.321 |
Neg logit contributions | |
romeda | -1.282 |
USS | -1.251 |
| -1.250 |
Span | -1.230 |
Tempest | -1.216 |
Token | Part |
Token ID | 7841 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ijk | +1.500 |
�� | +1.421 |
ld | +1.354 |
ruct | +1.350 |
—- | +1.278 |
Neg logit contributions | |
| -1.486 |
romeda | -1.442 |
Span | -1.428 |
USS | -1.414 |
Tempest | -1.403 |
Token | 6 |
Token ID | 718 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ijk | +1.250 |
�� | +1.192 |
ruct | +1.130 |
ld | +1.121 |
elephants | +1.057 |
Neg logit contributions | |
| -1.192 |
USS | -1.160 |
romeda | -1.145 |
Span | -1.136 |
Tempest | -1.121 |
Token | [ |
Token ID | 685 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
| +0.424 |
USS | +0.407 |
Span | +0.406 |
romeda | +0.402 |
Tempest | +0.402 |
Neg logit contributions | |
ijk | -0.459 |
�� | -0.440 |
ruct | -0.411 |
ld | -0.408 |
phe | -0.390 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ijk | +0.891 |
�� | +0.848 |
ruct | +0.795 |
ld | +0.789 |
elephants | +0.741 |
Neg logit contributions | |
| -1.033 |
romeda | -0.997 |
USS | -0.995 |
Span | -0.991 |
Tempest | -0.975 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
| +2.697 |
USS | +2.502 |
Span | +2.488 |
Tempest | +2.460 |
romeda | +2.415 |
Neg logit contributions | |
ijk | -4.105 |
�� | -3.983 |
ruct | -3.742 |
ld | -3.653 |
phe | -3.621 |
Token |
|
Token ID | 198 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ijk | +1.148 |
ld | +1.054 |
�� | +1.054 |
ruct | +1.051 |
—- | +0.993 |
Neg logit contributions | |
romeda | -0.907 |
| -0.904 |
USS | -0.886 |
Span | -0.875 |
Tempest | -0.859 |
Token |
|
Token ID | 198 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
| +0.591 |
romeda | +0.577 |
USS | +0.574 |
Span | +0.567 |
Tempest | +0.558 |
Neg logit contributions | |
ijk | -0.805 |
�� | -0.757 |
ld | -0.735 |
ruct | -0.735 |
phe | -0.693 |
Token | It |
Token ID | 1026 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
| +0.632 |
USS | +0.612 |
romeda | +0.602 |
Span | +0.602 |
Tempest | +0.595 |
Neg logit contributions | |
ijk | -0.668 |
�� | -0.642 |
ruct | -0.602 |
ld | -0.596 |
elephants | -0.570 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
| +0.077 |
USS | +0.075 |
romeda | +0.074 |
Span | +0.074 |
Tempest | +0.073 |
Neg logit contributions | |
ijk | -0.071 |
�� | -0.068 |
ruct | -0.064 |
ld | -0.063 |
elephants | -0.060 |
Token | read |
Token ID | 1100 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ijk | +0.631 |
�� | +0.601 |
ld | +0.565 |
ruct | +0.564 |
elephants | +0.534 |
Neg logit contributions | |
| -0.652 |
USS | -0.633 |
romeda | -0.627 |
Span | -0.626 |
Tempest | -0.619 |
Token | our |
Token ID | 674 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
ijk | +1.004 |
�� | +0.959 |
ruct | +0.899 |
ld | +0.893 |
elephants | +0.845 |
Neg logit contributions | |
| -1.060 |
USS | -1.023 |
romeda | -1.017 |
Span | -1.015 |
Tempest | -1.001 |
Token | comments |
Token ID | 3651 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ijk | +0.333 |
�� | +0.320 |
ruct | +0.302 |
ld | +0.302 |
elephants | +0.287 |
Neg logit contributions | |
| -0.273 |
USS | -0.263 |
romeda | -0.263 |
Span | -0.261 |
Tempest | -0.257 |
Token | policy |
Token ID | 2450 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
| +0.356 |
USS | +0.347 |
romeda | +0.346 |
Span | +0.344 |
Tempest | +0.341 |
Neg logit contributions | |
ijk | -0.219 |
�� | -0.206 |
ruct | -0.190 |
ld | -0.189 |
elephants | -0.175 |
Token | before |
Token ID | 878 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
| +1.695 |
USS | +1.631 |
romeda | +1.621 |
Span | +1.617 |
Tempest | +1.595 |
Neg logit contributions | |
ijk | -1.838 |
�� | -1.762 |
ruct | -1.659 |
ld | -1.650 |
elephants | -1.566 |
Token | commenting |
Token ID | 26387 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
ijk | +0.576 |
�� | +0.546 |
ld | +0.512 |
ruct | +0.502 |
elephants | +0.480 |
Neg logit contributions | |
| -0.790 |
romeda | -0.775 |
USS | -0.767 |
Tempest | -0.759 |
Span | -0.759 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
| +3.076 |
USS | +2.956 |
Span | +2.929 |
romeda | +2.922 |
Tempest | +2.879 |
Neg logit contributions | |
ijk | -3.625 |
�� | -3.486 |
ruct | -3.279 |
ld | -3.260 |
elephants | -3.106 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
| +0.079 |
romeda | +0.079 |
USS | +0.077 |
Nanto | +0.076 |
Tempest | +0.076 |
Neg logit contributions | |
ijk | -0.099 |
�� | -0.094 |
ruct | -0.090 |
ld | -0.089 |
elephants | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ijk | +0.282 |
ld | +0.259 |
�� | +0.259 |
ruct | +0.257 |
—- | +0.243 |
Neg logit contributions | |
romeda | -0.220 |
| -0.219 |
USS | -0.215 |
Span | -0.213 |
Tempest | -0.211 |
Token | Note |
Token ID | 6425 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ijk | +0.340 |
�� | +0.324 |
ld | +0.309 |
ruct | +0.307 |
elephants | +0.289 |
Neg logit contributions | |
| -0.314 |
romeda | -0.305 |
USS | -0.300 |
Tempest | -0.296 |
Span | -0.295 |
Token | : |
Token ID | 25 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ijk | +1.389 |
�� | +1.318 |
ld | +1.255 |
ruct | +1.248 |
elephants | +1.167 |
Neg logit contributions | |
| -1.385 |
romeda | -1.346 |
USS | -1.345 |
Tempest | -1.318 |
Span | -1.318 |
Token |
|
Token ID | 198 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
| +0.629 |
USS | +0.603 |
romeda | +0.598 |
Span | +0.597 |
Tempest | +0.588 |
Neg logit contributions | |
ijk | -0.811 |
�� | -0.780 |
ruct | -0.738 |
ld | -0.734 |
elephants | -0.700 |
Token |
|
Token ID | 198 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
| +0.397 |
romeda | +0.388 |
USS | +0.385 |
Span | +0.381 |
Tempest | +0.376 |
Neg logit contributions | |
ijk | -0.536 |
�� | -0.502 |
ld | -0.490 |
ruct | -0.489 |
phe | -0.461 |
Token | Other |
Token ID | 6395 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
| +0.333 |
USS | +0.321 |
romeda | +0.318 |
Span | +0.317 |
Tempest | +0.312 |
Neg logit contributions | |
ijk | -0.384 |
�� | -0.369 |
ruct | -0.348 |
ld | -0.345 |
elephants | -0.330 |
Token | media |
Token ID | 2056 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ijk | +0.581 |
�� | +0.555 |
ruct | +0.524 |
ld | +0.524 |
elephants | +0.498 |
Neg logit contributions | |
| -0.522 |
USS | -0.504 |
romeda | -0.501 |
Span | -0.498 |
Tempest | -0.492 |
Token | [ |
Token ID | 685 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ijk | +0.235 |
�� | +0.224 |
ruct | +0.211 |
ld | +0.210 |
elephants | +0.199 |
Neg logit contributions | |
| -0.246 |
USS | -0.239 |
romeda | -0.237 |
Span | -0.237 |
Tempest | -0.233 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
| +0.427 |
USS | +0.412 |
Span | +0.407 |
romeda | +0.406 |
Tempest | +0.403 |
Neg logit contributions | |
ijk | -0.389 |
�� | -0.372 |
ruct | -0.348 |
ld | -0.344 |
elephants | -0.326 |
Token | ] |
Token ID | 2361 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
| +2.631 |
Span | +2.378 |
USS | +2.372 |
Tempest | +2.336 |
romeda | +2.286 |
Neg logit contributions | |
ijk | -4.127 |
�� | -4.013 |
ruct | -3.766 |
ld | -3.666 |
phe | -3.659 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ijk | +0.466 |
�� | +0.450 |
ruct | +0.426 |
ld | +0.423 |
elephants | +0.406 |
Neg logit contributions | |
| -0.302 |
USS | -0.287 |
Span | -0.285 |
romeda | -0.282 |
Tempest | -0.280 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
| +1.102 |
USS | +1.059 |
romeda | +1.055 |
Span | +1.047 |
Tempest | +1.030 |
Neg logit contributions | |
ijk | -1.561 |
�� | -1.493 |
ruct | -1.427 |
ld | -1.421 |
elephants | -1.354 |
Token | Video |
Token ID | 10798 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
| +0.915 |
USS | +0.888 |
romeda | +0.868 |
Span | +0.867 |
Tempest | +0.855 |
Neg logit contributions | |
ijk | -1.029 |
�� | -0.992 |
ruct | -0.930 |
ld | -0.917 |
elephants | -0.884 |
Token | games |
Token ID | 1830 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
| +0.306 |
USS | +0.294 |
romeda | +0.292 |
Span | +0.291 |
Tempest | +0.287 |
Neg logit contributions | |
ijk | -0.348 |
�� | -0.334 |
ruct | -0.315 |
ld | -0.312 |
elephants | -0.297 |
Token | pe |
Token ID | 431 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ijk | +1.017 |
�� | +0.963 |
ruct | +0.906 |
ld | +0.904 |
phe | +0.852 |
Neg logit contributions | |
| -1.148 |
USS | -1.117 |
romeda | -1.104 |
Span | -1.097 |
Tempest | -1.087 |
Token | re |
Token ID | 260 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
| +0.113 |
USS | +0.110 |
romeda | +0.109 |
Span | +0.109 |
Tempest | +0.107 |
Neg logit contributions | |
ijk | -0.109 |
�� | -0.104 |
ruct | -0.098 |
ld | -0.098 |
phe | -0.092 |
Token | Art |
Token ID | 3683 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
ijk | +1.085 |
�� | +1.028 |
ruct | +0.966 |
ld | +0.964 |
elephants | +0.911 |
Neg logit contributions | |
| -1.178 |
USS | -1.144 |
romeda | -1.140 |
Span | -1.129 |
Tempest | -1.113 |
Token | Museum |
Token ID | 9594 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ijk | +0.444 |
�� | +0.418 |
ruct | +0.383 |
ld | +0.380 |
elephants | +0.352 |
Neg logit contributions | |
| -0.751 |
USS | -0.730 |
romeda | -0.727 |
Span | -0.725 |
Tempest | -0.717 |
Token | [ |
Token ID | 685 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ijk | +0.371 |
�� | +0.355 |
ruct | +0.333 |
ld | +0.331 |
elephants | +0.314 |
Neg logit contributions | |
| -0.371 |
USS | -0.358 |
romeda | -0.356 |
Span | -0.355 |
Tempest | -0.350 |
Token | edit |
Token ID | 4370 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
| +0.285 |
USS | +0.276 |
romeda | +0.275 |
Span | +0.274 |
Tempest | +0.270 |
Neg logit contributions | |
ijk | -0.252 |
�� | -0.239 |
ruct | -0.224 |
ld | -0.223 |
elephants | -0.210 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
| +2.675 |
USS | +2.483 |
Span | +2.464 |
Tempest | +2.409 |
romeda | +2.396 |
Neg logit contributions | |
ijk | -3.985 |
�� | -3.983 |
ruct | -3.629 |
ld | -3.573 |
elephants | -3.511 |
Token |
|
Token ID | 198 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
ijk | +1.931 |
ld | +1.769 |
ruct | +1.749 |
�� | +1.732 |
—- | +1.654 |
Neg logit contributions | |
romeda | -1.593 |
| -1.580 |
USS | -1.560 |
Span | -1.532 |
Tempest | -1.512 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
ijk | +0.718 |
ld | +0.660 |
�� | +0.654 |
ruct | +0.654 |
—- | +0.619 |
Neg logit contributions | |
| -0.561 |
romeda | -0.561 |
USS | -0.552 |
Span | -0.545 |
Tempest | -0.538 |
Token | The |
Token ID | 464 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
ijk | +0.312 |
�� | +0.298 |
ruct | +0.280 |
ld | +0.278 |
elephants | +0.264 |
Neg logit contributions | |
| -0.310 |
USS | -0.299 |
romeda | -0.297 |
Span | -0.297 |
Tempest | -0.293 |
Token | M |
Token ID | 337 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ijk | +0.756 |
�� | +0.717 |
ruct | +0.676 |
ld | +0.675 |
elephants | +0.642 |
Neg logit contributions | |
| -0.747 |
USS | -0.724 |
romeda | -0.720 |
Span | -0.714 |
Tempest | -0.700 |
Token | the |
Token ID | 262 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ijk | +0.081 |
�� | +0.077 |
ruct | +0.072 |
ld | +0.072 |
elephants | +0.068 |
Neg logit contributions | |
| -0.092 |
USS | -0.089 |
romeda | -0.088 |
Span | -0.088 |
Tempest | -0.087 |
Token | A |
Token ID | 317 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ijk | +0.361 |
�� | +0.345 |
ld | +0.325 |
ruct | +0.325 |
elephants | +0.309 |
Neg logit contributions | |
| -0.365 |
USS | -0.354 |
romeda | -0.352 |
Span | -0.349 |
Tempest | -0.343 |
Token | - |
Token ID | 12 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
ijk | +1.009 |
�� | +0.966 |
ruct | +0.925 |
ld | +0.923 |
phe | +0.859 |
Neg logit contributions | |
| -0.967 |
romeda | -0.927 |
Span | -0.915 |
USS | -0.911 |
Tempest | -0.902 |
Token | story |
Token ID | 13571 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
| +0.569 |
USS | +0.550 |
romeda | +0.546 |
Span | +0.545 |
Tempest | +0.538 |
Neg logit contributions | |
ijk | -0.526 |
�� | -0.502 |
ruct | -0.470 |
ld | -0.466 |
elephants | -0.441 |
Token | or |
Token ID | 393 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ijk | +1.060 |
�� | +1.012 |
ruct | +0.957 |
ld | +0.955 |
elephants | +0.903 |
Neg logit contributions | |
| -1.007 |
USS | -0.977 |
romeda | -0.967 |
Span | -0.964 |
Tempest | -0.948 |
Token | B |
Token ID | 347 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ijk | +1.052 |
�� | +1.005 |
ruct | +0.947 |
ld | +0.946 |
elephants | +0.894 |
Neg logit contributions | |
| -1.073 |
USS | -1.041 |
romeda | -1.030 |
Span | -1.028 |
Tempest | -1.009 |
Token | - |
Token ID | 12 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
| +2.780 |
USS | +2.679 |
romeda | +2.618 |
Tempest | +2.602 |
Span | +2.601 |
Neg logit contributions | |
ijk | -3.778 |
�� | -3.617 |
ruct | -3.409 |
ld | -3.337 |
elephants | -3.262 |
Token | story |
Token ID | 13571 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
| +2.212 |
USS | +2.135 |
romeda | +2.109 |
Span | +2.103 |
Tempest | +2.074 |
Neg logit contributions | |
ijk | -2.313 |
�� | -2.244 |
ruct | -2.088 |
ld | -2.051 |
elephants | -1.987 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ijk | +0.735 |
�� | +0.704 |
ruct | +0.663 |
ld | +0.660 |
elephants | +0.626 |
Neg logit contributions | |
| -0.687 |
USS | -0.663 |
romeda | -0.657 |
Span | -0.656 |
Tempest | -0.646 |
Token | So |
Token ID | 1406 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
ijk | +0.587 |
�� | +0.559 |
ruct | +0.540 |
ld | +0.538 |
phe | +0.509 |
Neg logit contributions | |
| -0.447 |
USS | -0.440 |
romeda | -0.437 |
Span | -0.428 |
Tempest | -0.420 |
Token | a |
Token ID | 257 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
| +0.464 |
USS | +0.447 |
romeda | +0.443 |
Span | +0.442 |
Tempest | +0.436 |
Neg logit contributions | |
ijk | -0.526 |
�� | -0.504 |
ruct | -0.476 |
ld | -0.473 |
elephants | -0.450 |
Token | on |
Token ID | 319 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
| +0.497 |
USS | +0.479 |
romeda | +0.477 |
Span | +0.475 |
Tempest | +0.466 |
Neg logit contributions | |
ijk | -0.549 |
�� | -0.526 |
ruct | -0.497 |
ld | -0.495 |
elephants | -0.470 |
Token | sleeve |
Token ID | 23179 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
| +0.396 |
Span | +0.380 |
USS | +0.379 |
Tempest | +0.373 |
romeda | +0.370 |
Neg logit contributions | |
ijk | -0.399 |
�� | -0.392 |
ruct | -0.362 |
ld | -0.351 |
phe | -0.343 |
Token | at |
Token ID | 379 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ijk | +0.016 |
�� | +0.015 |
ruct | +0.014 |
ld | +0.014 |
phe | +0.013 |
Neg logit contributions | |
| -0.016 |
USS | -0.016 |
Span | -0.016 |
Tempest | -0.016 |
romeda | -0.016 |
Token | basketball |
Token ID | 9669 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
| +0.995 |
USS | +0.961 |
Span | +0.958 |
romeda | +0.952 |
Tempest | +0.944 |
Neg logit contributions | |
ijk | -0.954 |
�� | -0.911 |
ruct | -0.854 |
ld | -0.842 |
phe | -0.796 |
Token | game |
Token ID | 983 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
| +0.671 |
USS | +0.649 |
romeda | +0.648 |
Span | +0.642 |
Tempest | +0.622 |
Neg logit contributions | |
ijk | -0.878 |
�� | -0.844 |
ld | -0.801 |
ruct | -0.796 |
elephants | -0.767 |
Token | MORE |
Token ID | 12011 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
| +0.160 |
USS | +0.154 |
Span | +0.153 |
romeda | +0.152 |
Tempest | +0.152 |
Neg logit contributions | |
ijk | -0.200 |
�� | -0.193 |
ruct | -0.182 |
ld | -0.180 |
elephants | -0.172 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ijk | +2.201 |
�� | +2.096 |
ruct | +1.967 |
ld | +1.964 |
elephants | +1.865 |
Neg logit contributions | |
| -2.388 |
USS | -2.319 |
romeda | -2.317 |
Span | -2.290 |
Tempest | -2.253 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ijk | +0.950 |
�� | +0.903 |
ld | +0.857 |
ruct | +0.847 |
elephants | +0.816 |
Neg logit contributions | |
| -1.018 |
USS | -0.993 |
romeda | -0.986 |
Span | -0.976 |
Tempest | -0.965 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
| +0.782 |
USS | +0.754 |
romeda | +0.749 |
Span | +0.749 |
Tempest | +0.739 |
Neg logit contributions | |
ijk | -0.724 |
�� | -0.692 |
ruct | -0.648 |
ld | -0.643 |
elephants | -0.608 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
| +0.518 |
USS | +0.497 |
Span | +0.493 |
romeda | +0.492 |
Tempest | +0.486 |
Neg logit contributions | |
ijk | -0.572 |
�� | -0.549 |
ruct | -0.516 |
ld | -0.511 |
elephants | -0.487 |
Token | Diane |
Token ID | 26542 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ijk | +1.287 |
�� | +1.238 |
ruct | +1.170 |
ld | +1.164 |
elephants | +1.073 |
Neg logit contributions | |
romeda | -2.229 |
| -2.225 |
USS | -2.214 |
Span | -2.206 |
Nanto | -2.127 |
Token | be |
Token ID | 307 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ijk | +0.474 |
�� | +0.446 |
ruct | +0.420 |
ld | +0.420 |
elephants | +0.397 |
Neg logit contributions | |
| -0.550 |
USS | -0.537 |
romeda | -0.530 |
Span | -0.528 |
Tempest | -0.522 |
Token | stored |
Token ID | 8574 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ijk | +0.099 |
�� | +0.094 |
ruct | +0.089 |
ld | +0.089 |
elephants | +0.084 |
Neg logit contributions | |
| -0.095 |
USS | -0.092 |
romeda | -0.091 |
Span | -0.091 |
Tempest | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
ijk | +0.244 |
�� | +0.232 |
ruct | +0.221 |
ld | +0.220 |
elephants | +0.208 |
Neg logit contributions | |
| -0.230 |
USS | -0.223 |
romeda | -0.221 |
Span | -0.219 |
Tempest | -0.216 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
| +0.052 |
USS | +0.050 |
romeda | +0.050 |
Span | +0.050 |
Tempest | +0.049 |
Neg logit contributions | |
ijk | -0.049 |
�� | -0.047 |
ruct | -0.044 |
ld | -0.044 |
elephants | -0.041 |
Token | S |
Token ID | 311 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ijk | +0.193 |
�� | +0.183 |
ld | +0.175 |
ruct | +0.175 |
elephants | +0.165 |
Neg logit contributions | |
| -0.168 |
USS | -0.161 |
romeda | -0.161 |
Span | -0.158 |
Tempest | -0.156 |
Token | 3 |
Token ID | 18 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ijk | +0.696 |
�� | +0.658 |
ruct | +0.614 |
ld | +0.610 |
elephants | +0.569 |
Neg logit contributions | |
| -0.943 |
USS | -0.909 |
romeda | -0.908 |
Span | -0.904 |
Tempest | -0.896 |
Token | bucket |
Token ID | 19236 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ijk | +2.698 |
�� | +2.516 |
ruct | +2.356 |
ld | +2.355 |
elephants | +2.179 |
Neg logit contributions | |
| -3.602 |
USS | -3.536 |
romeda | -3.489 |
Span | -3.401 |
Nanto | -3.391 |
Token | . |
Token ID | 13 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ijk | +0.188 |
�� | +0.180 |
ruct | +0.170 |
ld | +0.169 |
elephants | +0.160 |
Neg logit contributions | |
| -0.175 |
USS | -0.169 |
romeda | -0.167 |
Span | -0.167 |
Tempest | -0.164 |
Token | As |
Token ID | 1081 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
| +0.417 |
USS | +0.403 |
romeda | +0.399 |
Span | +0.394 |
Tempest | +0.387 |
Neg logit contributions | |
ijk | -0.539 |
�� | -0.513 |
ruct | -0.492 |
ld | -0.490 |
elephants | -0.465 |
Token | the |
Token ID | 262 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
ijk | +0.021 |
�� | +0.020 |
ld | +0.019 |
ruct | +0.019 |
elephants | +0.018 |
Neg logit contributions | |
| -0.019 |
USS | -0.018 |
romeda | -0.018 |
Span | -0.018 |
Tempest | -0.017 |
Token | input |
Token ID | 5128 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
| +0.057 |
USS | +0.055 |
romeda | +0.054 |
Span | +0.054 |
Tempest | +0.053 |
Neg logit contributions | |
ijk | -0.067 |
�� | -0.064 |
ruct | -0.060 |
ld | -0.060 |
elephants | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
| +0.871 |
USS | +0.834 |
Span | +0.831 |
romeda | +0.827 |
Tempest | +0.818 |
Neg logit contributions | |
ijk | -0.928 |
�� | -0.894 |
ruct | -0.835 |
ld | -0.827 |
phe | -0.787 |
Token | Mor |
Token ID | 3461 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
| +1.132 |
Span | +1.097 |
Tempest | +1.084 |
USS | +1.077 |
romeda | +1.067 |
Neg logit contributions | |
ijk | -1.207 |
�� | -1.159 |
ruct | -1.079 |
ld | -1.061 |
phe | -1.017 |
Token | ia |
Token ID | 544 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ijk | +1.733 |
�� | +1.589 |
ld | +1.568 |
ruct | +1.546 |
phe | +1.466 |
Neg logit contributions | |
| -1.733 |
USS | -1.720 |
romeda | -1.684 |
Span | -1.677 |
Tempest | -1.648 |
Token | . |
Token ID | 13 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
ijk | +1.195 |
�� | +1.130 |
ruct | +1.073 |
ld | +1.069 |
elephants | +1.009 |
Neg logit contributions | |
| -1.275 |
USS | -1.244 |
romeda | -1.234 |
Span | -1.220 |
Tempest | -1.207 |
Token | Inside |
Token ID | 14384 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ijk | +0.689 |
�� | +0.652 |
ld | +0.624 |
ruct | +0.622 |
elephants | +0.586 |
Neg logit contributions | |
| -0.677 |
romeda | -0.659 |
USS | -0.658 |
Span | -0.640 |
Tempest | -0.633 |
Token | Mor |
Token ID | 3461 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ijk | +0.182 |
�� | +0.174 |
ruct | +0.163 |
ld | +0.161 |
elephants | +0.153 |
Neg logit contributions | |
| -0.185 |
Span | -0.178 |
USS | -0.177 |
romeda | -0.176 |
Tempest | -0.175 |
Token | ia |
Token ID | 544 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ijk | +2.281 |
ld | +2.060 |
ruct | +2.024 |
�� | +2.014 |
phe | +1.914 |
Neg logit contributions | |
USS | -2.423 |
| -2.406 |
Span | -2.362 |
romeda | -2.343 |
Tempest | -2.310 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ijk | +2.206 |
�� | +2.108 |
ruct | +1.977 |
ld | +1.967 |
elephants | +1.864 |
Neg logit contributions | |
| -2.359 |
USS | -2.280 |
romeda | -2.269 |
Span | -2.251 |
Tempest | -2.222 |
Token | they |
Token ID | 484 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ijk | +1.419 |
�� | +1.355 |
ruct | +1.270 |
ld | +1.266 |
elephants | +1.201 |
Neg logit contributions | |
| -1.594 |
USS | -1.545 |
romeda | -1.538 |
Span | -1.521 |
Tempest | -1.500 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ijk | +0.635 |
�� | +0.595 |
ld | +0.571 |
ruct | +0.568 |
elephants | +0.539 |
Neg logit contributions | |
| -0.676 |
USS | -0.663 |
romeda | -0.654 |
Span | -0.653 |
Tempest | -0.644 |
Token | of |
Token ID | 286 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
| +0.073 |
USS | +0.070 |
Span | +0.070 |
romeda | +0.069 |
Tempest | +0.069 |
Neg logit contributions | |
ijk | -0.085 |
�� | -0.081 |
ruct | -0.077 |
ld | -0.076 |
phe | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ijk | +1.004 |
�� | +0.959 |
ruct | +0.914 |
ld | +0.905 |
elephants | +0.866 |
Neg logit contributions | |
| -0.804 |
romeda | -0.776 |
USS | -0.774 |
Span | -0.759 |
Tempest | -0.751 |
Token | collection |
Token ID | 4947 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ijk | +0.407 |
�� | +0.387 |
ruct | +0.366 |
ld | +0.365 |
elephants | +0.348 |
Neg logit contributions | |
| -0.369 |
USS | -0.357 |
romeda | -0.356 |
Span | -0.351 |
Tempest | -0.345 |
Token | , |
Token ID | 11 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
ijk | +0.342 |
�� | +0.326 |
ruct | +0.306 |
ld | +0.304 |
elephants | +0.288 |
Neg logit contributions | |
| -0.358 |
USS | -0.345 |
romeda | -0.343 |
Span | -0.342 |
Tempest | -0.338 |
Token | said |
Token ID | 531 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ijk | +0.743 |
�� | +0.711 |
ruct | +0.670 |
ld | +0.666 |
elephants | +0.634 |
Neg logit contributions | |
| -0.698 |
USS | -0.677 |
romeda | -0.673 |
Span | -0.666 |
Tempest | -0.658 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
| +0.191 |
USS | +0.183 |
Span | +0.182 |
romeda | +0.181 |
Tempest | +0.179 |
Neg logit contributions | |
ijk | -0.234 |
�� | -0.225 |
ruct | -0.212 |
ld | -0.211 |
elephants | -0.201 |
Token | editor |
Token ID | 5464 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ijk | +1.513 |
�� | +1.440 |
ruct | +1.361 |
ld | +1.361 |
elephants | +1.288 |
Neg logit contributions | |
| -1.464 |
USS | -1.437 |
romeda | -1.425 |
Span | -1.401 |
Tempest | -1.382 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ijk | +2.375 |
�� | +2.276 |
ruct | +2.141 |
ld | +2.135 |
elephants | +2.023 |
Neg logit contributions | |
| -2.194 |
USS | -2.133 |
romeda | -2.115 |
Span | -2.097 |
Tempest | -2.067 |
Token | are |
Token ID | 389 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ijk | +0.904 |
�� | +0.865 |
ruct | +0.813 |
ld | +0.807 |
elephants | +0.765 |
Neg logit contributions | |
| -0.902 |
USS | -0.869 |
romeda | -0.863 |
Span | -0.862 |
Tempest | -0.850 |
Token | not |
Token ID | 407 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
| +0.610 |
USS | +0.587 |
romeda | +0.583 |
Span | +0.583 |
Tempest | +0.575 |
Neg logit contributions | |
ijk | -0.599 |
�� | -0.575 |
ruct | -0.538 |
ld | -0.533 |
phe | -0.505 |
Token | only |
Token ID | 691 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
| +0.861 |
USS | +0.828 |
Span | +0.823 |
romeda | +0.823 |
Tempest | +0.814 |
Neg logit contributions | |
ijk | -0.776 |
�� | -0.744 |
ruct | -0.692 |
ld | -0.686 |
phe | -0.649 |
Token | about |
Token ID | 546 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
ijk | +0.012 |
�� | +0.011 |
ruct | +0.011 |
ld | +0.011 |
elephants | +0.010 |
Neg logit contributions | |
| -0.012 |
USS | -0.012 |
romeda | -0.012 |
Span | -0.012 |
Tempest | -0.012 |
Token | get |
Token ID | 651 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ijk | +0.107 |
�� | +0.102 |
ruct | +0.096 |
ld | +0.095 |
elephants | +0.090 |
Neg logit contributions | |
| -0.116 |
USS | -0.112 |
romeda | -0.111 |
Span | -0.111 |
Tempest | -0.109 |
Token | - |
Token ID | 12 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
| +0.130 |
USS | +0.125 |
romeda | +0.124 |
Span | +0.124 |
Tempest | +0.122 |
Neg logit contributions | |
ijk | -0.144 |
�� | -0.138 |
ruct | -0.130 |
ld | -0.129 |
elephants | -0.123 |
Token | out |
Token ID | 448 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
| +0.210 |
romeda | +0.201 |
Span | +0.200 |
USS | +0.200 |
Tempest | +0.199 |
Neg logit contributions | |
ijk | -0.427 |
�� | -0.409 |
ld | -0.401 |
ruct | -0.394 |
phe | -0.381 |
Token | - |
Token ID | 12 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
| +0.120 |
USS | +0.116 |
romeda | +0.114 |
Span | +0.114 |
Tempest | +0.112 |
Neg logit contributions | |
ijk | -0.144 |
�� | -0.138 |
ruct | -0.129 |
ld | -0.128 |
elephants | -0.123 |
Token | the |
Token ID | 1169 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
ijk | +1.755 |
�� | +1.667 |
ld | +1.643 |
ruct | +1.632 |
elephants | +1.519 |
Neg logit contributions | |
| -1.510 |
romeda | -1.491 |
Span | -1.480 |
Tempest | -1.461 |
USS | -1.444 |
Token | - |
Token ID | 12 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
| +0.063 |
USS | +0.061 |
romeda | +0.061 |
Span | +0.061 |
Tempest | +0.060 |
Neg logit contributions | |
ijk | -0.066 |
�� | -0.062 |
ld | -0.059 |
ruct | -0.059 |
elephants | -0.056 |
Token | vote |
Token ID | 27257 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ijk | +2.017 |
�� | +1.844 |
ld | +1.799 |
ruct | +1.734 |
elephants | +1.613 |
Neg logit contributions | |
| -2.679 |
romeda | -2.672 |
Span | -2.639 |
USS | -2.629 |
Tempest | -2.626 |
Token | efforts |
Token ID | 4040 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ijk | +0.526 |
�� | +0.498 |
ruct | +0.468 |
ld | +0.467 |
elephants | +0.439 |
Neg logit contributions | |
| -0.635 |
USS | -0.619 |
romeda | -0.615 |
Span | -0.614 |
Tempest | -0.605 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ijk | +0.380 |
�� | +0.364 |
ruct | +0.342 |
ld | +0.339 |
elephants | +0.322 |
Neg logit contributions | |
| -0.365 |
USS | -0.351 |
romeda | -0.349 |
Span | -0.349 |
Tempest | -0.344 |
Token | and |
Token ID | 290 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
ijk | +0.174 |
�� | +0.167 |
ruct | +0.157 |
ld | +0.156 |
elephants | +0.148 |
Neg logit contributions | |
| -0.170 |
USS | -0.164 |
romeda | -0.163 |
Span | -0.162 |
Tempest | -0.160 |
Token | populist |
Token ID | 26815 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
| +0.039 |
USS | +0.038 |
romeda | +0.038 |
Span | +0.038 |
Tempest | +0.037 |
Neg logit contributions | |
ijk | -0.039 |
�� | -0.037 |
ruct | -0.035 |
ld | -0.035 |
elephants | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ijk | +0.366 |
�� | +0.350 |
ruct | +0.330 |
ld | +0.327 |
elephants | +0.310 |
Neg logit contributions | |
| -0.352 |
USS | -0.340 |
romeda | -0.338 |
Span | -0.336 |
Tempest | -0.332 |
Token | a |
Token ID | 257 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
| +0.201 |
USS | +0.193 |
Span | +0.192 |
romeda | +0.192 |
Tempest | +0.189 |
Neg logit contributions | |
ijk | -0.211 |
�� | -0.202 |
ruct | -0.190 |
ld | -0.189 |
elephants | -0.179 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ijk | +0.137 |
�� | +0.131 |
ruct | +0.123 |
ld | +0.122 |
elephants | +0.115 |
Neg logit contributions | |
| -0.145 |
USS | -0.140 |
romeda | -0.139 |
Span | -0.139 |
Tempest | -0.137 |
Token | percent |
Token ID | 1411 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
| +0.089 |
USS | +0.086 |
romeda | +0.086 |
Span | +0.085 |
Tempest | +0.084 |
Neg logit contributions | |
ijk | -0.095 |
�� | -0.091 |
ruct | -0.086 |
ld | -0.085 |
elephants | -0.081 |
Token | wheat |
Token ID | 17135 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
| +0.403 |
USS | +0.389 |
romeda | +0.386 |
Span | +0.386 |
Tempest | +0.381 |
Neg logit contributions | |
ijk | -0.365 |
�� | -0.348 |
ruct | -0.326 |
ld | -0.323 |
elephants | -0.305 |
Token | IPA |
Token ID | 27966 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ijk | +0.388 |
�� | +0.369 |
ruct | +0.348 |
ld | +0.347 |
elephants | +0.327 |
Neg logit contributions | |
| -0.396 |
USS | -0.384 |
romeda | -0.382 |
Span | -0.378 |
Tempest | -0.374 |
Token | made |
Token ID | 925 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ijk | +1.311 |
�� | +1.241 |
ld | +1.178 |
ruct | +1.169 |
elephants | +1.105 |
Neg logit contributions | |
| -1.374 |
USS | -1.338 |
romeda | -1.327 |
Span | -1.320 |
Tempest | -1.297 |
Token | with |
Token ID | 351 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ijk | +1.323 |
�� | +1.255 |
ruct | +1.192 |
ld | +1.190 |
elephants | +1.127 |
Neg logit contributions | |
| -1.335 |
USS | -1.302 |
romeda | -1.288 |
Span | -1.283 |
Tempest | -1.264 |
Token | Chin |
Token ID | 22604 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ijk | +0.449 |
�� | +0.428 |
ruct | +0.405 |
ld | +0.404 |
elephants | +0.385 |
Neg logit contributions | |
| -0.429 |
USS | -0.415 |
romeda | -0.411 |
Span | -0.407 |
Tempest | -0.403 |
Token | ook |
Token ID | 566 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ijk | +0.658 |
�� | +0.586 |
ld | +0.553 |
ruct | +0.552 |
elephants | +0.511 |
Neg logit contributions | |
| -1.264 |
romeda | -1.237 |
USS | -1.234 |
Span | -1.217 |
Tempest | -1.217 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
| +0.269 |
USS | +0.259 |
romeda | +0.256 |
Span | +0.254 |
Tempest | +0.250 |
Neg logit contributions | |
ijk | -0.379 |
�� | -0.364 |
ruct | -0.347 |
ld | -0.345 |
elephants | -0.331 |
Token | full |
Token ID | 1336 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
ijk | +0.782 |
�� | +0.757 |
ld | +0.716 |
ruct | +0.713 |
elephants | +0.682 |
Neg logit contributions | |
| -0.693 |
romeda | -0.671 |
USS | -0.666 |
Span | -0.661 |
Tempest | -0.647 |
Token | training |
Token ID | 3047 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
| +0.051 |
USS | +0.049 |
romeda | +0.049 |
Span | +0.049 |
Tempest | +0.048 |
Neg logit contributions | |
ijk | -0.044 |
�� | -0.042 |
ld | -0.040 |
ruct | -0.040 |
elephants | -0.037 |
Token | this |
Token ID | 428 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ijk | +0.954 |
�� | +0.904 |
ruct | +0.856 |
ld | +0.854 |
elephants | +0.816 |
Neg logit contributions | |
| -1.037 |
USS | -1.012 |
romeda | -1.007 |
Span | -0.993 |
Tempest | -0.984 |
Token | week |
Token ID | 1285 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
| +0.416 |
USS | +0.401 |
romeda | +0.398 |
Span | +0.398 |
Tempest | +0.393 |
Neg logit contributions | |
ijk | -0.374 |
�� | -0.358 |
ruct | -0.335 |
ld | -0.331 |
elephants | -0.313 |
Token | after |
Token ID | 706 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ijk | +0.174 |
�� | +0.166 |
ruct | +0.156 |
ld | +0.155 |
elephants | +0.147 |
Neg logit contributions | |
| -0.173 |
USS | -0.167 |
romeda | -0.165 |
Span | -0.165 |
Tempest | -0.163 |
Token | an |
Token ID | 281 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ijk | +0.521 |
�� | +0.497 |
ruct | +0.464 |
ld | +0.463 |
elephants | +0.437 |
Neg logit contributions | |
| -0.590 |
USS | -0.572 |
romeda | -0.569 |
Span | -0.565 |
Tempest | -0.558 |
Token | abdominal |
Token ID | 32692 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ijk | +0.554 |
�� | +0.523 |
ruct | +0.491 |
ld | +0.486 |
elephants | +0.463 |
Neg logit contributions | |
| -0.641 |
USS | -0.624 |
romeda | -0.618 |
Span | -0.616 |
Tempest | -0.607 |
Token | injury |
Token ID | 5095 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
| +1.334 |
USS | +1.280 |
Span | +1.279 |
romeda | +1.275 |
Tempest | +1.262 |
Neg logit contributions | |
ijk | -1.183 |
�� | -1.129 |
ruct | -1.054 |
ld | -1.043 |
phe | -0.989 |
Token | . |
Token ID | 13 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ijk | +0.037 |
�� | +0.035 |
ruct | +0.033 |
ld | +0.033 |
elephants | +0.031 |
Neg logit contributions | |
| -0.038 |
USS | -0.037 |
romeda | -0.037 |
Span | -0.037 |
Tempest | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ijk | +0.622 |
�� | +0.598 |
ruct | +0.566 |
ld | +0.563 |
elephants | +0.537 |
Neg logit contributions | |
| -0.477 |
USS | -0.458 |
romeda | -0.455 |
Span | -0.453 |
Tempest | -0.446 |
Token |
|
Token ID | 198 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ijk | +0.606 |
ld | +0.559 |
ruct | +0.552 |
�� | +0.551 |
—- | +0.525 |
Neg logit contributions | |
romeda | -0.486 |
| -0.480 |
USS | -0.477 |
Span | -0.470 |
Tempest | -0.465 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ijk | +0.590 |
�� | +0.565 |
ruct | +0.529 |
ld | +0.527 |
elephants | +0.498 |
Neg logit contributions | |
| -0.614 |
USS | -0.594 |
romeda | -0.590 |
Span | -0.588 |
Tempest | -0.580 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
| +0.269 |
USS | +0.259 |
romeda | +0.258 |
Span | +0.258 |
Tempest | +0.254 |
Neg logit contributions | |
ijk | -0.238 |
�� | -0.228 |
ruct | -0.213 |
ld | -0.210 |
phe | -0.199 |
Token | image |
Token ID | 2939 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
| +0.204 |
USS | +0.197 |
romeda | +0.196 |
Span | +0.196 |
Tempest | +0.193 |
Neg logit contributions | |
ijk | -0.183 |
�� | -0.175 |
ruct | -0.164 |
ld | -0.162 |
elephants | -0.153 |
Token | below |
Token ID | 2174 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ijk | +0.400 |
�� | +0.382 |
ruct | +0.360 |
ld | +0.359 |
elephants | +0.340 |
Neg logit contributions | |
| -0.376 |
USS | -0.364 |
romeda | -0.360 |
Span | -0.360 |
Tempest | -0.354 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ijk | +0.332 |
�� | +0.318 |
ruct | +0.298 |
ld | +0.295 |
elephants | +0.280 |
Neg logit contributions | |
| -0.341 |
USS | -0.328 |
romeda | -0.326 |
Span | -0.326 |
Tempest | -0.321 |
Token | Best |
Token ID | 6705 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
| +0.128 |
USS | +0.123 |
romeda | +0.122 |
Span | +0.122 |
Tempest | +0.120 |
Neg logit contributions | |
ijk | -0.135 |
�� | -0.129 |
ruct | -0.122 |
ld | -0.121 |
elephants | -0.115 |
Token | Buy |
Token ID | 11763 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ijk | +0.322 |
�� | +0.307 |
ruct | +0.293 |
ld | +0.292 |
phe | +0.276 |
Neg logit contributions | |
| -0.264 |
USS | -0.256 |
romeda | -0.255 |
Span | -0.252 |
Tempest | -0.249 |
Token | will |
Token ID | 481 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
| +0.266 |
USS | +0.257 |
romeda | +0.255 |
Span | +0.254 |
Tempest | +0.251 |
Neg logit contributions | |
ijk | -0.255 |
�� | -0.243 |
ruct | -0.229 |
ld | -0.228 |
elephants | -0.215 |
Token | have |
Token ID | 423 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ijk | +0.069 |
�� | +0.065 |
ld | +0.062 |
ruct | +0.062 |
elephants | +0.059 |
Neg logit contributions | |
| -0.077 |
USS | -0.075 |
romeda | -0.075 |
Span | -0.074 |
Tempest | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ijk | +0.187 |
�� | +0.179 |
ruct | +0.168 |
ld | +0.167 |
elephants | +0.158 |
Neg logit contributions | |
| -0.188 |
USS | -0.181 |
romeda | -0.180 |
Span | -0.180 |
Tempest | -0.177 |
Token | Google |
Token ID | 3012 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ijk | +0.434 |
�� | +0.416 |
ruct | +0.394 |
ld | +0.392 |
elephants | +0.374 |
Neg logit contributions | |
| -0.376 |
USS | -0.362 |
romeda | -0.360 |
Span | -0.358 |
Tempest | -0.352 |
Token | success |
Token ID | 1943 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ijk | +0.293 |
�� | +0.279 |
ruct | +0.264 |
ld | +0.263 |
elephants | +0.249 |
Neg logit contributions | |
| -0.289 |
USS | -0.280 |
romeda | -0.277 |
Span | -0.276 |
Tempest | -0.273 |
Token | or |
Token ID | 393 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ijk | +0.133 |
�� | +0.129 |
ruct | +0.120 |
ld | +0.119 |
elephants | +0.113 |
Neg logit contributions | |
| -0.127 |
Span | -0.121 |
USS | -0.121 |
romeda | -0.121 |
Tempest | -0.119 |
Token | failure |
Token ID | 5287 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ijk | +1.289 |
�� | +1.227 |
ld | +1.171 |
ruct | +1.170 |
elephants | +1.120 |
Neg logit contributions | |
| -1.077 |
USS | -1.047 |
romeda | -1.035 |
Span | -1.029 |
Tempest | -1.010 |
Token | ; |
Token ID | 26 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ijk | +0.999 |
�� | +0.959 |
ruct | +0.901 |
ld | +0.894 |
elephants | +0.848 |
Neg logit contributions | |
| -0.949 |
USS | -0.912 |
romeda | -0.906 |
Span | -0.906 |
Tempest | -0.892 |
Token | it |
Token ID | 340 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
ijk | +0.112 |
�� | +0.107 |
ruct | +0.100 |
ld | +0.100 |
elephants | +0.094 |
Neg logit contributions | |
| -0.120 |
USS | -0.115 |
romeda | -0.115 |
Span | -0.115 |
Tempest | -0.113 |
Token | is |
Token ID | 318 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ijk | +0.499 |
�� | +0.479 |
ruct | +0.446 |
ld | +0.442 |
phe | +0.417 |
Neg logit contributions | |
| -0.541 |
USS | -0.520 |
Span | -0.518 |
romeda | -0.518 |
Tempest | -0.510 |
Token | life |
Token ID | 1204 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ijk | +0.899 |
�� | +0.857 |
ruct | +0.809 |
ld | +0.804 |
elephants | +0.764 |
Neg logit contributions | |
| -0.908 |
USS | -0.879 |
romeda | -0.871 |
Span | -0.867 |
Tempest | -0.854 |
Token | and |
Token ID | 290 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ijk | +1.324 |
�� | +1.262 |
ruct | +1.192 |
ld | +1.191 |
elephants | +1.132 |
Neg logit contributions | |
| -1.257 |
USS | -1.220 |
romeda | -1.205 |
Span | -1.191 |
Tempest | -1.187 |
Token | death |
Token ID | 1918 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ijk | +0.051 |
�� | +0.048 |
ld | +0.045 |
ruct | +0.045 |
elephants | +0.042 |
Neg logit contributions | |
| -0.068 |
USS | -0.066 |
romeda | -0.065 |
Span | -0.065 |
Tempest | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ijk | +1.277 |
�� | +1.220 |
ruct | +1.153 |
ld | +1.150 |
elephants | +1.094 |
Neg logit contributions | |
| -1.160 |
USS | -1.125 |
romeda | -1.113 |
Span | -1.107 |
Tempest | -1.095 |
Token | Elon |
Token ID | 32451 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ijk | +0.212 |
�� | +0.202 |
ruct | +0.194 |
ld | +0.194 |
elephants | +0.183 |
Neg logit contributions | |
| -0.170 |
USS | -0.166 |
romeda | -0.165 |
Span | -0.161 |
Tempest | -0.160 |
Token | scheduled |
Token ID | 7530 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ijk | +0.185 |
�� | +0.176 |
ruct | +0.166 |
ld | +0.166 |
elephants | +0.158 |
Neg logit contributions | |
| -0.183 |
USS | -0.177 |
romeda | -0.177 |
Span | -0.176 |
Tempest | -0.173 |
Token | before |
Token ID | 878 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ijk | +0.111 |
�� | +0.107 |
ruct | +0.100 |
ld | +0.099 |
elephants | +0.094 |
Neg logit contributions | |
| -0.110 |
USS | -0.105 |
Span | -0.105 |
romeda | -0.105 |
Tempest | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ijk | +0.383 |
�� | +0.366 |
ruct | +0.345 |
ld | +0.342 |
elephants | +0.325 |
Neg logit contributions | |
| -0.368 |
USS | -0.355 |
romeda | -0.353 |
Span | -0.352 |
Tempest | -0.347 |
Token | Paris |
Token ID | 6342 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ijk | +0.365 |
�� | +0.347 |
ruct | +0.326 |
ld | +0.324 |
elephants | +0.306 |
Neg logit contributions | |
| -0.405 |
USS | -0.392 |
romeda | -0.391 |
Span | -0.389 |
Tempest | -0.384 |
Token | conference |
Token ID | 4495 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ijk | +0.347 |
�� | +0.330 |
ruct | +0.307 |
ld | +0.304 |
elephants | +0.286 |
Neg logit contributions | |
| -0.451 |
USS | -0.437 |
romeda | -0.435 |
Span | -0.434 |
Tempest | -0.429 |
Token | but |
Token ID | 475 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ijk | +1.485 |
�� | +1.408 |
ruct | +1.330 |
ld | +1.320 |
elephants | +1.255 |
Neg logit contributions | |
| -1.574 |
USS | -1.528 |
romeda | -1.523 |
Span | -1.511 |
Tempest | -1.495 |
Token | warned |
Token ID | 7728 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ijk | +0.217 |
�� | +0.208 |
ruct | +0.196 |
ld | +0.194 |
elephants | +0.184 |
Neg logit contributions | |
| -0.211 |
USS | -0.204 |
romeda | -0.203 |
Span | -0.202 |
Tempest | -0.199 |
Token | that |
Token ID | 326 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
| +0.080 |
USS | +0.077 |
romeda | +0.076 |
Span | +0.076 |
Tempest | +0.075 |
Neg logit contributions | |
ijk | -0.092 |
�� | -0.089 |
ruct | -0.084 |
ld | -0.083 |
elephants | -0.079 |
Token | its |
Token ID | 663 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
| +0.596 |
USS | +0.570 |
romeda | +0.566 |
Span | +0.566 |
Tempest | +0.559 |
Neg logit contributions | |
ijk | -0.586 |
�� | -0.562 |
ruct | -0.526 |
ld | -0.521 |
phe | -0.493 |
Token | success |
Token ID | 1943 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
ijk | +0.290 |
�� | +0.276 |
ruct | +0.261 |
ld | +0.261 |
elephants | +0.248 |
Neg logit contributions | |
| -0.292 |
USS | -0.285 |
romeda | -0.284 |
Span | -0.281 |
Tempest | -0.278 |
Token | � |
Token ID | 564 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ijk | +0.535 |
�� | +0.510 |
ruct | +0.475 |
ld | +0.471 |
elephants | +0.444 |
Neg logit contributions | |
| -0.647 |
USS | -0.625 |
romeda | -0.622 |
Span | -0.621 |
Tempest | -0.613 |
Token | Tab |
Token ID | 16904 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
| +0.443 |
USS | +0.426 |
romeda | +0.423 |
Span | +0.423 |
Tempest | +0.417 |
Neg logit contributions | |
ijk | -0.452 |
�� | -0.434 |
ruct | -0.407 |
ld | -0.404 |
elephants | -0.383 |
Token | riz |
Token ID | 47847 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
ijk | +0.248 |
�� | +0.235 |
ruct | +0.225 |
ld | +0.224 |
phe | +0.211 |
Neg logit contributions | |
| -0.225 |
USS | -0.218 |
romeda | -0.215 |
Span | -0.215 |
Tempest | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
| +0.535 |
Span | +0.504 |
USS | +0.502 |
Tempest | +0.495 |
romeda | +0.494 |
Neg logit contributions | |
ijk | -0.568 |
�� | -0.549 |
ruct | -0.514 |
ld | -0.507 |
elephants | -0.487 |
Token | Yaz |
Token ID | 35856 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ijk | +0.058 |
�� | +0.055 |
ruct | +0.052 |
ld | +0.051 |
elephants | +0.049 |
Neg logit contributions | |
| -0.056 |
USS | -0.054 |
romeda | -0.054 |
Span | -0.054 |
Tempest | -0.053 |
Token | d |
Token ID | 67 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ijk | +0.241 |
�� | +0.227 |
ruct | +0.212 |
ld | +0.211 |
elephants | +0.196 |
Neg logit contributions | |
| -0.336 |
USS | -0.327 |
romeda | -0.325 |
Span | -0.324 |
Tempest | -0.320 |
Token | and |
Token ID | 290 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ijk | +0.260 |
�� | +0.249 |
ruct | +0.234 |
ld | +0.232 |
elephants | +0.219 |
Neg logit contributions | |
| -0.271 |
USS | -0.261 |
romeda | -0.259 |
Span | -0.259 |
Tempest | -0.256 |
Token | Shir |
Token ID | 21972 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
| +0.141 |
USS | +0.136 |
Span | +0.135 |
romeda | +0.135 |
Tempest | +0.133 |
Neg logit contributions | |
ijk | -0.148 |
�� | -0.142 |
ruct | -0.133 |
ld | -0.132 |
elephants | -0.126 |
Token | az |
Token ID | 1031 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
| +0.582 |
USS | +0.562 |
romeda | +0.560 |
Span | +0.557 |
Tempest | +0.548 |
Neg logit contributions | |
ijk | -0.616 |
�� | -0.586 |
ruct | -0.555 |
ld | -0.553 |
elephants | -0.521 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
| +0.537 |
USS | +0.508 |
Span | +0.508 |
romeda | +0.505 |
Tempest | +0.501 |
Neg logit contributions | |
ijk | -0.573 |
�� | -0.552 |
ruct | -0.518 |
ld | -0.513 |
elephants | -0.488 |
Token | where |
Token ID | 810 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
| +0.898 |
USS | +0.860 |
Span | +0.857 |
romeda | +0.853 |
Tempest | +0.846 |
Neg logit contributions | |
ijk | -0.842 |
�� | -0.807 |
ruct | -0.752 |
ld | -0.745 |
phe | -0.706 |
Token | protesters |
Token ID | 9584 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
| +0.484 |
USS | +0.469 |
romeda | +0.467 |
Span | +0.465 |
Tempest | +0.459 |
Neg logit contributions | |
ijk | -0.430 |
�� | -0.409 |
ruct | -0.383 |
ld | -0.381 |
elephants | -0.360 |
Token | ( |
Token ID | 357 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
| +0.346 |
USS | +0.330 |
Span | +0.329 |
romeda | +0.328 |
Tempest | +0.323 |
Neg logit contributions | |
ijk | -0.394 |
�� | -0.380 |
ruct | -0.357 |
ld | -0.353 |
elephants | -0.337 |
Token | This |
Token ID | 1212 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
| +0.716 |
USS | +0.690 |
romeda | +0.686 |
Span | +0.684 |
Tempest | +0.675 |
Neg logit contributions | |
ijk | -0.683 |
�� | -0.653 |
ruct | -0.612 |
ld | -0.607 |
elephants | -0.575 |
Token | is |
Token ID | 318 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
| +1.144 |
Span | +1.092 |
USS | +1.092 |
romeda | +1.086 |
Tempest | +1.080 |
Neg logit contributions | |
ijk | -1.117 |
�� | -1.076 |
ruct | -1.004 |
ld | -0.989 |
elephants | -0.940 |
Token | an |
Token ID | 281 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
| +0.727 |
USS | +0.700 |
romeda | +0.696 |
Span | +0.695 |
Tempest | +0.687 |
Neg logit contributions | |
ijk | -0.706 |
�� | -0.676 |
ruct | -0.633 |
ld | -0.628 |
elephants | -0.594 |
Token | old |
Token ID | 1468 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ijk | +0.001 |
�� | +0.001 |
ruct | +0.001 |
ld | +0.001 |
elephants | +0.001 |
Neg logit contributions | |
| -0.001 |
USS | -0.001 |
romeda | -0.001 |
Span | -0.001 |
Tempest | -0.001 |
Token | one |
Token ID | 530 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
ijk | +0.539 |
�� | +0.514 |
ruct | +0.482 |
ld | +0.481 |
elephants | +0.455 |
Neg logit contributions | |
| -0.555 |
USS | -0.537 |
romeda | -0.535 |
Span | -0.531 |
Tempest | -0.522 |
Token | !) |
Token ID | 8133 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
| +0.609 |
USS | +0.583 |
romeda | +0.581 |
Span | +0.579 |
Tempest | +0.571 |
Neg logit contributions | |
ijk | -0.641 |
�� | -0.616 |
ruct | -0.579 |
ld | -0.573 |
elephants | -0.545 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
| +0.463 |
USS | +0.446 |
romeda | +0.443 |
Span | +0.440 |
Tempest | +0.433 |
Neg logit contributions | |
ijk | -0.591 |
�� | -0.567 |
ruct | -0.537 |
ld | -0.535 |
elephants | -0.510 |
Token |
|
Token ID | 198 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
| +0.272 |
romeda | +0.267 |
USS | +0.265 |
Span | +0.262 |
Tempest | +0.258 |
Neg logit contributions | |
ijk | -0.362 |
�� | -0.337 |
ld | -0.331 |
ruct | -0.330 |
phe | -0.311 |
Token | Speaking |
Token ID | 13887 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
| +0.513 |
USS | +0.494 |
romeda | +0.489 |
Span | +0.489 |
Tempest | +0.481 |
Neg logit contributions | |
ijk | -0.588 |
�� | -0.564 |
ruct | -0.532 |
ld | -0.528 |
elephants | -0.503 |
Token | of |
Token ID | 286 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
| +0.076 |
Span | +0.072 |
USS | +0.072 |
romeda | +0.071 |
Tempest | +0.071 |
Neg logit contributions | |
ijk | -0.096 |
�� | -0.093 |
ruct | -0.088 |
ld | -0.087 |
phe | -0.083 |
Token | � |
Token ID | 134 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
| +0.782 |
USS | +0.751 |
Span | +0.746 |
romeda | +0.744 |
Tempest | +0.735 |
Neg logit contributions | |
ijk | -0.831 |
�� | -0.798 |
ruct | -0.751 |
ld | -0.743 |
elephants | -0.706 |
Token | � |
Token ID | 119 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
| +0.240 |
USS | +0.233 |
romeda | +0.231 |
Span | +0.231 |
Tempest | +0.228 |
Neg logit contributions | |
ijk | -0.180 |
�� | -0.171 |
ruct | -0.159 |
ld | -0.157 |
elephants | -0.148 |
Token | i |
Token ID | 72 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
| +0.374 |
USS | +0.362 |
romeda | +0.360 |
Span | +0.359 |
Tempest | +0.355 |
Neg logit contributions | |
ijk | -0.310 |
�� | -0.296 |
ruct | -0.275 |
ld | -0.273 |
elephants | -0.258 |
Token | pa |
Token ID | 14187 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
ijk | +0.074 |
�� | +0.071 |
ruct | +0.067 |
ld | +0.066 |
elephants | +0.063 |
Neg logit contributions | |
| -0.070 |
USS | -0.068 |
romeda | -0.067 |
Span | -0.067 |
Tempest | -0.066 |
Token | ia |
Token ID | 544 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
| +0.569 |
USS | +0.548 |
romeda | +0.544 |
Span | +0.544 |
Tempest | +0.536 |
Neg logit contributions | |
ijk | -0.576 |
�� | -0.552 |
ruct | -0.518 |
ld | -0.514 |
elephants | -0.487 |
Token | |
Token ID | 220 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ijk | +0.016 |
�� | +0.015 |
ruct | +0.014 |
ld | +0.014 |
elephants | +0.013 |
Neg logit contributions | |
| -0.014 |
USS | -0.014 |
romeda | -0.014 |
Span | -0.014 |
Tempest | -0.013 |
Token | � |
Token ID | 134 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
| +1.207 |
USS | +1.166 |
romeda | +1.155 |
Span | +1.151 |
Tempest | +1.141 |
Neg logit contributions | |
ijk | -1.006 |
�� | -0.961 |
ruct | -0.897 |
ld | -0.882 |
elephants | -0.845 |
Token | � |
Token ID | 119 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
| +1.362 |
USS | +1.315 |
romeda | +1.304 |
Span | +1.301 |
Tempest | +1.289 |
Neg logit contributions | |
ijk | -1.080 |
�� | -1.012 |
ruct | -0.954 |
ld | -0.943 |
phe | -0.891 |
Token | el |
Token ID | 417 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ijk | +0.162 |
�� | +0.155 |
ruct | +0.145 |
ld | +0.144 |
elephants | +0.136 |
Neg logit contributions | |
| -0.186 |
USS | -0.180 |
romeda | -0.179 |
Span | -0.179 |
Tempest | -0.176 |
Token | ua |
Token ID | 6413 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ijk | +0.386 |
�� | +0.365 |
ruct | +0.344 |
ld | +0.343 |
phe | +0.323 |
Neg logit contributions | |
| -0.406 |
USS | -0.393 |
romeda | -0.390 |
Span | -0.389 |
Tempest | -0.385 |
Token | ma |
Token ID | 17266 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
| +0.363 |
USS | +0.349 |
romeda | +0.347 |
Span | +0.347 |
Tempest | +0.342 |
Neg logit contributions | |
ijk | -0.393 |
�� | -0.377 |
ruct | -0.355 |
ld | -0.352 |
elephants | -0.334 |
Token | with |
Token ID | 351 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
| +0.603 |
USS | +0.580 |
romeda | +0.575 |
Span | +0.575 |
Tempest | +0.567 |
Neg logit contributions | |
ijk | -0.620 |
�� | -0.594 |
ruct | -0.558 |
ld | -0.554 |
elephants | -0.525 |
Token | the |
Token ID | 262 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
| +1.280 |
USS | +1.221 |
Span | +1.220 |
romeda | +1.209 |
Tempest | +1.200 |
Neg logit contributions | |
ijk | -1.387 |
�� | -1.336 |
ruct | -1.254 |
ld | -1.237 |
phe | -1.180 |
Token | Ch |
Token ID | 609 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ijk | +0.416 |
�� | +0.396 |
ruct | +0.374 |
ld | +0.374 |
elephants | +0.356 |
Neg logit contributions | |
| -0.382 |
USS | -0.370 |
romeda | -0.369 |
Span | -0.364 |
Tempest | -0.360 |
Token | ipp |
Token ID | 3974 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
ijk | +0.210 |
�� | +0.201 |
ruct | +0.190 |
ld | +0.189 |
phe | +0.179 |
Neg logit contributions | |
| -0.197 |
USS | -0.190 |
romeda | -0.189 |
Span | -0.188 |
Tempest | -0.186 |
Token | ew |
Token ID | 413 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ijk | +0.630 |
�� | +0.604 |
ruct | +0.558 |
ld | +0.551 |
elephants | +0.522 |
Neg logit contributions | |
| -0.799 |
USS | -0.772 |
Span | -0.768 |
romeda | -0.767 |
Tempest | -0.756 |
Token | as |
Token ID | 292 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
ijk | +0.571 |
�� | +0.548 |
ruct | +0.509 |
ld | +0.505 |
elephants | +0.475 |
Neg logit contributions | |
| -0.692 |
USS | -0.669 |
Span | -0.666 |
romeda | -0.665 |
Tempest | -0.657 |
Token | of |
Token ID | 286 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
| +0.487 |
USS | +0.467 |
Span | +0.466 |
romeda | +0.462 |
Tempest | +0.459 |
Neg logit contributions | |
ijk | -0.479 |
�� | -0.459 |
ruct | -0.430 |
ld | -0.426 |
phe | -0.403 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ijk | +0.436 |
�� | +0.416 |
ruct | +0.392 |
ld | +0.390 |
elephants | +0.370 |
Neg logit contributions | |
| -0.428 |
USS | -0.414 |
romeda | -0.413 |
Span | -0.409 |
Tempest | -0.403 |
Token | Thames |
Token ID | 42521 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ijk | +0.100 |
�� | +0.095 |
ruct | +0.090 |
ld | +0.090 |
elephants | +0.085 |
Neg logit contributions | |
| -0.094 |
USS | -0.091 |
romeda | -0.091 |
Span | -0.090 |
Tempest | -0.089 |
Token | First |
Token ID | 3274 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
ijk | +0.907 |
�� | +0.862 |
ruct | +0.808 |
ld | +0.806 |
elephants | +0.760 |
Neg logit contributions | |
| -0.976 |
USS | -0.951 |
romeda | -0.949 |
Span | -0.935 |
Tempest | -0.923 |
Token | Nation |
Token ID | 8741 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
| +0.483 |
USS | +0.463 |
Span | +0.461 |
romeda | +0.457 |
Tempest | +0.454 |
Neg logit contributions | |
ijk | -0.512 |
�� | -0.493 |
ruct | -0.461 |
ld | -0.457 |
phe | -0.436 |
Token | owner |
Token ID | 4870 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
| +0.955 |
USS | +0.919 |
Span | +0.914 |
romeda | +0.912 |
Tempest | +0.902 |
Neg logit contributions | |
ijk | -0.868 |
�� | -0.831 |
ruct | -0.775 |
ld | -0.769 |
elephants | -0.726 |
Token | . |
Token ID | 13 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
| +0.854 |
Span | +0.817 |
USS | +0.813 |
romeda | +0.805 |
Tempest | +0.801 |
Neg logit contributions | |
ijk | -0.914 |
�� | -0.876 |
ruct | -0.824 |
ld | -0.809 |
phe | -0.778 |
Token | Given |
Token ID | 11259 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
| +0.502 |
USS | +0.482 |
romeda | +0.478 |
Span | +0.478 |
Tempest | +0.470 |
Neg logit contributions | |
ijk | -0.608 |
�� | -0.584 |
ruct | -0.551 |
ld | -0.548 |
elephants | -0.522 |
Token | Fab |
Token ID | 14236 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ijk | +0.782 |
�� | +0.750 |
ruct | +0.704 |
ld | +0.701 |
elephants | +0.664 |
Neg logit contributions | |
| -0.764 |
USS | -0.738 |
romeda | -0.734 |
Span | -0.730 |
Tempest | -0.721 |
Token | io |
Token ID | 952 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ijk | +0.014 |
�� | +0.013 |
ruct | +0.012 |
ld | +0.012 |
elephants | +0.011 |
Neg logit contributions | |
| -0.015 |
USS | -0.014 |
romeda | -0.014 |
Span | -0.014 |
Tempest | -0.014 |
Token | Cape |
Token ID | 15725 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ijk | +0.082 |
�� | +0.077 |
ruct | +0.071 |
ld | +0.070 |
elephants | +0.065 |
Neg logit contributions | |
| -0.130 |
USS | -0.126 |
Span | -0.126 |
romeda | -0.125 |
Tempest | -0.124 |
Token | llo |
Token ID | 18798 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
| +0.236 |
USS | +0.230 |
Span | +0.229 |
romeda | +0.228 |
Tempest | +0.227 |
Neg logit contributions | |
ijk | -0.113 |
�� | -0.107 |
ruct | -0.095 |
ld | -0.094 |
elephants | -0.087 |
Token | 's |
Token ID | 338 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ijk | +0.412 |
�� | +0.396 |
ruct | +0.368 |
ld | +0.362 |
phe | +0.347 |
Neg logit contributions | |
| -0.430 |
Span | -0.410 |
USS | -0.410 |
romeda | -0.406 |
Tempest | -0.402 |
Token | recent |
Token ID | 2274 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
| +0.307 |
USS | +0.297 |
romeda | +0.295 |
Span | +0.294 |
Tempest | +0.290 |
Neg logit contributions | |
ijk | -0.285 |
�� | -0.272 |
ruct | -0.255 |
ld | -0.254 |
elephants | -0.240 |
Token | experience |
Token ID | 1998 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
| +0.943 |
USS | +0.909 |
romeda | +0.903 |
Span | +0.902 |
Tempest | +0.890 |
Neg logit contributions | |
ijk | -0.892 |
�� | -0.853 |
ruct | -0.799 |
ld | -0.794 |
elephants | -0.750 |
Token | with |
Token ID | 351 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
| +0.372 |
Span | +0.354 |
USS | +0.353 |
romeda | +0.349 |
Tempest | +0.347 |
Neg logit contributions | |
ijk | -0.410 |
�� | -0.395 |
ruct | -0.371 |
ld | -0.365 |
phe | -0.350 |
Token | going |
Token ID | 1016 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
ijk | +0.560 |
�� | +0.534 |
ruct | +0.503 |
ld | +0.501 |
elephants | +0.474 |
Neg logit contributions | |
| -0.593 |
USS | -0.574 |
romeda | -0.570 |
Span | -0.568 |
Tempest | -0.560 |
Token | to |
Token ID | 284 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
ijk | +0.586 |
�� | +0.560 |
ruct | +0.525 |
ld | +0.522 |
elephants | +0.494 |
Neg logit contributions | |
| -0.618 |
USS | -0.596 |
romeda | -0.593 |
Span | -0.591 |
Tempest | -0.583 |
Token | explode |
Token ID | 22818 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ijk | +0.059 |
�� | +0.056 |
ruct | +0.053 |
ld | +0.052 |
elephants | +0.050 |
Neg logit contributions | |
| -0.063 |
USS | -0.061 |
romeda | -0.061 |
Span | -0.061 |
Tempest | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ijk | +0.163 |
�� | +0.156 |
ruct | +0.147 |
ld | +0.146 |
elephants | +0.139 |
Neg logit contributions | |
| -0.146 |
USS | -0.140 |
romeda | -0.139 |
Span | -0.139 |
Tempest | -0.137 |
Token | These |
Token ID | 2312 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
| +0.366 |
USS | +0.354 |
romeda | +0.354 |
Span | +0.346 |
Tempest | +0.343 |
Neg logit contributions | |
ijk | -0.447 |
�� | -0.428 |
ruct | -0.408 |
ld | -0.406 |
phe | -0.385 |
Token | two |
Token ID | 734 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
| +0.825 |
USS | +0.793 |
Span | +0.789 |
romeda | +0.788 |
Tempest | +0.781 |
Neg logit contributions | |
ijk | -0.788 |
�� | -0.756 |
ruct | -0.705 |
ld | -0.697 |
phe | -0.662 |
Token | are |
Token ID | 389 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
| +1.941 |
USS | +1.862 |
Span | +1.858 |
romeda | +1.851 |
Tempest | +1.831 |
Neg logit contributions | |
ijk | -1.979 |
�� | -1.906 |
ruct | -1.781 |
ld | -1.753 |
phe | -1.674 |
Token | going |
Token ID | 1016 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
| +0.424 |
USS | +0.409 |
romeda | +0.406 |
Span | +0.405 |
Tempest | +0.399 |
Neg logit contributions | |
ijk | -0.437 |
�� | -0.418 |
ruct | -0.394 |
ld | -0.392 |
elephants | -0.373 |
Token | to |
Token ID | 284 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
| +0.472 |
USS | +0.453 |
Span | +0.447 |
Tempest | +0.446 |
romeda | +0.446 |
Neg logit contributions | |
ijk | -0.494 |
�� | -0.470 |
ruct | -0.444 |
ld | -0.436 |
phe | -0.418 |
Token | d |
Token ID | 288 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
| +0.780 |
USS | +0.754 |
romeda | +0.749 |
Span | +0.747 |
Tempest | +0.737 |
Neg logit contributions | |
ijk | -0.742 |
�� | -0.708 |
ruct | -0.665 |
ld | -0.661 |
elephants | -0.626 |
Token | uke |
Token ID | 4649 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
| +0.991 |
USS | +0.958 |
romeda | +0.952 |
Span | +0.950 |
Tempest | +0.937 |
Neg logit contributions | |
ijk | -0.809 |
�� | -0.775 |
ruct | -0.718 |
ld | -0.711 |
elephants | -0.672 |
Token | cy |
Token ID | 948 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ijk | +0.911 |
�� | +0.869 |
ruct | +0.820 |
ld | +0.817 |
elephants | +0.772 |
Neg logit contributions | |
| -0.880 |
USS | -0.851 |
romeda | -0.847 |
Span | -0.842 |
Tempest | -0.831 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
| +0.113 |
USS | +0.109 |
romeda | +0.108 |
Span | +0.108 |
Tempest | +0.106 |
Neg logit contributions | |
ijk | -0.117 |
�� | -0.112 |
ruct | -0.105 |
ld | -0.105 |
elephants | -0.099 |
Token | The |
Token ID | 383 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
ijk | +0.906 |
�� | +0.861 |
ruct | +0.823 |
ld | +0.821 |
phe | +0.770 |
Neg logit contributions | |
| -0.812 |
romeda | -0.792 |
USS | -0.784 |
Span | -0.776 |
Tempest | -0.768 |
Token | Devils |
Token ID | 26199 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ijk | +0.530 |
�� | +0.507 |
ruct | +0.478 |
ld | +0.475 |
elephants | +0.450 |
Neg logit contributions | |
| -0.513 |
USS | -0.496 |
romeda | -0.493 |
Span | -0.490 |
Tempest | -0.484 |
Token | wrap |
Token ID | 14441 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ijk | +0.993 |
�� | +0.937 |
ld | +0.893 |
ruct | +0.892 |
elephants | +0.837 |
Neg logit contributions | |
| -1.044 |
USS | -1.017 |
romeda | -1.015 |
Span | -1.007 |
Tempest | -0.993 |
Token | up |
Token ID | 510 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
| +0.101 |
USS | +0.096 |
Span | +0.095 |
romeda | +0.095 |
Tempest | +0.094 |
Neg logit contributions | |
ijk | -0.143 |
�� | -0.138 |
ruct | -0.130 |
ld | -0.129 |
phe | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
| +2.108 |
USS | +2.020 |
Span | +2.012 |
Tempest | +1.989 |
romeda | +1.980 |
Neg logit contributions | |
ijk | -1.736 |
�� | -1.691 |
ruct | -1.534 |
ld | -1.510 |
phe | -1.442 |
Token | home |
Token ID | 1363 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ijk | +0.936 |
�� | +0.885 |
ld | +0.841 |
ruct | +0.839 |
elephants | +0.787 |
Neg logit contributions | |
| -1.032 |
romeda | -1.002 |
USS | -1.000 |
Span | -0.988 |
Tempest | -0.978 |
Token | - |
Token ID | 12 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
ijk | +0.604 |
�� | +0.578 |
ruct | +0.548 |
ld | +0.546 |
elephants | +0.517 |
Neg logit contributions | |
| -0.520 |
USS | -0.500 |
romeda | -0.499 |
Span | -0.495 |
Tempest | -0.489 |
Token | and |
Token ID | 392 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
| +0.483 |
USS | +0.469 |
romeda | +0.467 |
Span | +0.465 |
Tempest | +0.460 |
Neg logit contributions | |
ijk | -0.313 |
�� | -0.295 |
ruct | -0.273 |
ld | -0.270 |
elephants | -0.251 |
Token | - |
Token ID | 12 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ijk | +0.175 |
ld | +0.160 |
�� | +0.160 |
ruct | +0.156 |
phe | +0.148 |
Neg logit contributions | |
| -0.175 |
USS | -0.174 |
Span | -0.171 |
Tempest | -0.168 |
romeda | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
| +0.392 |
Span | +0.370 |
USS | +0.370 |
romeda | +0.369 |
Tempest | +0.364 |
Neg logit contributions | |
ijk | -0.451 |
�� | -0.435 |
ruct | -0.408 |
ld | -0.404 |
elephants | -0.385 |
Token | The |
Token ID | 383 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ijk | +0.309 |
�� | +0.291 |
ruct | +0.283 |
ld | +0.282 |
phe | +0.267 |
Neg logit contributions | |
| -0.251 |
USS | -0.249 |
romeda | -0.248 |
Span | -0.240 |
Tempest | -0.237 |
Token | book |
Token ID | 1492 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
| +0.020 |
USS | +0.020 |
romeda | +0.020 |
Span | +0.020 |
Tempest | +0.019 |
Neg logit contributions | |
ijk | -0.019 |
�� | -0.019 |
ruct | -0.017 |
ld | -0.017 |
elephants | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ijk | +0.068 |
�� | +0.065 |
ruct | +0.061 |
ld | +0.061 |
elephants | +0.058 |
Neg logit contributions | |
| -0.069 |
USS | -0.066 |
romeda | -0.066 |
Span | -0.066 |
Tempest | -0.065 |
Token | sort |
Token ID | 3297 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
| +0.387 |
USS | +0.372 |
romeda | +0.370 |
Span | +0.370 |
Tempest | +0.365 |
Neg logit contributions | |
ijk | -0.373 |
�� | -0.357 |
ruct | -0.334 |
ld | -0.331 |
phe | -0.314 |
Token | of |
Token ID | 286 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
| +0.081 |
USS | +0.078 |
romeda | +0.077 |
Span | +0.077 |
Tempest | +0.076 |
Neg logit contributions | |
ijk | -0.099 |
�� | -0.095 |
ruct | -0.089 |
ld | -0.089 |
elephants | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
| +2.182 |
Span | +2.085 |
romeda | +2.071 |
USS | +2.064 |
Tempest | +2.064 |
Neg logit contributions | |
ijk | -2.032 |
�� | -1.960 |
ruct | -1.813 |
ld | -1.782 |
phe | -1.705 |
Token | stop |
Token ID | 2245 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
| +1.570 |
Span | +1.503 |
USS | +1.500 |
romeda | +1.492 |
Tempest | +1.487 |
Neg logit contributions | |
ijk | -1.436 |
�� | -1.377 |
ruct | -1.284 |
ld | -1.263 |
phe | -1.200 |
Token | along |
Token ID | 1863 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
| +0.758 |
USS | +0.726 |
Span | +0.725 |
romeda | +0.721 |
Tempest | +0.714 |
Neg logit contributions | |
ijk | -0.660 |
�� | -0.631 |
ruct | -0.589 |
ld | -0.583 |
elephants | -0.552 |
Token | the |
Token ID | 262 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
ijk | +0.472 |
�� | +0.451 |
ruct | +0.423 |
ld | +0.421 |
elephants | +0.399 |
Neg logit contributions | |
| -0.475 |
USS | -0.459 |
romeda | -0.456 |
Span | -0.454 |
Tempest | -0.448 |
Token | way |
Token ID | 835 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
| +0.034 |
USS | +0.033 |
romeda | +0.033 |
Span | +0.033 |
Tempest | +0.032 |
Neg logit contributions | |
ijk | -0.037 |
�� | -0.035 |
ruct | -0.033 |
ld | -0.033 |
elephants | -0.031 |
Token | discuss |
Token ID | 2112 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ijk | +0.107 |
�� | +0.100 |
ld | +0.096 |
ruct | +0.096 |
elephants | +0.090 |
Neg logit contributions | |
| -0.108 |
USS | -0.106 |
romeda | -0.105 |
Span | -0.104 |
Tempest | -0.103 |
Token | possible |
Token ID | 1744 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
| +0.292 |
romeda | +0.284 |
USS | +0.284 |
Span | +0.282 |
Tempest | +0.278 |
Neg logit contributions | |
ijk | -0.284 |
�� | -0.271 |
ruct | -0.256 |
ld | -0.256 |
elephants | -0.244 |
Token | post |
Token ID | 1281 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
| +1.123 |
USS | +1.091 |
romeda | +1.089 |
Span | +1.083 |
Tempest | +1.070 |
Neg logit contributions | |
ijk | -1.038 |
�� | -0.988 |
ruct | -0.929 |
ld | -0.928 |
elephants | -0.878 |
Token | - |
Token ID | 12 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
| +0.410 |
USS | +0.394 |
romeda | +0.390 |
Span | +0.389 |
Tempest | +0.383 |
Neg logit contributions | |
ijk | -0.475 |
�� | -0.456 |
ruct | -0.429 |
ld | -0.425 |
phe | -0.405 |
Token | Brexit |
Token ID | 40730 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
| +0.533 |
USS | +0.511 |
romeda | +0.511 |
Span | +0.511 |
Tempest | +0.504 |
Neg logit contributions | |
ijk | -0.602 |
�� | -0.576 |
ruct | -0.545 |
ld | -0.543 |
phe | -0.513 |
Token | trade |
Token ID | 3292 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
| +1.442 |
USS | +1.397 |
romeda | +1.391 |
Span | +1.387 |
Tempest | +1.371 |
Neg logit contributions | |
ijk | -1.287 |
�� | -1.225 |
ruct | -1.150 |
ld | -1.143 |
elephants | -1.079 |
Token | ties |
Token ID | 8470 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
| +2.145 |
USS | +2.070 |
romeda | +2.054 |
Span | +2.048 |
Tempest | +2.022 |
Neg logit contributions | |
ijk | -1.731 |
�� | -1.652 |
ruct | -1.532 |
ld | -1.518 |
phe | -1.434 |
Token | . |
Token ID | 13 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
| +0.236 |
USS | +0.227 |
Span | +0.224 |
romeda | +0.224 |
Tempest | +0.221 |
Neg logit contributions | |
ijk | -0.263 |
�� | -0.253 |
ruct | -0.238 |
ld | -0.236 |
phe | -0.224 |
Token |
|
Token ID | 198 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
| +0.282 |
USS | +0.268 |
Span | +0.265 |
romeda | +0.263 |
Tempest | +0.260 |
Neg logit contributions | |
ijk | -0.426 |
�� | -0.412 |
ruct | -0.389 |
ld | -0.387 |
elephants | -0.372 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ijk | +0.080 |
ld | +0.074 |
�� | +0.073 |
ruct | +0.073 |
—- | +0.069 |
Neg logit contributions | |
romeda | -0.063 |
| -0.062 |
USS | -0.062 |
Span | -0.061 |
Tempest | -0.060 |
Token | On |
Token ID | 2202 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ijk | +0.378 |
�� | +0.360 |
ld | +0.343 |
ruct | +0.341 |
phe | +0.321 |
Neg logit contributions | |
| -0.363 |
romeda | -0.355 |
Span | -0.351 |
Tempest | -0.347 |
USS | -0.346 |
Token | ! |
Token ID | 0 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ijk | +0.819 |
�� | +0.774 |
ruct | +0.739 |
ld | +0.731 |
elephants | +0.695 |
Neg logit contributions | |
| -0.751 |
USS | -0.732 |
romeda | -0.726 |
Span | -0.720 |
Tempest | -0.709 |
Token | Y |
Token ID | 575 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
| +0.122 |
USS | +0.119 |
romeda | +0.118 |
Span | +0.117 |
Tempest | +0.114 |
Neg logit contributions | |
ijk | -0.157 |
�� | -0.149 |
ruct | -0.143 |
ld | -0.143 |
phe | -0.135 |
Token | ay |
Token ID | 323 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ijk | +0.396 |
�� | +0.375 |
ruct | +0.352 |
ld | +0.350 |
elephants | +0.329 |
Neg logit contributions | |
| -0.463 |
USS | -0.447 |
romeda | -0.445 |
Span | -0.444 |
Tempest | -0.438 |
Token | ! |
Token ID | 0 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
| +0.546 |
USS | +0.524 |
romeda | +0.521 |
Span | +0.518 |
Tempest | +0.514 |
Neg logit contributions | |
ijk | -0.686 |
�� | -0.663 |
ruct | -0.624 |
ld | -0.618 |
phe | -0.591 |
Token | Back |
Token ID | 5157 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
| +0.791 |
USS | +0.760 |
romeda | +0.755 |
Span | +0.751 |
Tempest | +0.738 |
Neg logit contributions | |
ijk | -1.074 |
�� | -1.031 |
ruct | -0.980 |
ld | -0.975 |
elephants | -0.930 |
Token | ers |
Token ID | 364 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
| +0.809 |
USS | +0.785 |
romeda | +0.780 |
Span | +0.776 |
Tempest | +0.767 |
Neg logit contributions | |
ijk | -0.844 |
�� | -0.805 |
ruct | -0.761 |
ld | -0.757 |
elephants | -0.716 |
Token | outside |
Token ID | 2354 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
| +3.092 |
USS | +2.932 |
Span | +2.924 |
romeda | +2.918 |
Tempest | +2.905 |
Neg logit contributions | |
ijk | -3.456 |
�� | -3.376 |
ruct | -3.119 |
ld | -3.083 |
elephants | -2.960 |
Token | of |
Token ID | 286 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
| +0.679 |
USS | +0.654 |
romeda | +0.645 |
Span | +0.645 |
Tempest | +0.637 |
Neg logit contributions | |
ijk | -0.779 |
�� | -0.748 |
ruct | -0.704 |
ld | -0.700 |
elephants | -0.666 |
Token | The |
Token ID | 383 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
| +0.319 |
USS | +0.307 |
romeda | +0.307 |
Span | +0.305 |
Tempest | +0.301 |
Neg logit contributions | |
ijk | -0.339 |
�� | -0.325 |
ruct | -0.306 |
ld | -0.305 |
elephants | -0.289 |
Token | United |
Token ID | 1578 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ijk | +0.382 |
�� | +0.369 |
ruct | +0.352 |
ld | +0.351 |
elephants | +0.336 |
Neg logit contributions | |
| -0.203 |
romeda | -0.194 |
USS | -0.193 |
Span | -0.191 |
Tempest | -0.187 |
Token | States |
Token ID | 1829 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
| +0.019 |
romeda | +0.018 |
USS | +0.018 |
Span | +0.018 |
Tempest | +0.018 |
Neg logit contributions | |
ijk | -0.019 |
�� | -0.018 |
ruct | -0.017 |
ld | -0.017 |
elephants | -0.016 |