Token | reading |
Token ID | 3555 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
PASS | +0.043 |
Musk | +0.041 |
RIS | +0.039 |
FISA | +0.039 |
Route | +0.038 |
Neg logit contributions | |
sterdam | -0.060 |
anco | -0.060 |
ldom | -0.057 |
apest | -0.054 |
merce | -0.054 |
Token | about |
Token ID | 546 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
sterdam | +0.339 |
anco | +0.338 |
ldom | +0.323 |
apest | +0.307 |
merce | +0.305 |
Neg logit contributions | |
PASS | -0.233 |
Musk | -0.220 |
RIS | -0.211 |
FISA | -0.209 |
Route | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
PASS | +0.534 |
Musk | +0.511 |
RIS | +0.488 |
FISA | +0.484 |
Route | +0.476 |
Neg logit contributions | |
sterdam | -0.761 |
anco | -0.758 |
ldom | -0.727 |
apest | -0.691 |
merce | -0.688 |
Token | real |
Token ID | 1103 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
sterdam | +0.001 |
anco | +0.001 |
ldom | +0.001 |
apest | +0.001 |
merce | +0.001 |
Neg logit contributions | |
PASS | -0.001 |
Musk | -0.001 |
RIS | -0.001 |
FISA | -0.001 |
Route | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
sterdam | +0.155 |
anco | +0.154 |
ldom | +0.147 |
apest | +0.139 |
merce | +0.138 |
Neg logit contributions | |
PASS | -0.129 |
Musk | -0.123 |
RIS | -0.118 |
FISA | -0.117 |
Route | -0.115 |
Token | life |
Token ID | 6042 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
PASS | +0.318 |
Musk | +0.302 |
RIS | +0.290 |
FISA | +0.288 |
Route | +0.282 |
Neg logit contributions | |
sterdam | -0.418 |
anco | -0.417 |
ldom | -0.399 |
apest | -0.378 |
merce | -0.376 |
Token | Barbie |
Token ID | 46829 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Musk | +4.172 |
PASS | +4.164 |
FISA | +3.987 |
RIS | +3.983 |
Route | +3.901 |
Neg logit contributions | |
anco | -4.802 |
sterdam | -4.778 |
ldom | -4.613 |
merce | -4.365 |
apest | -4.327 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
PASS | +1.290 |
Musk | +1.250 |
RIS | +1.195 |
FISA | +1.188 |
Route | +1.171 |
Neg logit contributions | |
sterdam | -1.543 |
anco | -1.536 |
ldom | -1.467 |
apest | -1.389 |
merce | -1.371 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
PASS | +0.837 |
Musk | +0.806 |
RIS | +0.772 |
FISA | +0.767 |
Route | +0.753 |
Neg logit contributions | |
sterdam | -1.065 |
anco | -1.061 |
ldom | -1.013 |
apest | -0.960 |
merce | -0.952 |
Token | I |
Token ID | 314 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
PASS | +0.009 |
Musk | +0.009 |
RIS | +0.008 |
FISA | +0.008 |
Route | +0.008 |
Neg logit contributions | |
sterdam | -0.014 |
anco | -0.014 |
ldom | -0.013 |
apest | -0.012 |
merce | -0.012 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
PASS | +0.445 |
Musk | +0.425 |
RIS | +0.409 |
FISA | +0.405 |
Route | +0.398 |
Neg logit contributions | |
sterdam | -0.562 |
anco | -0.558 |
ldom | -0.534 |
apest | -0.506 |
merce | -0.503 |
Token | From |
Token ID | 4863 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
sterdam | +0.298 |
anco | +0.297 |
ldom | +0.283 |
apest | +0.267 |
merce | +0.266 |
Neg logit contributions | |
PASS | -0.261 |
Musk | -0.248 |
RIS | -0.239 |
FISA | -0.237 |
Route | -0.233 |
Token | : |
Token ID | 25 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
sterdam | +0.374 |
anco | +0.372 |
ldom | +0.356 |
apest | +0.339 |
merce | +0.337 |
Neg logit contributions | |
PASS | -0.273 |
Musk | -0.261 |
RIS | -0.250 |
FISA | -0.248 |
Route | -0.243 |
Token | A |
Token ID | 317 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
PASS | +0.291 |
Musk | +0.279 |
RIS | +0.267 |
FISA | +0.265 |
Route | +0.260 |
Neg logit contributions | |
sterdam | -0.385 |
anco | -0.382 |
ldom | -0.367 |
apest | -0.348 |
merce | -0.346 |
Token | Long |
Token ID | 5882 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
sterdam | +0.928 |
anco | +0.925 |
ldom | +0.882 |
apest | +0.830 |
merce | +0.825 |
Neg logit contributions | |
PASS | -0.837 |
Musk | -0.798 |
RIS | -0.768 |
FISA | -0.762 |
Route | -0.749 |
Token | - |
Token ID | 12 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
PASS | +0.320 |
Musk | +0.304 |
RIS | +0.291 |
FISA | +0.289 |
Route | +0.284 |
Neg logit contributions | |
sterdam | -0.434 |
anco | -0.433 |
ldom | -0.414 |
apest | -0.393 |
merce | -0.391 |
Token | Time |
Token ID | 7575 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
PASS | +0.683 |
Musk | +0.648 |
RIS | +0.620 |
FISA | +0.616 |
Route | +0.607 |
Neg logit contributions | |
sterdam | -0.868 |
anco | -0.866 |
ldom | -0.826 |
apest | -0.785 |
merce | -0.779 |
Token | Real |
Token ID | 6416 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Musk | +3.398 |
PASS | +3.380 |
FISA | +3.210 |
RIS | +3.154 |
ACC | +3.152 |
Neg logit contributions | |
sterdam | -5.257 |
anco | -5.179 |
ldom | -5.032 |
merce | -4.870 |
apest | -4.795 |
Token | ist |
Token ID | 396 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
sterdam | +0.562 |
anco | +0.561 |
ldom | +0.537 |
apest | +0.509 |
merce | +0.504 |
Neg logit contributions | |
PASS | -0.407 |
Musk | -0.383 |
RIS | -0.369 |
FISA | -0.365 |
Route | -0.357 |
Token | Reader |
Token ID | 25342 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
PASS | +0.691 |
Musk | +0.662 |
RIS | +0.633 |
FISA | +0.630 |
Route | +0.617 |
Neg logit contributions | |
sterdam | -0.935 |
anco | -0.931 |
ldom | -0.893 |
apest | -0.848 |
merce | -0.844 |
Token | [ |
Token ID | 685 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
PASS | +0.962 |
Musk | +0.928 |
RIS | +0.889 |
FISA | +0.886 |
Route | +0.867 |
Neg logit contributions | |
sterdam | -1.313 |
anco | -1.297 |
ldom | -1.254 |
apest | -1.193 |
merce | -1.192 |
Token | Email |
Token ID | 15333 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
sterdam | +2.027 |
anco | +2.026 |
ldom | +1.933 |
apest | +1.828 |
merce | +1.796 |
Neg logit contributions | |
PASS | -1.730 |
Musk | -1.663 |
RIS | -1.596 |
FISA | -1.592 |
Route | -1.562 |
Token | going |
Token ID | 1016 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
PASS | +1.222 |
Musk | +1.169 |
RIS | +1.126 |
FISA | +1.117 |
Route | +1.097 |
Neg logit contributions | |
sterdam | -1.479 |
anco | -1.473 |
ldom | -1.406 |
apest | -1.332 |
merce | -1.332 |
Token | to |
Token ID | 284 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
PASS | +0.124 |
Musk | +0.118 |
RIS | +0.113 |
FISA | +0.112 |
Route | +0.109 |
Neg logit contributions | |
sterdam | -0.177 |
anco | -0.176 |
ldom | -0.168 |
apest | -0.160 |
merce | -0.158 |
Token | be |
Token ID | 307 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
sterdam | +0.520 |
anco | +0.519 |
ldom | +0.496 |
apest | +0.475 |
merce | +0.469 |
Neg logit contributions | |
PASS | -0.336 |
Musk | -0.316 |
RIS | -0.301 |
FISA | -0.299 |
Route | -0.293 |
Token | real |
Token ID | 1103 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
sterdam | +0.786 |
anco | +0.784 |
ldom | +0.747 |
apest | +0.705 |
merce | +0.696 |
Neg logit contributions | |
PASS | -0.679 |
Musk | -0.644 |
RIS | -0.619 |
FISA | -0.616 |
Route | -0.604 |
Token | - |
Token ID | 12 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
sterdam | +0.565 |
anco | +0.563 |
ldom | +0.536 |
apest | +0.504 |
merce | +0.499 |
Neg logit contributions | |
PASS | -0.534 |
Musk | -0.509 |
RIS | -0.491 |
FISA | -0.488 |
Route | -0.479 |
Token | life |
Token ID | 6042 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
PASS | +0.216 |
Musk | +0.205 |
RIS | +0.197 |
FISA | +0.196 |
Route | +0.192 |
Neg logit contributions | |
sterdam | -0.292 |
anco | -0.291 |
ldom | -0.278 |
apest | -0.264 |
merce | -0.262 |
Token | pur |
Token ID | 1308 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
PASS | +4.018 |
Musk | +3.992 |
RIS | +3.832 |
FISA | +3.811 |
Route | +3.790 |
Neg logit contributions | |
anco | -4.414 |
sterdam | -4.387 |
ldom | -4.197 |
merce | -4.047 |
apest | -3.956 |
Token | ges |
Token ID | 3212 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
PASS | +2.309 |
Musk | +2.193 |
RIS | +2.099 |
FISA | +2.097 |
@# | +2.065 |
Neg logit contributions | |
anco | -2.862 |
sterdam | -2.861 |
ldom | -2.701 |
Indust | -2.616 |
merce | -2.590 |
Token | , |
Token ID | 11 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
PASS | +0.025 |
Musk | +0.024 |
RIS | +0.023 |
FISA | +0.022 |
Route | +0.022 |
Neg logit contributions | |
sterdam | -0.031 |
anco | -0.031 |
ldom | -0.029 |
apest | -0.028 |
merce | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
PASS | +0.060 |
Musk | +0.058 |
RIS | +0.055 |
FISA | +0.055 |
Route | +0.054 |
Neg logit contributions | |
sterdam | -0.070 |
anco | -0.070 |
ldom | -0.067 |
apest | -0.063 |
merce | -0.063 |
Token | they |
Token ID | 484 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
sterdam | +0.108 |
anco | +0.107 |
ldom | +0.103 |
apest | +0.097 |
merce | +0.097 |
Neg logit contributions | |
PASS | -0.082 |
Musk | -0.079 |
RIS | -0.075 |
FISA | -0.075 |
Route | -0.073 |
Token | M |
Token ID | 44 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
sterdam | +0.439 |
anco | +0.438 |
ldom | +0.420 |
apest | +0.399 |
merce | +0.396 |
Neg logit contributions | |
PASS | -0.295 |
Musk | -0.279 |
RIS | -0.267 |
FISA | -0.265 |
Route | -0.259 |
Token | FL |
Token ID | 3697 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
sterdam | +0.560 |
anco | +0.556 |
ldom | +0.532 |
apest | +0.502 |
merce | +0.501 |
Neg logit contributions | |
PASS | -0.515 |
Musk | -0.490 |
RIS | -0.472 |
FISA | -0.468 |
Route | -0.461 |
Token | Y |
Token ID | 56 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
PASS | +0.262 |
Musk | +0.247 |
RIS | +0.236 |
FISA | +0.234 |
Route | +0.230 |
Neg logit contributions | |
sterdam | -0.394 |
anco | -0.392 |
ldom | -0.377 |
apest | -0.359 |
merce | -0.357 |
Token | NN |
Token ID | 6144 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
sterdam | +1.314 |
anco | +1.312 |
ldom | +1.256 |
apest | +1.197 |
merce | +1.189 |
Neg logit contributions | |
PASS | -0.789 |
Musk | -0.748 |
RIS | -0.711 |
FISA | -0.708 |
Route | -0.690 |
Token | JR |
Token ID | 44817 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
sterdam | +0.155 |
anco | +0.154 |
ldom | +0.148 |
apest | +0.141 |
merce | +0.141 |
Neg logit contributions | |
PASS | -0.091 |
Musk | -0.085 |
RIS | -0.081 |
FISA | -0.080 |
Route | -0.079 |
Token | � |
Token ID | 8582 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
sterdam | +0.444 |
anco | +0.443 |
ldom | +0.425 |
apest | +0.405 |
merce | +0.403 |
Neg logit contributions | |
PASS | -0.269 |
Musk | -0.254 |
RIS | -0.242 |
FISA | -0.240 |
Route | -0.234 |
Token | � |
Token ID | 229 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
PASS | +3.665 |
Musk | +3.519 |
@# | +3.415 |
FISA | +3.377 |
RIS | +3.375 |
Neg logit contributions | |
sterdam | -4.547 |
anco | -4.378 |
ldom | -4.266 |
apest | -4.065 |
merce | -4.056 |
Token | � |
Token ID | 118 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
sterdam | +0.338 |
anco | +0.337 |
ldom | +0.319 |
apest | +0.299 |
merce | +0.296 |
Neg logit contributions | |
PASS | -0.384 |
Musk | -0.368 |
RIS | -0.356 |
FISA | -0.355 |
Route | -0.349 |
Token | � |
Token ID | 8582 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
anco | +2.099 |
sterdam | +2.093 |
ldom | +2.007 |
apest | +1.909 |
merce | +1.894 |
Neg logit contributions | |
PASS | -1.259 |
Musk | -1.197 |
RIS | -1.137 |
FISA | -1.128 |
Route | -1.102 |
Token | � |
Token ID | 229 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
PASS | +3.504 |
Musk | +3.391 |
@# | +3.314 |
FISA | +3.256 |
Route | +3.233 |
Neg logit contributions | |
sterdam | -4.506 |
anco | -4.275 |
ldom | -4.191 |
merce | -4.017 |
Indust | -3.967 |
Token | � |
Token ID | 116 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
sterdam | +0.465 |
anco | +0.463 |
ldom | +0.437 |
apest | +0.408 |
merce | +0.405 |
Neg logit contributions | |
PASS | -0.572 |
Musk | -0.550 |
RIS | -0.532 |
FISA | -0.530 |
Route | -0.522 |
Token | lf |
Token ID | 1652 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
PASS | +1.077 |
Musk | +1.010 |
RIS | +0.949 |
FISA | +0.947 |
Route | +0.923 |
Neg logit contributions | |
sterdam | -2.071 |
anco | -2.057 |
ldom | -1.972 |
merce | -1.898 |
apest | -1.894 |
Token | had |
Token ID | 550 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
PASS | +0.478 |
Musk | +0.457 |
RIS | +0.438 |
FISA | +0.436 |
Route | +0.428 |
Neg logit contributions | |
sterdam | -0.567 |
anco | -0.564 |
ldom | -0.538 |
apest | -0.510 |
merce | -0.507 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
PASS | +0.604 |
Musk | +0.576 |
RIS | +0.553 |
FISA | +0.548 |
Route | +0.537 |
Neg logit contributions | |
sterdam | -0.811 |
anco | -0.805 |
ldom | -0.769 |
apest | -0.733 |
merce | -0.730 |
Token | 190 |
Token ID | 19884 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
PASS | +0.177 |
Musk | +0.169 |
RIS | +0.163 |
FISA | +0.162 |
Route | +0.159 |
Neg logit contributions | |
sterdam | -0.190 |
anco | -0.189 |
ldom | -0.179 |
apest | -0.169 |
merce | -0.169 |
Token | - |
Token ID | 12 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
PASS | +0.408 |
Musk | +0.391 |
RIS | +0.370 |
FISA | +0.369 |
Route | +0.366 |
Neg logit contributions | |
sterdam | -0.595 |
anco | -0.586 |
ldom | -0.560 |
apest | -0.536 |
merce | -0.534 |
Token | word |
Token ID | 4775 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
PASS | +0.328 |
Musk | +0.310 |
RIS | +0.295 |
FISA | +0.293 |
Route | +0.288 |
Neg logit contributions | |
sterdam | -0.487 |
anco | -0.484 |
ldom | -0.464 |
apest | -0.442 |
merce | -0.440 |
Token | mon |
Token ID | 937 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
PASS | +3.733 |
Musk | +3.678 |
FISA | +3.533 |
RIS | +3.514 |
Route | +3.458 |
Neg logit contributions | |
sterdam | -4.460 |
anco | -4.366 |
ldom | -4.181 |
merce | -4.030 |
apest | -3.977 |
Token | ologue |
Token ID | 39795 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
PASS | +0.959 |
Musk | +0.916 |
RIS | +0.858 |
FISA | +0.846 |
Route | +0.845 |
Neg logit contributions | |
sterdam | -1.822 |
anco | -1.805 |
ldom | -1.743 |
apest | -1.664 |
merce | -1.661 |
Token | in |
Token ID | 287 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
PASS | +1.099 |
Musk | +1.057 |
RIS | +1.012 |
FISA | +1.007 |
Route | +0.987 |
Neg logit contributions | |
sterdam | -1.463 |
anco | -1.451 |
ldom | -1.385 |
apest | -1.325 |
merce | -1.320 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
PASS | +0.260 |
Musk | +0.248 |
RIS | +0.237 |
FISA | +0.235 |
Route | +0.230 |
Neg logit contributions | |
sterdam | -0.382 |
anco | -0.380 |
ldom | -0.364 |
apest | -0.346 |
merce | -0.345 |
Token | second |
Token ID | 1218 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
PASS | +0.121 |
Musk | +0.116 |
RIS | +0.111 |
FISA | +0.110 |
Route | +0.108 |
Neg logit contributions | |
sterdam | -0.157 |
anco | -0.157 |
ldom | -0.150 |
apest | -0.142 |
merce | -0.141 |
Token | provide |
Token ID | 2148 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
sterdam | +0.175 |
anco | +0.174 |
ldom | +0.166 |
apest | +0.157 |
merce | +0.156 |
Neg logit contributions | |
PASS | -0.149 |
Musk | -0.142 |
RIS | -0.137 |
FISA | -0.136 |
Route | -0.134 |
Token | commentary |
Token ID | 14604 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
PASS | +0.008 |
Musk | +0.008 |
RIS | +0.007 |
FISA | +0.007 |
Route | +0.007 |
Neg logit contributions | |
sterdam | -0.009 |
anco | -0.009 |
ldom | -0.009 |
apest | -0.008 |
merce | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
PASS | +0.723 |
Musk | +0.691 |
RIS | +0.663 |
FISA | +0.655 |
Route | +0.643 |
Neg logit contributions | |
sterdam | -1.039 |
anco | -1.035 |
ldom | -0.992 |
apest | -0.947 |
merce | -0.940 |
Token | real |
Token ID | 1103 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
PASS | +0.361 |
Musk | +0.345 |
RIS | +0.331 |
FISA | +0.329 |
Route | +0.322 |
Neg logit contributions | |
sterdam | -0.463 |
anco | -0.461 |
ldom | -0.441 |
apest | -0.418 |
merce | -0.416 |
Token | - |
Token ID | 12 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
PASS | +0.013 |
Musk | +0.013 |
RIS | +0.012 |
FISA | +0.012 |
Route | +0.012 |
Neg logit contributions | |
sterdam | -0.017 |
anco | -0.017 |
ldom | -0.016 |
apest | -0.015 |
merce | -0.015 |
Token | time |
Token ID | 2435 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
PASS | +0.362 |
Musk | +0.342 |
RIS | +0.327 |
FISA | +0.324 |
Route | +0.317 |
Neg logit contributions | |
sterdam | -0.569 |
anco | -0.568 |
ldom | -0.545 |
apest | -0.518 |
merce | -0.516 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
PASS | +3.135 |
Musk | +3.107 |
RIS | +2.976 |
ACC | +2.900 |
FISA | +2.884 |
Neg logit contributions | |
sterdam | -4.860 |
anco | -4.847 |
ldom | -4.667 |
apest | -4.508 |
merce | -4.430 |
Token | Integrated |
Token ID | 35432 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
PASS | +0.088 |
Musk | +0.084 |
RIS | +0.081 |
FISA | +0.080 |
Route | +0.079 |
Neg logit contributions | |
sterdam | -0.116 |
anco | -0.115 |
ldom | -0.111 |
apest | -0.105 |
merce | -0.105 |
Token | social |
Token ID | 1919 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
PASS | +0.866 |
Musk | +0.831 |
RIS | +0.795 |
FISA | +0.789 |
Route | +0.774 |
Neg logit contributions | |
sterdam | -1.188 |
anco | -1.181 |
ldom | -1.138 |
apest | -1.084 |
merce | -1.072 |
Token | features |
Token ID | 3033 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
sterdam | +0.070 |
anco | +0.070 |
ldom | +0.066 |
apest | +0.062 |
merce | +0.061 |
Neg logit contributions | |
PASS | -0.080 |
Musk | -0.077 |
RIS | -0.075 |
FISA | -0.074 |
Route | -0.073 |
Token | also |
Token ID | 635 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
PASS | +0.706 |
Musk | +0.680 |
RIS | +0.651 |
FISA | +0.647 |
Route | +0.637 |
Neg logit contributions | |
sterdam | -0.812 |
anco | -0.806 |
ldom | -0.772 |
apest | -0.731 |
merce | -0.724 |
Token | NN |
Token ID | 6144 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
sterdam | +1.314 |
anco | +1.312 |
ldom | +1.256 |
apest | +1.197 |
merce | +1.189 |
Neg logit contributions | |
PASS | -0.789 |
Musk | -0.748 |
RIS | -0.711 |
FISA | -0.708 |
Route | -0.690 |
Token | JR |
Token ID | 44817 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
sterdam | +0.155 |
anco | +0.154 |
ldom | +0.148 |
apest | +0.141 |
merce | +0.141 |
Neg logit contributions | |
PASS | -0.091 |
Musk | -0.085 |
RIS | -0.081 |
FISA | -0.080 |
Route | -0.079 |
Token | � |
Token ID | 8582 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
sterdam | +0.444 |
anco | +0.443 |
ldom | +0.425 |
apest | +0.405 |
merce | +0.403 |
Neg logit contributions | |
PASS | -0.269 |
Musk | -0.254 |
RIS | -0.242 |
FISA | -0.240 |
Route | -0.234 |
Token | � |
Token ID | 229 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
PASS | +3.665 |
Musk | +3.519 |
@# | +3.415 |
FISA | +3.377 |
RIS | +3.375 |
Neg logit contributions | |
sterdam | -4.547 |
anco | -4.378 |
ldom | -4.266 |
apest | -4.065 |
merce | -4.056 |
Token | � |
Token ID | 118 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
sterdam | +0.338 |
anco | +0.337 |
ldom | +0.319 |
apest | +0.299 |
merce | +0.296 |
Neg logit contributions | |
PASS | -0.384 |
Musk | -0.368 |
RIS | -0.356 |
FISA | -0.355 |
Route | -0.349 |
Token | � |
Token ID | 8582 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
anco | +2.099 |
sterdam | +2.093 |
ldom | +2.007 |
apest | +1.909 |
merce | +1.894 |
Neg logit contributions | |
PASS | -1.259 |
Musk | -1.197 |
RIS | -1.137 |
FISA | -1.128 |
Route | -1.102 |
Token | � |
Token ID | 229 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
PASS | +3.504 |
Musk | +3.391 |
@# | +3.314 |
FISA | +3.256 |
Route | +3.233 |
Neg logit contributions | |
sterdam | -4.506 |
anco | -4.275 |
ldom | -4.191 |
merce | -4.017 |
Indust | -3.967 |
Token | � |
Token ID | 116 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
sterdam | +0.465 |
anco | +0.463 |
ldom | +0.437 |
apest | +0.408 |
merce | +0.405 |
Neg logit contributions | |
PASS | -0.572 |
Musk | -0.550 |
RIS | -0.532 |
FISA | -0.530 |
Route | -0.522 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
sterdam | +0.468 |
anco | +0.467 |
ldom | +0.449 |
apest | +0.428 |
merce | +0.426 |
Neg logit contributions | |
PASS | -0.252 |
Musk | -0.237 |
RIS | -0.225 |
FISA | -0.223 |
Route | -0.218 |
Token | m |
Token ID | 76 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
PASS | +1.217 |
Musk | +1.139 |
RIS | +1.094 |
FISA | +1.086 |
@# | +1.072 |
Neg logit contributions | |
sterdam | -1.420 |
anco | -1.406 |
ldom | -1.349 |
apest | -1.274 |
merce | -1.266 |
Token | f |
Token ID | 69 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
sterdam | +0.531 |
anco | +0.529 |
ldom | +0.509 |
apest | +0.485 |
merce | +0.482 |
Neg logit contributions | |
PASS | -0.302 |
Musk | -0.284 |
RIS | -0.271 |
FISA | -0.268 |
Route | -0.262 |
Token | to |
Token ID | 284 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
PASS | +0.578 |
Musk | +0.551 |
RIS | +0.524 |
FISA | +0.521 |
Route | +0.509 |
Neg logit contributions | |
sterdam | -0.882 |
anco | -0.879 |
ldom | -0.844 |
apest | -0.804 |
merce | -0.798 |
Token | pay |
Token ID | 1414 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
PASS | +0.385 |
Musk | +0.370 |
RIS | +0.358 |
FISA | +0.356 |
Route | +0.350 |
Neg logit contributions | |
sterdam | -0.336 |
anco | -0.334 |
ldom | -0.317 |
apest | -0.296 |
merce | -0.294 |
Token | a |
Token ID | 257 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
sterdam | +0.180 |
anco | +0.180 |
ldom | +0.171 |
apest | +0.162 |
merce | +0.161 |
Neg logit contributions | |
PASS | -0.161 |
Musk | -0.154 |
RIS | -0.148 |
FISA | -0.147 |
Route | -0.145 |
Token | 73 |
Token ID | 8854 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
sterdam | +0.127 |
anco | +0.127 |
ldom | +0.120 |
apest | +0.113 |
merce | +0.111 |
Neg logit contributions | |
PASS | -0.143 |
Musk | -0.138 |
RIS | -0.133 |
FISA | -0.133 |
Route | -0.131 |
Token | - |
Token ID | 12 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
PASS | +0.342 |
Musk | +0.326 |
RIS | +0.311 |
FISA | +0.307 |
Route | +0.301 |
Neg logit contributions | |
sterdam | -0.524 |
anco | -0.522 |
ldom | -0.500 |
apest | -0.477 |
merce | -0.472 |
Token | per |
Token ID | 525 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
PASS | +0.361 |
Musk | +0.343 |
RIS | +0.328 |
FISA | +0.325 |
Route | +0.320 |
Neg logit contributions | |
sterdam | -0.458 |
anco | -0.457 |
ldom | -0.436 |
apest | -0.414 |
merce | -0.410 |
Token | - |
Token ID | 12 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
PASS | +2.963 |
Musk | +2.813 |
ACC | +2.634 |
Route | +2.614 |
@# | +2.596 |
Neg logit contributions | |
sterdam | -5.145 |
anco | -5.025 |
ldom | -4.812 |
merce | -4.717 |
Indust | -4.665 |
Token | cent |
Token ID | 1087 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anco | +0.627 |
sterdam | +0.626 |
ldom | +0.593 |
apest | +0.551 |
merce | +0.545 |
Neg logit contributions | |
PASS | -0.777 |
Musk | -0.749 |
RIS | -0.729 |
FISA | -0.724 |
Route | -0.712 |
Token | tax |
Token ID | 1687 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
sterdam | +0.691 |
anco | +0.688 |
ldom | +0.651 |
apest | +0.610 |
merce | +0.605 |
Neg logit contributions | |
PASS | -0.788 |
Musk | -0.758 |
RIS | -0.733 |
FISA | -0.730 |
Route | -0.717 |
Token | when |
Token ID | 618 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
PASS | +0.228 |
Musk | +0.219 |
RIS | +0.212 |
FISA | +0.210 |
Route | +0.207 |
Neg logit contributions | |
sterdam | -0.216 |
anco | -0.216 |
ldom | -0.205 |
apest | -0.193 |
merce | -0.191 |
Token | even |
Token ID | 772 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
sterdam | +0.541 |
anco | +0.539 |
ldom | +0.516 |
apest | +0.489 |
merce | +0.486 |
Neg logit contributions | |
PASS | -0.397 |
Musk | -0.377 |
RIS | -0.362 |
FISA | -0.359 |
Route | -0.352 |
Token | of |
Token ID | 286 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
sterdam | +0.154 |
anco | +0.153 |
ldom | +0.146 |
apest | +0.138 |
merce | +0.137 |
Neg logit contributions | |
PASS | -0.136 |
Musk | -0.129 |
RIS | -0.125 |
FISA | -0.124 |
Route | -0.122 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
anco | +0.077 |
sterdam | +0.077 |
ldom | +0.074 |
apest | +0.071 |
merce | +0.070 |
Neg logit contributions | |
PASS | -0.045 |
Musk | -0.042 |
RIS | -0.040 |
FISA | -0.040 |
Route | -0.039 |
Token | 's |
Token ID | 338 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
sterdam | +0.346 |
anco | +0.345 |
ldom | +0.330 |
apest | +0.314 |
merce | +0.311 |
Neg logit contributions | |
PASS | -0.253 |
Musk | -0.241 |
RIS | -0.231 |
FISA | -0.230 |
Route | -0.225 |
Token | hard |
Token ID | 1327 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
anco | +0.450 |
sterdam | +0.450 |
ldom | +0.425 |
apest | +0.395 |
merce | +0.392 |
Neg logit contributions | |
PASS | -0.527 |
Musk | -0.504 |
RIS | -0.489 |
FISA | -0.484 |
Route | -0.477 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
sterdam | +0.609 |
anco | +0.606 |
ldom | +0.581 |
apest | +0.552 |
merce | +0.548 |
Neg logit contributions | |
PASS | -0.420 |
Musk | -0.398 |
RIS | -0.381 |
FISA | -0.379 |
Route | -0.371 |
Token | line |
Token ID | 1370 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
PASS | +0.657 |
Musk | +0.617 |
RIS | +0.588 |
FISA | +0.585 |
Route | +0.573 |
Neg logit contributions | |
sterdam | -1.034 |
anco | -1.027 |
ldom | -0.991 |
merce | -0.938 |
apest | -0.938 |
Token | plan |
Token ID | 1410 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
PASS | +3.430 |
Musk | +3.359 |
FISA | +3.295 |
Route | +3.176 |
RIS | +3.167 |
Neg logit contributions | |
sterdam | -4.635 |
anco | -4.506 |
ldom | -4.379 |
merce | -4.230 |
apest | -4.185 |
Token | to |
Token ID | 284 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
sterdam | +0.747 |
anco | +0.746 |
ldom | +0.713 |
apest | +0.678 |
merce | +0.674 |
Neg logit contributions | |
PASS | -0.515 |
Musk | -0.485 |
RIS | -0.467 |
FISA | -0.462 |
Route | -0.453 |
Token | crack |
Token ID | 8469 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
PASS | +0.339 |
Musk | +0.323 |
RIS | +0.311 |
FISA | +0.309 |
Route | +0.304 |
Neg logit contributions | |
sterdam | -0.387 |
anco | -0.386 |
ldom | -0.368 |
apest | -0.347 |
merce | -0.345 |
Token | down |
Token ID | 866 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
PASS | +0.626 |
Musk | +0.601 |
FISA | +0.578 |
RIS | +0.560 |
Route | +0.545 |
Neg logit contributions | |
sterdam | -1.086 |
anco | -1.075 |
ldom | -1.041 |
apest | -0.995 |
merce | -0.991 |
Token | on |
Token ID | 319 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
PASS | +0.382 |
Musk | +0.362 |
RIS | +0.346 |
FISA | +0.344 |
Route | +0.337 |
Neg logit contributions | |
sterdam | -0.558 |
anco | -0.556 |
ldom | -0.534 |
apest | -0.508 |
merce | -0.504 |
Token | Obama |
Token ID | 2486 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
sterdam | +1.093 |
anco | +1.087 |
ldom | +1.042 |
apest | +0.989 |
merce | +0.983 |
Neg logit contributions | |
PASS | -0.823 |
Musk | -0.789 |
RIS | -0.755 |
FISA | -0.750 |
Route | -0.734 |
Token | is |
Token ID | 318 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
sterdam | +0.687 |
anco | +0.684 |
ldom | +0.653 |
apest | +0.619 |
merce | +0.614 |
Neg logit contributions | |
PASS | -0.561 |
Musk | -0.536 |
RIS | -0.515 |
FISA | -0.511 |
Route | -0.502 |
Token | the |
Token ID | 262 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
PASS | +0.142 |
Musk | +0.136 |
RIS | +0.131 |
FISA | +0.129 |
Route | +0.127 |
Neg logit contributions | |
sterdam | -0.176 |
anco | -0.176 |
ldom | -0.168 |
apest | -0.159 |
merce | -0.158 |
Token | worst |
Token ID | 5290 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
PASS | +0.610 |
Musk | +0.591 |
RIS | +0.570 |
FISA | +0.564 |
Route | +0.553 |
Neg logit contributions | |
sterdam | -0.743 |
anco | -0.742 |
ldom | -0.707 |
merce | -0.669 |
apest | -0.665 |
Token | ne |
Token ID | 497 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
PASS | +0.462 |
Musk | +0.448 |
RIS | +0.433 |
FISA | +0.426 |
ACC | +0.418 |
Neg logit contributions | |
sterdam | -0.600 |
anco | -0.594 |
ldom | -0.573 |
apest | -0.541 |
merce | -0.540 |
Token | |
Token ID | 3907 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
sterdam | +1.229 |
anco | +1.228 |
ldom | +1.161 |
apest | +1.091 |
merce | +1.082 |
Neg logit contributions | |
PASS | -1.308 |
Musk | -1.252 |
RIS | -1.211 |
FISA | -1.203 |
Route | -1.183 |
Token | go |
Token ID | 2188 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
PASS | +3.807 |
Musk | +3.680 |
RIS | +3.483 |
FISA | +3.462 |
Route | +3.450 |
Neg logit contributions | |
sterdam | -4.210 |
anco | -4.111 |
ldom | -3.961 |
Indust | -3.782 |
apest | -3.726 |
Token | |
Token ID | 3907 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
PASS | +1.940 |
Musk | +1.871 |
RIS | +1.805 |
FISA | +1.787 |
Route | +1.766 |
Neg logit contributions | |
sterdam | -2.245 |
anco | -2.208 |
ldom | -2.116 |
Indust | -2.009 |
merce | -1.988 |
Token | ti |
Token ID | 20259 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
PASS | +2.557 |
Musk | +2.500 |
RIS | +2.409 |
face | +2.376 |
Route | +2.376 |
Neg logit contributions | |
sterdam | -2.299 |
anco | -2.225 |
ldom | -2.164 |
Indust | -2.037 |
apest | -2.015 |
Token | |
Token ID | 3907 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
sterdam | +1.048 |
anco | +1.045 |
ldom | +0.993 |
apest | +0.935 |
merce | +0.927 |
Neg logit contributions | |
PASS | -1.033 |
Musk | -0.987 |
RIS | -0.953 |
FISA | -0.948 |
Route | -0.932 |
Token | at |
Token ID | 265 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
PASS | +2.002 |
Musk | +1.947 |
RIS | +1.848 |
face | +1.827 |
ACC | +1.814 |
Neg logit contributions | |
sterdam | -2.681 |
anco | -2.593 |
ldom | -2.556 |
Indust | -2.453 |
apest | -2.434 |
Token | ging |
Token ID | 2667 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
PASS | +0.525 |
Musk | +0.496 |
RIS | +0.472 |
Route | +0.467 |
FISA | +0.463 |
Neg logit contributions | |
sterdam | -0.720 |
anco | -0.715 |
ldom | -0.675 |
apest | -0.648 |
merce | -0.646 |
Token | for |
Token ID | 329 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
sterdam | +1.154 |
anco | +1.151 |
ldom | +1.100 |
apest | +1.041 |
merce | +1.034 |
Neg logit contributions | |
PASS | -0.856 |
Musk | -0.811 |
RIS | -0.779 |
FISA | -0.775 |
Route | -0.757 |
Token | the |
Token ID | 262 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
sterdam | +0.245 |
anco | +0.244 |
ldom | +0.233 |
apest | +0.220 |
merce | +0.219 |
Neg logit contributions | |
PASS | -0.211 |
Musk | -0.201 |
RIS | -0.194 |
FISA | -0.192 |
Route | -0.189 |
Token | Pay |
Token ID | 7119 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
sterdam | +0.007 |
anco | +0.007 |
ldom | +0.006 |
apest | +0.006 |
merce | +0.006 |
Neg logit contributions | |
PASS | -0.006 |
Musk | -0.006 |
RIS | -0.006 |
FISA | -0.006 |
Route | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
sterdam | +0.807 |
anco | +0.805 |
ldom | +0.772 |
merce | +0.734 |
apest | +0.734 |
Neg logit contributions | |
PASS | -0.534 |
Musk | -0.507 |
RIS | -0.482 |
FISA | -0.477 |
Route | -0.474 |
Token | Per |
Token ID | 5990 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
sterdam | +0.032 |
anco | +0.032 |
ldom | +0.031 |
merce | +0.029 |
apest | +0.029 |
Neg logit contributions | |
PASS | -0.020 |
Musk | -0.019 |
RIS | -0.018 |
FISA | -0.017 |
@# | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
PASS | +2.775 |
Musk | +2.708 |
Route | +2.557 |
Model | +2.535 |
ACC | +2.511 |
Neg logit contributions | |
sterdam | -5.111 |
anco | -4.994 |
ldom | -4.815 |
merce | -4.678 |
apest | -4.623 |
Token | View |
Token ID | 7680 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
PASS | +0.002 |
Musk | +0.002 |
RIS | +0.002 |
FISA | +0.002 |
Route | +0.002 |
Neg logit contributions | |
sterdam | -0.002 |
anco | -0.002 |
ldom | -0.002 |
apest | -0.002 |
merce | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
PASS | +0.578 |
Musk | +0.550 |
RIS | +0.529 |
FISA | +0.523 |
Route | +0.517 |
Neg logit contributions | |
sterdam | -0.711 |
anco | -0.708 |
ldom | -0.678 |
apest | -0.638 |
merce | -0.637 |
Token | just |
Token ID | 655 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
PASS | +0.318 |
Musk | +0.302 |
RIS | +0.290 |
FISA | +0.288 |
Route | +0.283 |
Neg logit contributions | |
sterdam | -0.424 |
anco | -0.422 |
ldom | -0.404 |
apest | -0.383 |
merce | -0.381 |
Token | have |
Token ID | 423 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
PASS | +0.315 |
Musk | +0.301 |
RIS | +0.290 |
FISA | +0.287 |
Route | +0.282 |
Neg logit contributions | |
sterdam | -0.380 |
anco | -0.378 |
ldom | -0.361 |
apest | -0.341 |
merce | -0.339 |
Token | this |
Token ID | 428 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
PASS | +0.492 |
Musk | +0.472 |
FISA | +0.451 |
RIS | +0.447 |
Route | +0.437 |
Neg logit contributions | |
sterdam | -0.775 |
anco | -0.766 |
ldom | -0.734 |
apest | -0.708 |
merce | -0.695 |
Token | case |
Token ID | 1339 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
sterdam | +0.299 |
anco | +0.298 |
ldom | +0.283 |
apest | +0.267 |
merce | +0.265 |
Neg logit contributions | |
PASS | -0.291 |
Musk | -0.279 |
RIS | -0.269 |
FISA | -0.268 |
Route | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
sterdam | +1.337 |
anco | +1.332 |
ldom | +1.268 |
apest | +1.199 |
merce | +1.189 |
Neg logit contributions | |
PASS | -1.227 |
Musk | -1.177 |
RIS | -1.133 |
FISA | -1.125 |
Route | -1.108 |
Token | The |
Token ID | 383 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
PASS | +0.181 |
Musk | +0.172 |
RIS | +0.165 |
FISA | +0.164 |
Route | +0.161 |
Neg logit contributions | |
sterdam | -0.237 |
anco | -0.236 |
ldom | -0.226 |
apest | -0.214 |
merce | -0.213 |
Token | smart |
Token ID | 4451 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
sterdam | +0.411 |
anco | +0.409 |
ldom | +0.390 |
apest | +0.367 |
merce | +0.365 |
Neg logit contributions | |
PASS | -0.372 |
Musk | -0.358 |
RIS | -0.344 |
FISA | -0.343 |
Route | -0.337 |
Token | money |
Token ID | 1637 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
sterdam | +0.224 |
anco | +0.223 |
ldom | +0.213 |
apest | +0.199 |
merce | +0.198 |
Neg logit contributions | |
PASS | -0.219 |
Musk | -0.210 |
RIS | -0.203 |
FISA | -0.202 |
Route | -0.198 |
Token | would |
Token ID | 561 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
PASS | +3.077 |
Musk | +3.008 |
RIS | +2.913 |
@# | +2.830 |
FISA | +2.808 |
Neg logit contributions | |
sterdam | -4.605 |
anco | -4.572 |
ldom | -4.449 |
apest | -4.208 |
Indust | -4.206 |
Token | still |
Token ID | 991 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
PASS | +0.377 |
Musk | +0.357 |
RIS | +0.342 |
FISA | +0.340 |
Route | +0.333 |
Neg logit contributions | |
sterdam | -0.530 |
anco | -0.529 |
ldom | -0.506 |
apest | -0.480 |
merce | -0.478 |
Token | say |
Token ID | 910 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
PASS | +0.902 |
Musk | +0.858 |
RIS | +0.830 |
FISA | +0.818 |
Route | +0.800 |
Neg logit contributions | |
sterdam | -1.282 |
anco | -1.268 |
ldom | -1.219 |
merce | -1.153 |
apest | -1.152 |
Token | that |
Token ID | 326 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
PASS | +1.021 |
Musk | +0.984 |
FISA | +0.940 |
RIS | +0.939 |
Route | +0.916 |
Neg logit contributions | |
sterdam | -1.310 |
anco | -1.305 |
ldom | -1.244 |
apest | -1.183 |
merce | -1.169 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
PASS | +0.016 |
Musk | +0.016 |
RIS | +0.015 |
FISA | +0.015 |
Route | +0.015 |
Neg logit contributions | |
sterdam | -0.021 |
anco | -0.021 |
ldom | -0.020 |
apest | -0.019 |
merce | -0.019 |
Token | blown |
Token ID | 31290 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
sterdam | +0.832 |
anco | +0.830 |
ldom | +0.781 |
apest | +0.742 |
merce | +0.730 |
Neg logit contributions | |
PASS | -0.683 |
Musk | -0.647 |
RIS | -0.626 |
FISA | -0.625 |
Route | -0.608 |
Token | pand |
Token ID | 19798 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
PASS | +1.112 |
Musk | +1.079 |
RIS | +1.051 |
FISA | +1.028 |
Route | +1.018 |
Neg logit contributions | |
sterdam | -1.547 |
anco | -1.539 |
ldom | -1.476 |
apest | -1.408 |
merce | -1.403 |
Token | emic |
Token ID | 5314 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
sterdam | +0.845 |
anco | +0.843 |
ldom | +0.787 |
apest | +0.723 |
merce | +0.713 |
Neg logit contributions | |
PASS | -1.419 |
Musk | -1.371 |
RIS | -1.333 |
FISA | -1.327 |
Route | -1.308 |
Token | . |
Token ID | 13 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
sterdam | +0.476 |
anco | +0.473 |
ldom | +0.451 |
apest | +0.428 |
merce | +0.424 |
Neg logit contributions | |
PASS | -0.419 |
Musk | -0.402 |
RIS | -0.388 |
FISA | -0.384 |
Route | -0.379 |
Token | SW |
Token ID | 12672 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
sterdam | +0.252 |
anco | +0.251 |
ldom | +0.240 |
apest | +0.227 |
merce | +0.226 |
Neg logit contributions | |
PASS | -0.201 |
Musk | -0.191 |
RIS | -0.184 |
FISA | -0.182 |
Route | -0.179 |
Token | INE |
Token ID | 8881 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
sterdam | +0.047 |
anco | +0.047 |
ldom | +0.045 |
apest | +0.042 |
merce | +0.042 |
Neg logit contributions | |
PASS | -0.036 |
Musk | -0.034 |
RIS | -0.032 |
FISA | -0.032 |
Route | -0.032 |
Token | FL |
Token ID | 9977 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
PASS | +3.473 |
Musk | +3.257 |
RIS | +3.220 |
FISA | +3.103 |
ACC | +3.099 |
Neg logit contributions | |
sterdam | -4.334 |
anco | -4.305 |
ldom | -4.178 |
merce | -3.968 |
apest | -3.920 |
Token | U |
Token ID | 52 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
PASS | +0.576 |
Musk | +0.545 |
RIS | +0.524 |
FISA | +0.517 |
Route | +0.507 |
Neg logit contributions | |
sterdam | -0.776 |
anco | -0.770 |
ldom | -0.739 |
merce | -0.703 |
apest | -0.699 |
Token | - |
Token ID | 532 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
PASS | +0.435 |
Musk | +0.415 |
RIS | +0.403 |
FISA | +0.397 |
Route | +0.391 |
Neg logit contributions | |
sterdam | -0.473 |
anco | -0.470 |
ldom | -0.449 |
merce | -0.423 |
apest | -0.421 |
Token | THE |
Token ID | 3336 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
sterdam | +1.175 |
anco | +1.172 |
ldom | +1.122 |
apest | +1.065 |
merce | +1.056 |
Neg logit contributions | |
PASS | -0.821 |
Musk | -0.777 |
RIS | -0.742 |
FISA | -0.740 |
Route | -0.723 |
Token | BAS |
Token ID | 29809 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
PASS | +0.566 |
Musk | +0.534 |
RIS | +0.518 |
FISA | +0.505 |
ACC | +0.494 |
Neg logit contributions | |
sterdam | -1.030 |
anco | -1.026 |
ldom | -0.989 |
merce | -0.943 |
apest | -0.938 |
Token | Philadelphia |
Token ID | 8857 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
PASS | +0.068 |
Musk | +0.064 |
RIS | +0.061 |
FISA | +0.061 |
Route | +0.059 |
Neg logit contributions | |
sterdam | -0.102 |
anco | -0.102 |
ldom | -0.098 |
apest | -0.093 |
merce | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
PASS | +0.045 |
Musk | +0.043 |
RIS | +0.041 |
FISA | +0.041 |
Route | +0.040 |
Neg logit contributions | |
sterdam | -0.055 |
anco | -0.055 |
ldom | -0.052 |
merce | -0.050 |
apest | -0.049 |
Token | A |
Token ID | 32 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
PASS | +0.131 |
Musk | +0.126 |
RIS | +0.121 |
FISA | +0.120 |
Route | +0.118 |
Neg logit contributions | |
sterdam | -0.145 |
anco | -0.145 |
ldom | -0.138 |
apest | -0.130 |
merce | -0.130 |
Token | two |
Token ID | 734 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
sterdam | +0.504 |
anco | +0.502 |
ldom | +0.480 |
apest | +0.454 |
merce | +0.451 |
Neg logit contributions | |
PASS | -0.408 |
Musk | -0.387 |
RIS | -0.373 |
FISA | -0.370 |
Route | -0.363 |
Token | - |
Token ID | 12 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
sterdam | +0.307 |
anco | +0.306 |
ldom | +0.293 |
apest | +0.277 |
merce | +0.275 |
Neg logit contributions | |
PASS | -0.230 |
Musk | -0.218 |
RIS | -0.209 |
FISA | -0.207 |
Route | -0.202 |
Token | time |
Token ID | 2435 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
sterdam | +0.278 |
anco | +0.277 |
ldom | +0.265 |
apest | +0.250 |
merce | +0.248 |
Neg logit contributions | |
PASS | -0.211 |
Musk | -0.201 |
RIS | -0.194 |
FISA | -0.192 |
Route | -0.187 |
Token | Olymp |
Token ID | 7001 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
PASS | +2.945 |
Musk | +2.870 |
FISA | +2.750 |
ACC | +2.747 |
RIS | +2.717 |
Neg logit contributions | |
anco | -4.809 |
sterdam | -4.750 |
ldom | -4.606 |
merce | -4.383 |
apest | -4.343 |
Token | ian |
Token ID | 666 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
PASS | +1.264 |
Musk | +1.219 |
FISA | +1.154 |
RIS | +1.152 |
Route | +1.142 |
Neg logit contributions | |
sterdam | -1.514 |
anco | -1.489 |
ldom | -1.430 |
merce | -1.361 |
apest | -1.354 |
Token | , |
Token ID | 11 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
PASS | +0.564 |
Musk | +0.536 |
RIS | +0.513 |
FISA | +0.509 |
Route | +0.499 |
Neg logit contributions | |
sterdam | -0.807 |
anco | -0.803 |
ldom | -0.770 |
apest | -0.733 |
merce | -0.727 |
Token | Lang |
Token ID | 16332 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
PASS | +0.191 |
Musk | +0.176 |
RIS | +0.166 |
FISA | +0.164 |
Route | +0.159 |
Neg logit contributions | |
sterdam | -0.448 |
anco | -0.447 |
ldom | -0.431 |
apest | -0.413 |
merce | -0.411 |
Token | en |
Token ID | 268 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
PASS | +0.635 |
Musk | +0.614 |
RIS | +0.594 |
FISA | +0.592 |
Route | +0.585 |
Neg logit contributions | |
sterdam | -0.425 |
anco | -0.423 |
ldom | -0.397 |
apest | -0.367 |
merce | -0.366 |
Token | here |
Token ID | 994 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
sterdam | +0.497 |
anco | +0.495 |
ldom | +0.475 |
apest | +0.452 |
merce | +0.449 |
Neg logit contributions | |
PASS | -0.317 |
Musk | -0.300 |
RIS | -0.286 |
FISA | -0.284 |
Route | -0.278 |
Token | is |
Token ID | 318 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
sterdam | +0.711 |
anco | +0.708 |
ldom | +0.676 |
apest | +0.637 |
merce | +0.633 |
Neg logit contributions | |
PASS | -0.643 |
Musk | -0.616 |
RIS | -0.594 |
FISA | -0.588 |
Route | -0.578 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
sterdam | +0.210 |
anco | +0.210 |
ldom | +0.201 |
apest | +0.191 |
merce | +0.190 |
Neg logit contributions | |
PASS | -0.156 |
Musk | -0.149 |
RIS | -0.143 |
FISA | -0.141 |
Route | -0.139 |
Token | real |
Token ID | 1103 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
sterdam | +0.009 |
anco | +0.008 |
ldom | +0.008 |
apest | +0.008 |
merce | +0.008 |
Neg logit contributions | |
PASS | -0.007 |
Musk | -0.007 |
RIS | -0.007 |
FISA | -0.007 |
Route | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
PASS | +0.013 |
Musk | +0.013 |
RIS | +0.012 |
FISA | +0.012 |
Route | +0.012 |
Neg logit contributions | |
sterdam | -0.016 |
anco | -0.016 |
ldom | -0.016 |
apest | -0.015 |
merce | -0.015 |
Token | time |
Token ID | 2435 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
PASS | +0.279 |
Musk | +0.266 |
RIS | +0.257 |
FISA | +0.255 |
Route | +0.250 |
Neg logit contributions | |
sterdam | -0.309 |
anco | -0.308 |
ldom | -0.293 |
apest | -0.277 |
merce | -0.274 |
Token | / |
Token ID | 1220 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
PASS | +3.512 |
Musk | +3.411 |
RIS | +3.339 |
FISA | +3.294 |
Route | +3.254 |
Neg logit contributions | |
sterdam | -4.155 |
anco | -4.130 |
ldom | -3.976 |
merce | -3.728 |
apest | -3.703 |
Token | streaming |
Token ID | 11305 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
sterdam | +0.643 |
anco | +0.641 |
ldom | +0.610 |
apest | +0.579 |
merce | +0.574 |
Neg logit contributions | |
PASS | -0.536 |
Musk | -0.511 |
RIS | -0.489 |
FISA | -0.488 |
Route | -0.478 |
Token | analytics |
Token ID | 23696 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
sterdam | +0.791 |
anco | +0.789 |
ldom | +0.753 |
apest | +0.715 |
merce | +0.707 |
Neg logit contributions | |
PASS | -0.620 |
Musk | -0.589 |
RIS | -0.565 |
FISA | -0.561 |
Route | -0.550 |
Token | version |
Token ID | 2196 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
sterdam | +0.225 |
anco | +0.224 |
ldom | +0.214 |
apest | +0.203 |
merce | +0.201 |
Neg logit contributions | |
PASS | -0.175 |
Musk | -0.167 |
RIS | -0.160 |
FISA | -0.159 |
Route | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
sterdam | +0.214 |
anco | +0.213 |
ldom | +0.204 |
apest | +0.193 |
merce | +0.192 |
Neg logit contributions | |
PASS | -0.174 |
Musk | -0.167 |
RIS | -0.161 |
FISA | -0.159 |
Route | -0.156 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
sterdam | +0.086 |
anco | +0.086 |
ldom | +0.082 |
apest | +0.078 |
merce | +0.078 |
Neg logit contributions | |
PASS | -0.062 |
Musk | -0.059 |
RIS | -0.057 |
FISA | -0.056 |
Route | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
PASS | +0.206 |
Musk | +0.199 |
RIS | +0.191 |
FISA | +0.189 |
Route | +0.187 |
Neg logit contributions | |
sterdam | -0.242 |
anco | -0.241 |
ldom | -0.230 |
apest | -0.219 |
merce | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
PASS | +0.262 |
Musk | +0.251 |
RIS | +0.240 |
FISA | +0.238 |
Route | +0.234 |
Neg logit contributions | |
sterdam | -0.351 |
anco | -0.349 |
ldom | -0.335 |
apest | -0.317 |
merce | -0.317 |
Token |
|
Token ID | 198 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
PASS | +0.247 |
Musk | +0.235 |
RIS | +0.227 |
FISA | +0.225 |
Route | +0.220 |
Neg logit contributions | |
anco | -0.296 |
sterdam | -0.295 |
ldom | -0.281 |
apest | -0.267 |
merce | -0.262 |
Token | THE |
Token ID | 10970 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
PASS | +0.065 |
Musk | +0.062 |
RIS | +0.059 |
FISA | +0.059 |
Route | +0.058 |
Neg logit contributions | |
sterdam | -0.075 |
anco | -0.074 |
ldom | -0.071 |
apest | -0.067 |
merce | -0.067 |
Token | PUR |
Token ID | 33079 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
PASS | +0.977 |
Musk | +0.917 |
RIS | +0.898 |
FISA | +0.876 |
ACC | +0.861 |
Neg logit contributions | |
sterdam | -1.713 |
anco | -1.707 |
ldom | -1.649 |
merce | -1.563 |
apest | -1.559 |
Token | GE |
Token ID | 8264 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
PASS | +4.072 |
RIS | +3.689 |
FISA | +3.621 |
Musk | +3.610 |
ACC | +3.580 |
Neg logit contributions | |
sterdam | -3.848 |
anco | -3.785 |
ldom | -3.650 |
merce | -3.492 |
apest | -3.347 |
Token | D |
Token ID | 360 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
PASS | +0.533 |
Musk | +0.503 |
RIS | +0.486 |
FISA | +0.478 |
Route | +0.467 |
Neg logit contributions | |
sterdam | -0.871 |
anco | -0.868 |
ldom | -0.834 |
apest | -0.793 |
merce | -0.793 |
Token | ATES |
Token ID | 29462 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
PASS | +0.184 |
Musk | +0.173 |
RIS | +0.167 |
FISA | +0.165 |
Route | +0.162 |
Neg logit contributions | |
sterdam | -0.263 |
anco | -0.262 |
ldom | -0.251 |
merce | -0.238 |
apest | -0.237 |
Token | * |
Token ID | 9 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
PASS | +0.812 |
Musk | +0.767 |
RIS | +0.739 |
FISA | +0.729 |
Route | +0.714 |
Neg logit contributions | |
sterdam | -1.215 |
anco | -1.209 |
ldom | -1.161 |
apest | -1.101 |
merce | -1.099 |
Token | Spread |
Token ID | 31843 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
PASS | +0.628 |
Musk | +0.597 |
RIS | +0.576 |
FISA | +0.567 |
Route | +0.558 |
Neg logit contributions | |
sterdam | -0.852 |
anco | -0.847 |
ldom | -0.815 |
merce | -0.769 |
apest | -0.768 |
Token | � |
Token ID | 564 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
sterdam | +0.687 |
anco | +0.685 |
ldom | +0.656 |
apest | +0.622 |
merce | +0.618 |
Neg logit contributions | |
PASS | -0.497 |
Musk | -0.471 |
RIS | -0.452 |
FISA | -0.448 |
Route | -0.439 |
Token | � |
Token ID | 250 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
sterdam | +0.720 |
anco | +0.716 |
ldom | +0.672 |
apest | +0.623 |
merce | +0.616 |
Neg logit contributions | |
PASS | -1.052 |
Musk | -1.014 |
RIS | -0.985 |
FISA | -0.980 |
Route | -0.967 |
Token | The |
Token ID | 464 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
PASS | +0.071 |
Musk | +0.067 |
RIS | +0.064 |
FISA | +0.064 |
Route | +0.063 |
Neg logit contributions | |
sterdam | -0.084 |
anco | -0.083 |
ldom | -0.080 |
apest | -0.075 |
merce | -0.075 |
Token | OS |
Token ID | 7294 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
sterdam | +1.547 |
anco | +1.542 |
ldom | +1.477 |
apest | +1.405 |
merce | +1.394 |
Neg logit contributions | |
PASS | -1.048 |
Musk | -0.989 |
RIS | -0.946 |
FISA | -0.940 |
Route | -0.918 |
Token | - |
Token ID | 12 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
PASS | +0.191 |
Musk | +0.182 |
RIS | +0.176 |
FISA | +0.173 |
Route | +0.171 |
Neg logit contributions | |
sterdam | -0.241 |
anco | -0.241 |
ldom | -0.230 |
apest | -0.217 |
merce | -0.217 |
Token | per |
Token ID | 525 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
PASS | +0.106 |
Musk | +0.100 |
RIS | +0.096 |
FISA | +0.096 |
Route | +0.094 |
Neg logit contributions | |
sterdam | -0.126 |
anco | -0.126 |
ldom | -0.120 |
apest | -0.113 |
merce | -0.113 |
Token | iment |
Token ID | 3681 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
PASS | +3.156 |
Musk | +2.994 |
FISA | +2.811 |
Route | +2.773 |
Model | +2.771 |
Neg logit contributions | |
sterdam | -4.536 |
anco | -4.447 |
ldom | -4.184 |
apest | -4.076 |
merce | -4.012 |
Token | � |
Token ID | 447 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
sterdam | +0.247 |
anco | +0.246 |
ldom | +0.236 |
merce | +0.225 |
apest | +0.225 |
Neg logit contributions | |
PASS | -0.160 |
Musk | -0.152 |
RIS | -0.145 |
FISA | -0.144 |
Route | -0.142 |
Token | � |
Token ID | 247 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
PASS | +0.404 |
Musk | +0.386 |
RIS | +0.371 |
FISA | +0.370 |
Route | +0.364 |
Neg logit contributions | |
sterdam | -0.437 |
anco | -0.434 |
ldom | -0.414 |
apest | -0.391 |
merce | -0.388 |
Token | s |
Token ID | 82 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
PASS | +0.186 |
Musk | +0.177 |
RIS | +0.170 |
FISA | +0.168 |
Route | +0.167 |
Neg logit contributions | |
sterdam | -0.229 |
anco | -0.228 |
ldom | -0.217 |
apest | -0.206 |
merce | -0.205 |
Token | service |
Token ID | 2139 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
sterdam | +0.244 |
anco | +0.243 |
ldom | +0.233 |
apest | +0.220 |
merce | +0.219 |
Neg logit contributions | |
PASS | -0.191 |
Musk | -0.182 |
RIS | -0.175 |
FISA | -0.173 |
Route | -0.171 |
Token | talking |
Token ID | 3375 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
sterdam | +1.159 |
anco | +1.156 |
ldom | +1.106 |
apest | +1.049 |
Indust | +1.038 |
Neg logit contributions | |
PASS | -0.792 |
Musk | -0.745 |
RIS | -0.714 |
FISA | -0.713 |
Route | -0.694 |
Token | about |
Token ID | 546 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
PASS | +0.419 |
Musk | +0.397 |
RIS | +0.378 |
FISA | +0.374 |
Route | +0.368 |
Neg logit contributions | |
sterdam | -0.659 |
anco | -0.658 |
ldom | -0.632 |
apest | -0.603 |
merce | -0.600 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
PASS | +0.935 |
Musk | +0.899 |
RIS | +0.859 |
FISA | +0.848 |
Route | +0.838 |
Neg logit contributions | |
sterdam | -1.294 |
anco | -1.289 |
ldom | -1.231 |
apest | -1.181 |
merce | -1.175 |
Token | north |
Token ID | 5093 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
PASS | +0.116 |
Musk | +0.111 |
RIS | +0.107 |
FISA | +0.106 |
Route | +0.104 |
Neg logit contributions | |
sterdam | -0.130 |
anco | -0.130 |
ldom | -0.124 |
apest | -0.117 |
merce | -0.116 |
Token | - |
Token ID | 12 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
PASS | +0.351 |
Musk | +0.335 |
RIS | +0.320 |
FISA | +0.316 |
Route | +0.311 |
Neg logit contributions | |
anco | -0.543 |
sterdam | -0.543 |
ldom | -0.518 |
apest | -0.493 |
merce | -0.492 |
Token | east |
Token ID | 23316 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
PASS | +0.458 |
Musk | +0.427 |
RIS | +0.404 |
FISA | +0.400 |
Route | +0.392 |
Neg logit contributions | |
sterdam | -0.907 |
anco | -0.905 |
ldom | -0.872 |
apest | -0.832 |
merce | -0.828 |
Token | weather |
Token ID | 6193 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
PASS | +3.125 |
Musk | +3.046 |
Route | +2.960 |
RIS | +2.915 |
ACC | +2.908 |
Neg logit contributions | |
anco | -4.341 |
sterdam | -4.327 |
ldom | -4.027 |
merce | -3.953 |
apest | -3.880 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
sterdam | +0.535 |
anco | +0.535 |
ldom | +0.510 |
apest | +0.481 |
merce | +0.480 |
Neg logit contributions | |
PASS | -0.437 |
Musk | -0.418 |
RIS | -0.401 |
FISA | -0.397 |
Route | -0.392 |
Token | I |
Token ID | 314 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
PASS | +0.120 |
Musk | +0.114 |
RIS | +0.109 |
FISA | +0.108 |
Route | +0.106 |
Neg logit contributions | |
sterdam | -0.184 |
anco | -0.183 |
ldom | -0.176 |
apest | -0.167 |
merce | -0.166 |
Token | just |
Token ID | 655 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
sterdam | +0.213 |
anco | +0.212 |
ldom | +0.203 |
apest | +0.193 |
merce | +0.192 |
Neg logit contributions | |
PASS | -0.141 |
Musk | -0.134 |
RIS | -0.128 |
FISA | -0.127 |
Route | -0.125 |
Token | feel |
Token ID | 1254 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
sterdam | +0.577 |
anco | +0.572 |
ldom | +0.547 |
apest | +0.514 |
merce | +0.513 |
Neg logit contributions | |
PASS | -0.552 |
Musk | -0.530 |
RIS | -0.510 |
FISA | -0.506 |
Route | -0.499 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sterdam | +0.405 |
anco | +0.404 |
ldom | +0.386 |
apest | +0.364 |
merce | +0.362 |
Neg logit contributions | |
PASS | -0.339 |
Musk | -0.323 |
RIS | -0.311 |
FISA | -0.309 |
Route | -0.303 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
anco | +0.780 |
sterdam | +0.772 |
ldom | +0.736 |
apest | +0.700 |
Indust | +0.685 |
Neg logit contributions | |
PASS | -0.692 |
Musk | -0.661 |
RIS | -0.639 |
FISA | -0.634 |
�醒 | -0.631 |
Token | An |
Token ID | 2025 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
sterdam | +0.878 |
anco | +0.876 |
ldom | +0.829 |
apest | +0.778 |
merce | +0.770 |
Neg logit contributions | |
PASS | -0.969 |
Musk | -0.932 |
RIS | -0.902 |
FISA | -0.897 |
Route | -0.882 |
Token | eight |
Token ID | 3624 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
sterdam | +1.322 |
anco | +1.316 |
ldom | +1.258 |
apest | +1.194 |
merce | +1.182 |
Neg logit contributions | |
PASS | -1.016 |
Musk | -0.962 |
RIS | -0.919 |
FISA | -0.914 |
@# | -0.898 |
Token | - |
Token ID | 12 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
PASS | +0.337 |
Musk | +0.321 |
FISA | +0.305 |
RIS | +0.304 |
Route | +0.299 |
Neg logit contributions | |
sterdam | -0.487 |
anco | -0.486 |
ldom | -0.465 |
apest | -0.443 |
merce | -0.439 |
Token | bill |
Token ID | 35546 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
PASS | +0.171 |
Musk | +0.160 |
RIS | +0.152 |
FISA | +0.151 |
Route | +0.148 |
Neg logit contributions | |
sterdam | -0.299 |
anco | -0.298 |
ldom | -0.287 |
apest | -0.273 |
merce | -0.271 |
Token | package |
Token ID | 5301 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
PASS | +3.519 |
Musk | +3.379 |
FISA | +3.332 |
RIS | +3.277 |
ACC | +3.222 |
Neg logit contributions | |
anco | -3.987 |
sterdam | -3.980 |
ldom | -3.838 |
apest | -3.625 |
Indust | -3.508 |
Token | introduced |
Token ID | 5495 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
sterdam | +1.797 |
anco | +1.794 |
ldom | +1.699 |
merce | +1.602 |
apest | +1.600 |
Neg logit contributions | |
PASS | -1.533 |
Musk | -1.451 |
RIS | -1.404 |
FISA | -1.391 |
@# | -1.365 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
sterdam | +0.745 |
anco | +0.742 |
ldom | +0.710 |
apest | +0.673 |
merce | +0.668 |
Neg logit contributions | |
PASS | -0.572 |
Musk | -0.544 |
RIS | -0.522 |
FISA | -0.518 |
Route | -0.508 |
Token | would |
Token ID | 561 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
sterdam | +0.726 |
anco | +0.724 |
ldom | +0.688 |
apest | +0.647 |
merce | +0.643 |
Neg logit contributions | |
PASS | -0.679 |
Musk | -0.646 |
RIS | -0.623 |
FISA | -0.620 |
Route | -0.609 |
Token | strengthen |
Token ID | 12160 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
sterdam | +0.190 |
anco | +0.190 |
ldom | +0.181 |
apest | +0.172 |
merce | +0.171 |
Neg logit contributions | |
PASS | -0.151 |
Musk | -0.143 |
RIS | -0.138 |
FISA | -0.137 |
Route | -0.134 |
Token | pr |
Token ID | 1050 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
sterdam | +1.006 |
anco | +1.003 |
ldom | +0.956 |
apest | +0.903 |
merce | +0.896 |
Neg logit contributions | |
PASS | -0.879 |
Musk | -0.839 |
RIS | -0.807 |
FISA | -0.802 |
Route | -0.788 |
Token | — |
Token ID | 851 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
sterdam | +0.534 |
anco | +0.531 |
ldom | +0.507 |
apest | +0.478 |
merce | +0.477 |
Neg logit contributions | |
PASS | -0.483 |
Musk | -0.460 |
RIS | -0.443 |
FISA | -0.440 |
Route | -0.434 |
Token | � |
Token ID | 12520 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
anco | +1.598 |
sterdam | +1.597 |
ldom | +1.531 |
apest | +1.462 |
Indust | +1.452 |
Neg logit contributions | |
PASS | -0.844 |
Musk | -0.786 |
RIS | -0.747 |
FISA | -0.742 |
Route | -0.720 |
Token | � |
Token ID | 229 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
PASS | +1.498 |
Musk | +1.422 |
@# | +1.360 |
RIS | +1.359 |
FISA | +1.358 |
Neg logit contributions | |
sterdam | -1.726 |
anco | -1.687 |
ldom | -1.624 |
apest | -1.549 |
merce | -1.525 |
Token | � |
Token ID | 118 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
sterdam | +1.063 |
anco | +1.062 |
ldom | +1.014 |
apest | +0.958 |
merce | +0.951 |
Neg logit contributions | |
PASS | -0.867 |
Musk | -0.826 |
RIS | -0.794 |
FISA | -0.789 |
Route | -0.773 |
Token | � |
Token ID | 8582 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
anco | +2.089 |
sterdam | +2.078 |
ldom | +2.001 |
apest | +1.899 |
merce | +1.885 |
Neg logit contributions | |
PASS | -1.301 |
Musk | -1.238 |
RIS | -1.179 |
FISA | -1.169 |
Route | -1.140 |
Token | � |
Token ID | 229 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
PASS | +3.145 |
Musk | +3.080 |
@# | +3.050 |
Route | +2.959 |
FISA | +2.951 |
Neg logit contributions | |
sterdam | -4.251 |
anco | -4.008 |
ldom | -3.994 |
merce | -3.766 |
apest | -3.761 |
Token | � |
Token ID | 116 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
sterdam | +0.621 |
anco | +0.619 |
ldom | +0.584 |
apest | +0.545 |
merce | +0.539 |
Neg logit contributions | |
PASS | -0.778 |
Musk | -0.748 |
RIS | -0.725 |
FISA | -0.721 |
Route | -0.710 |
Token | M |
Token ID | 44 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
sterdam | +0.439 |
anco | +0.438 |
ldom | +0.420 |
apest | +0.399 |
merce | +0.396 |
Neg logit contributions | |
PASS | -0.295 |
Musk | -0.279 |
RIS | -0.267 |
FISA | -0.265 |
Route | -0.259 |
Token | FL |
Token ID | 3697 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
sterdam | +0.560 |
anco | +0.556 |
ldom | +0.532 |
apest | +0.502 |
merce | +0.501 |
Neg logit contributions | |
PASS | -0.515 |
Musk | -0.490 |
RIS | -0.472 |
FISA | -0.468 |
Route | -0.461 |
Token | Y |
Token ID | 56 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
PASS | +0.262 |
Musk | +0.247 |
RIS | +0.236 |
FISA | +0.234 |
Route | +0.230 |
Neg logit contributions | |
sterdam | -0.394 |
anco | -0.392 |
ldom | -0.377 |
apest | -0.359 |
merce | -0.357 |
Token | Gov |
Token ID | 23774 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
sterdam | +0.295 |
anco | +0.293 |
ldom | +0.278 |
merce | +0.262 |
apest | +0.262 |
Neg logit contributions | |
PASS | -0.287 |
Musk | -0.272 |
RIS | -0.262 |
FISA | -0.260 |
Route | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
sterdam | +0.191 |
anco | +0.191 |
ldom | +0.182 |
apest | +0.171 |
merce | +0.170 |
Neg logit contributions | |
PASS | -0.182 |
Musk | -0.175 |
RIS | -0.168 |
FISA | -0.167 |
Route | -0.165 |
Token | Robert |
Token ID | 5199 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
PASS | +0.206 |
Musk | +0.198 |
RIS | +0.187 |
FISA | +0.187 |
Route | +0.186 |
Neg logit contributions | |
anco | -0.328 |
sterdam | -0.327 |
ldom | -0.316 |
apest | -0.302 |
merce | -0.301 |
Token | F |
Token ID | 376 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
PASS | +0.406 |
Musk | +0.395 |
RIS | +0.370 |
FISA | +0.368 |
Route | +0.366 |
Neg logit contributions | |
sterdam | -0.714 |
anco | -0.703 |
ldom | -0.679 |
merce | -0.654 |
apest | -0.646 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
PASS | +1.100 |
Musk | +1.055 |
FISA | +1.008 |
RIS | +1.008 |
Route | +1.001 |
Neg logit contributions | |
sterdam | -1.203 |
anco | -1.186 |
ldom | -1.137 |
merce | -1.086 |
apest | -1.079 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
PASS | +0.343 |
Musk | +0.323 |
RIS | +0.313 |
FISA | +0.311 |
Route | +0.303 |
Neg logit contributions | |
anco | -0.393 |
sterdam | -0.391 |
ldom | -0.373 |
apest | -0.352 |
merce | -0.348 |
Token | ( |
Token ID | 357 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
anco | +4.585 |
sterdam | +4.569 |
ldom | +4.299 |
Indust | +4.069 |
apest | +4.054 |
Neg logit contributions | |
PASS | -3.675 |
Musk | -3.422 |
FISA | -3.316 |
RIS | -3.299 |
Route | -3.231 |
Token | R |
Token ID | 49 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
PASS | +0.273 |
Musk | +0.255 |
RIS | +0.246 |
FISA | +0.243 |
Route | +0.240 |
Neg logit contributions | |
sterdam | -0.384 |
anco | -0.381 |
ldom | -0.366 |
apest | -0.347 |
merce | -0.346 |
Token | ) |
Token ID | 8 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
PASS | +0.953 |
Musk | +0.911 |
RIS | +0.876 |
FISA | +0.873 |
Route | +0.864 |
Neg logit contributions | |
sterdam | -1.001 |
anco | -0.989 |
ldom | -0.945 |
apest | -0.891 |
merce | -0.887 |
Token | took |
Token ID | 1718 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
PASS | +0.293 |
Musk | +0.282 |
RIS | +0.271 |
FISA | +0.268 |
Route | +0.264 |
Neg logit contributions | |
sterdam | -0.350 |
anco | -0.347 |
ldom | -0.333 |
apest | -0.315 |
merce | -0.313 |
Token | fl |
Token ID | 781 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
sterdam | +1.308 |
anco | +1.303 |
ldom | +1.244 |
apest | +1.177 |
merce | +1.168 |
Neg logit contributions | |
PASS | -1.087 |
Musk | -1.037 |
RIS | -0.997 |
FISA | -0.991 |
Route | -0.972 |
Token | www |
Token ID | 2503 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
sterdam | +1.810 |
anco | +1.805 |
ldom | +1.736 |
apest | +1.626 |
merce | +1.595 |
Neg logit contributions | |
PASS | -1.692 |
Musk | -1.638 |
RIS | -1.578 |
FISA | -1.570 |
Route | -1.537 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
anco | +1.825 |
sterdam | +1.786 |
ldom | +1.707 |
apest | +1.623 |
Indust | +1.567 |
Neg logit contributions | |
PASS | -2.141 |
Musk | -2.057 |
�醒 | -2.047 |
RIS | -2.004 |
FISA | -1.991 |
Token | bel |
Token ID | 6667 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
sterdam | +2.225 |
anco | +2.218 |
ldom | +2.133 |
apest | +2.006 |
merce | +1.996 |
Neg logit contributions | |
PASS | -1.641 |
Musk | -1.560 |
FISA | -1.511 |
RIS | -1.497 |
Route | -1.450 |
Token | fast |
Token ID | 7217 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
anco | +1.481 |
sterdam | +1.453 |
ldom | +1.352 |
apest | +1.251 |
merce | +1.208 |
Neg logit contributions | |
PASS | -2.580 |
Musk | -2.502 |
RIS | -2.464 |
FISA | -2.441 |
�醒 | -2.405 |
Token | te |
Token ID | 660 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
sterdam | +0.755 |
anco | +0.752 |
ldom | +0.703 |
apest | +0.647 |
merce | +0.639 |
Neg logit contributions | |
PASS | -1.223 |
Musk | -1.180 |
RIS | -1.148 |
FISA | -1.143 |
Route | -1.127 |
Token | legraph |
Token ID | 16606 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
anco | +1.039 |
sterdam | +1.037 |
ldom | +0.954 |
apest | +0.845 |
merce | +0.818 |
Neg logit contributions | |
PASS | -2.556 |
Musk | -2.480 |
RIS | -2.428 |
FISA | -2.418 |
Route | -2.376 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
anco | +3.586 |
sterdam | +3.524 |
ldom | +3.390 |
apest | +3.210 |
Indust | +3.059 |
Neg logit contributions | |
PASS | -4.522 |
�醒 | -4.348 |
Musk | -4.345 |
RIS | -4.261 |
FISA | -4.226 |
Token | co |
Token ID | 1073 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anco | +1.390 |
sterdam | +1.382 |
ldom | +1.302 |
apest | +1.217 |
merce | +1.185 |
Neg logit contributions | |
PASS | -1.853 |
Musk | -1.788 |
RIS | -1.733 |
FISA | -1.722 |
Route | -1.695 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
anco | +1.346 |
sterdam | +1.337 |
ldom | +1.271 |
apest | +1.197 |
Indust | +1.167 |
Neg logit contributions | |
PASS | -1.435 |
Musk | -1.376 |
RIS | -1.334 |
FISA | -1.327 |
�醒 | -1.306 |
Token | uk |
Token ID | 2724 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
anco | +1.287 |
sterdam | +1.282 |
ldom | +1.177 |
apest | +1.058 |
merce | +1.030 |
Neg logit contributions | |
PASS | -2.980 |
Musk | -2.888 |
RIS | -2.825 |
FISA | -2.813 |
Route | -2.775 |
Token | / |
Token ID | 14 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
anco | +2.780 |
sterdam | +2.733 |
ldom | +2.628 |
apest | +2.542 |
Indust | +2.465 |
Neg logit contributions | |
PASS | -2.150 |
Musk | -2.046 |
�醒 | -2.013 |
RIS | -1.985 |
FISA | -1.968 |
Token | going |
Token ID | 1016 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
PASS | +0.126 |
Musk | +0.120 |
RIS | +0.115 |
FISA | +0.114 |
Route | +0.111 |
Neg logit contributions | |
sterdam | -0.179 |
anco | -0.179 |
ldom | -0.171 |
apest | -0.163 |
merce | -0.162 |
Token | along |
Token ID | 1863 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
sterdam | +0.569 |
anco | +0.567 |
ldom | +0.543 |
apest | +0.515 |
merce | +0.512 |
Neg logit contributions | |
PASS | -0.408 |
Musk | -0.387 |
RIS | -0.370 |
FISA | -0.368 |
Route | -0.360 |
Token | with |
Token ID | 351 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
PASS | +0.109 |
Musk | +0.104 |
RIS | +0.100 |
FISA | +0.099 |
Route | +0.097 |
Neg logit contributions | |
sterdam | -0.139 |
anco | -0.139 |
ldom | -0.133 |
apest | -0.126 |
merce | -0.125 |
Token | whatever |
Token ID | 4232 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
sterdam | +0.238 |
anco | +0.237 |
ldom | +0.228 |
apest | +0.217 |
merce | +0.215 |
Neg logit contributions | |
PASS | -0.152 |
Musk | -0.144 |
RIS | -0.137 |
FISA | -0.136 |
Route | -0.133 |
Token | gast |
Token ID | 21956 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
sterdam | +1.089 |
anco | +1.085 |
ldom | +1.037 |
apest | +0.976 |
Indust | +0.976 |
Neg logit contributions | |
PASS | -0.851 |
Musk | -0.797 |
RIS | -0.775 |
FISA | -0.772 |
�醒 | -0.754 |
Token | ron |
Token ID | 1313 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
sterdam | +1.309 |
anco | +1.302 |
ldom | +1.236 |
apest | +1.158 |
merce | +1.143 |
Neg logit contributions | |
PASS | -1.477 |
Musk | -1.418 |
RIS | -1.372 |
FISA | -1.367 |
Route | -1.340 |
Token | omic |
Token ID | 10179 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
anco | +2.955 |
sterdam | +2.942 |
ldom | +2.783 |
apest | +2.455 |
merce | +2.417 |
Neg logit contributions | |
PASS | -5.305 |
Musk | -5.064 |
RIS | -4.995 |
FISA | -4.988 |
Route | -4.870 |
Token | project |
Token ID | 1628 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
sterdam | +1.428 |
anco | +1.422 |
ldom | +1.353 |
apest | +1.274 |
Indust | +1.263 |
Neg logit contributions | |
PASS | -1.307 |
Musk | -1.230 |
RIS | -1.200 |
FISA | -1.195 |
@# | -1.172 |
Token | her |
Token ID | 607 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
sterdam | +0.758 |
anco | +0.755 |
ldom | +0.720 |
apest | +0.680 |
merce | +0.675 |
Neg logit contributions | |
PASS | -0.618 |
Musk | -0.582 |
RIS | -0.562 |
FISA | -0.559 |
Route | -0.548 |
Token | husband |
Token ID | 5229 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
PASS | +0.031 |
Musk | +0.029 |
RIS | +0.028 |
FISA | +0.028 |
Route | +0.028 |
Neg logit contributions | |
sterdam | -0.034 |
anco | -0.034 |
ldom | -0.033 |
apest | -0.031 |
merce | -0.031 |
Token | wants |
Token ID | 3382 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
sterdam | +0.493 |
anco | +0.492 |
ldom | +0.467 |
apest | +0.440 |
merce | +0.438 |
Neg logit contributions | |
PASS | -0.427 |
Musk | -0.404 |
RIS | -0.391 |
FISA | -0.389 |
Route | -0.381 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sterdam | +0.100 |
anco | +0.099 |
ldom | +0.095 |
apest | +0.090 |
merce | +0.090 |
Neg logit contributions | |
PASS | -0.075 |
Musk | -0.071 |
RIS | -0.068 |
FISA | -0.068 |
Route | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
PASS | +0.688 |
Musk | +0.657 |
RIS | +0.631 |
FISA | +0.623 |
Route | +0.619 |
Neg logit contributions | |
sterdam | -0.854 |
anco | -0.844 |
ldom | -0.813 |
apest | -0.772 |
merce | -0.768 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
PASS | +0.291 |
Musk | +0.277 |
RIS | +0.267 |
FISA | +0.265 |
Route | +0.260 |
Neg logit contributions | |
sterdam | -0.350 |
anco | -0.348 |
ldom | -0.333 |
apest | -0.314 |
merce | -0.313 |
Token | yards |
Token ID | 5695 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
PASS | +0.117 |
Musk | +0.112 |
RIS | +0.109 |
FISA | +0.108 |
Route | +0.106 |
Neg logit contributions | |
sterdam | -0.114 |
anco | -0.113 |
ldom | -0.107 |
apest | -0.101 |
merce | -0.100 |
Token | per |
Token ID | 583 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
sterdam | +0.143 |
anco | +0.142 |
ldom | +0.136 |
apest | +0.130 |
merce | +0.129 |
Neg logit contributions | |
PASS | -0.094 |
Musk | -0.089 |
RIS | -0.085 |
FISA | -0.085 |
Route | -0.083 |
Token | carry |
Token ID | 3283 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
PASS | +0.815 |
Musk | +0.785 |
RIS | +0.763 |
FISA | +0.754 |
Route | +0.750 |
Neg logit contributions | |
sterdam | -0.650 |
anco | -0.644 |
ldom | -0.611 |
apest | -0.572 |
merce | -0.569 |
Token | ) |
Token ID | 8 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
anco | +3.884 |
sterdam | +3.850 |
ldom | +3.657 |
apest | +3.401 |
merce | +3.361 |
Neg logit contributions | |
PASS | -4.184 |
Musk | -3.975 |
FISA | -3.840 |
RIS | -3.826 |
�醒 | -3.758 |
Token | and |
Token ID | 290 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
sterdam | +0.655 |
anco | +0.652 |
ldom | +0.623 |
apest | +0.590 |
merce | +0.585 |
Neg logit contributions | |
PASS | -0.542 |
Musk | -0.517 |
RIS | -0.498 |
FISA | -0.494 |
Route | -0.485 |
Token | another |
Token ID | 1194 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
anco | +0.519 |
sterdam | +0.518 |
ldom | +0.496 |
apest | +0.469 |
merce | +0.465 |
Neg logit contributions | |
PASS | -0.364 |
Musk | -0.345 |
RIS | -0.330 |
FISA | -0.329 |
Route | -0.321 |
Token | 388 |
Token ID | 43550 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
PASS | +0.797 |
Musk | +0.750 |
RIS | +0.718 |
FISA | +0.713 |
Route | +0.700 |
Neg logit contributions | |
sterdam | -1.262 |
anco | -1.255 |
ldom | -1.206 |
apest | -1.155 |
merce | -1.149 |
Token | yards |
Token ID | 5695 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
PASS | +0.324 |
Musk | +0.309 |
RIS | +0.298 |
FISA | +0.295 |
Route | +0.291 |
Neg logit contributions | |
sterdam | -0.379 |
anco | -0.375 |
ldom | -0.360 |
apest | -0.342 |
merce | -0.340 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
sterdam | +0.524 |
anco | +0.524 |
ldom | +0.502 |
apest | +0.477 |
merce | +0.474 |
Neg logit contributions | |
PASS | -0.331 |
Musk | -0.312 |
RIS | -0.297 |
FISA | -0.296 |
Route | -0.288 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
PASS | +0.388 |
Musk | +0.371 |
RIS | +0.356 |
FISA | +0.352 |
Route | +0.350 |
Neg logit contributions | |
sterdam | -0.465 |
anco | -0.460 |
ldom | -0.442 |
apest | -0.419 |
merce | -0.416 |
Token | 4 |
Token ID | 19 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
PASS | +0.374 |
Musk | +0.356 |
RIS | +0.342 |
FISA | +0.340 |
Route | +0.334 |
Neg logit contributions | |
sterdam | -0.451 |
anco | -0.449 |
ldom | -0.429 |
apest | -0.405 |
merce | -0.405 |
Token | yards |
Token ID | 5695 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
sterdam | +0.510 |
anco | +0.508 |
ldom | +0.481 |
apest | +0.451 |
merce | +0.447 |
Neg logit contributions | |
PASS | -0.569 |
Musk | -0.546 |
RIS | -0.528 |
FISA | -0.525 |
Route | -0.517 |
Token | per |
Token ID | 583 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
sterdam | +0.068 |
anco | +0.067 |
ldom | +0.065 |
apest | +0.062 |
merce | +0.061 |
Neg logit contributions | |
PASS | -0.043 |
Musk | -0.041 |
RIS | -0.039 |
FISA | -0.039 |
Route | -0.038 |
Token | carry |
Token ID | 3283 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
PASS | +1.043 |
Musk | +1.006 |
RIS | +0.976 |
Route | +0.964 |
FISA | +0.963 |
Neg logit contributions | |
sterdam | -0.840 |
anco | -0.829 |
ldom | -0.790 |
apest | -0.739 |
merce | -0.738 |
Token | . |
Token ID | 13 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
anco | +4.234 |
sterdam | +4.197 |
ldom | +4.001 |
apest | +3.746 |
merce | +3.699 |
Neg logit contributions | |
PASS | -3.790 |
Musk | -3.580 |
FISA | -3.440 |
RIS | -3.420 |
@# | -3.375 |
Token | His |
Token ID | 2399 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
anco | +0.473 |
sterdam | +0.472 |
ldom | +0.451 |
apest | +0.429 |
Indust | +0.424 |
Neg logit contributions | |
PASS | -0.355 |
Musk | -0.335 |
RIS | -0.322 |
FISA | -0.320 |
Route | -0.312 |
Token | follow |
Token ID | 1061 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
sterdam | +1.084 |
anco | +1.084 |
ldom | +1.036 |
apest | +0.982 |
merce | +0.972 |
Neg logit contributions | |
PASS | -0.815 |
Musk | -0.775 |
RIS | -0.742 |
FISA | -0.737 |
Route | -0.720 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
sterdam | +1.169 |
anco | +1.166 |
ldom | +1.116 |
apest | +1.061 |
merce | +1.054 |
Neg logit contributions | |
PASS | -0.776 |
Musk | -0.734 |
RIS | -0.702 |
FISA | -0.697 |
Route | -0.681 |
Token | up |
Token ID | 929 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
sterdam | +1.005 |
anco | +1.003 |
ldom | +0.961 |
apest | +0.917 |
merce | +0.911 |
Neg logit contributions | |
PASS | -0.590 |
Musk | -0.556 |
RIS | -0.531 |
FISA | -0.526 |
Route | -0.513 |
Token | actually |
Token ID | 1682 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
sterdam | +0.375 |
anco | +0.374 |
ldom | +0.358 |
apest | +0.340 |
merce | +0.338 |
Neg logit contributions | |
PASS | -0.260 |
Musk | -0.247 |
RIS | -0.236 |
FISA | -0.235 |
Route | -0.229 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
sterdam | +0.560 |
anco | +0.558 |
ldom | +0.533 |
apest | +0.505 |
merce | +0.501 |
Neg logit contributions | |
PASS | -0.441 |
Musk | -0.418 |
RIS | -0.401 |
FISA | -0.399 |
Route | -0.392 |
Token | , |
Token ID | 11 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
sterdam | +1.684 |
anco | +1.677 |
ldom | +1.604 |
apest | +1.519 |
merce | +1.510 |
Neg logit contributions | |
PASS | -1.261 |
Musk | -1.191 |
RIS | -1.145 |
FISA | -1.137 |
Route | -1.114 |
Token | how |
Token ID | 703 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
sterdam | +0.401 |
anco | +0.400 |
ldom | +0.384 |
apest | +0.365 |
merce | +0.362 |
Neg logit contributions | |
PASS | -0.277 |
Musk | -0.264 |
RIS | -0.252 |
FISA | -0.251 |
Route | -0.245 |
Token | non |
Token ID | 1729 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
PASS | +0.414 |
Musk | +0.395 |
RIS | +0.378 |
FISA | +0.376 |
Route | +0.368 |
Neg logit contributions | |
sterdam | -0.553 |
anco | -0.553 |
ldom | -0.529 |
apest | -0.503 |
merce | -0.499 |
Token | chal |
Token ID | 38009 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
PASS | +1.584 |
Musk | +1.507 |
RIS | +1.445 |
FISA | +1.436 |
ACC | +1.413 |
Neg logit contributions | |
anco | -2.098 |
sterdam | -2.092 |
ldom | -2.013 |
apest | -1.889 |
merce | -1.880 |
Token | antly |
Token ID | 3875 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
anco | +4.745 |
sterdam | +4.715 |
ldom | +4.493 |
apest | +4.336 |
etrical | +4.237 |
Neg logit contributions | |
PASS | -3.349 |
Musk | -3.050 |
FISA | -3.037 |
RIS | -3.032 |
@# | -2.868 |
Token | some |
Token ID | 617 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
sterdam | +0.980 |
anco | +0.977 |
ldom | +0.935 |
apest | +0.888 |
merce | +0.882 |
Neg logit contributions | |
PASS | -0.709 |
Musk | -0.673 |
RIS | -0.645 |
FISA | -0.641 |
Route | -0.628 |
Token | say |
Token ID | 910 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
PASS | +0.418 |
Musk | +0.401 |
RIS | +0.385 |
FISA | +0.385 |
Route | +0.378 |
Neg logit contributions | |
sterdam | -0.435 |
anco | -0.435 |
ldom | -0.414 |
apest | -0.390 |
merce | -0.388 |
Token | that |
Token ID | 326 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
PASS | +0.454 |
Musk | +0.432 |
RIS | +0.413 |
FISA | +0.412 |
Route | +0.403 |
Neg logit contributions | |
anco | -0.636 |
sterdam | -0.635 |
ldom | -0.608 |
apest | -0.579 |
merce | -0.574 |
Token | it |
Token ID | 340 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
sterdam | +0.377 |
anco | +0.377 |
ldom | +0.361 |
apest | +0.343 |
merce | +0.340 |
Neg logit contributions | |
PASS | -0.268 |
Musk | -0.255 |
RIS | -0.244 |
FISA | -0.243 |
Route | -0.238 |
Token | group |
Token ID | 1448 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
sterdam | +0.899 |
anco | +0.897 |
ldom | +0.853 |
apest | +0.803 |
merce | +0.797 |
Neg logit contributions | |
PASS | -0.866 |
Musk | -0.829 |
RIS | -0.800 |
FISA | -0.795 |
Route | -0.782 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
sterdam | +0.916 |
anco | +0.915 |
ldom | +0.877 |
apest | +0.834 |
merce | +0.830 |
Neg logit contributions | |
PASS | -0.624 |
Musk | -0.594 |
RIS | -0.570 |
FISA | -0.564 |
Route | -0.555 |
Token | is |
Token ID | 318 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
PASS | +0.688 |
Musk | +0.657 |
RIS | +0.634 |
FISA | +0.622 |
Route | +0.621 |
Neg logit contributions | |
anco | -0.885 |
sterdam | -0.882 |
ldom | -0.843 |
apest | -0.806 |
merce | -0.802 |
Token | Being |
Token ID | 11204 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
PASS | +0.086 |
Musk | +0.078 |
RIS | +0.072 |
FISA | +0.072 |
Route | +0.069 |
Neg logit contributions | |
sterdam | -0.265 |
anco | -0.264 |
ldom | -0.256 |
apest | -0.246 |
merce | -0.244 |
Token | Sl |
Token ID | 3454 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
PASS | +0.330 |
Musk | +0.312 |
RIS | +0.298 |
FISA | +0.297 |
Route | +0.290 |
Neg logit contributions | |
sterdam | -0.492 |
anco | -0.491 |
ldom | -0.470 |
apest | -0.447 |
merce | -0.444 |
Token | aughtered |
Token ID | 32734 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
sterdam | +0.272 |
anco | +0.269 |
ldom | +0.234 |
apest | +0.195 |
merce | +0.190 |
Neg logit contributions | |
PASS | -1.132 |
Musk | -1.102 |
RIS | -1.079 |
FISA | -1.075 |
Route | -1.064 |
Token | Sil |
Token ID | 4243 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
sterdam | +2.908 |
anco | +2.889 |
ldom | +2.678 |
Indust | +2.560 |
pains | +2.419 |
Neg logit contributions | |
PASS | -5.006 |
Musk | -4.677 |
RIS | -4.639 |
FISA | -4.631 |
�醒 | -4.538 |
Token | ently |
Token ID | 1473 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
PASS | +0.661 |
Musk | +0.643 |
RIS | +0.622 |
FISA | +0.621 |
Route | +0.615 |
Neg logit contributions | |
sterdam | -0.389 |
anco | -0.385 |
ldom | -0.359 |
apest | -0.330 |
merce | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
sterdam | +0.281 |
anco | +0.279 |
ldom | +0.268 |
apest | +0.253 |
merce | +0.253 |
Neg logit contributions | |
PASS | -0.226 |
Musk | -0.216 |
RIS | -0.207 |
FISA | -0.206 |
Route | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
PASS | +0.010 |
Musk | +0.009 |
RIS | +0.009 |
FISA | +0.009 |
Route | +0.009 |
Neg logit contributions | |
sterdam | -0.013 |
anco | -0.013 |
ldom | -0.012 |
merce | -0.012 |
apest | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
anco | +0.810 |
sterdam | +0.803 |
ldom | +0.766 |
apest | +0.729 |
Indust | +0.714 |
Neg logit contributions | |
PASS | -0.715 |
Musk | -0.682 |
RIS | -0.658 |
FISA | -0.654 |
�醒 | -0.650 |
Token | the |
Token ID | 262 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
PASS | +0.932 |
Musk | +0.904 |
RIS | +0.866 |
FISA | +0.858 |
Route | +0.847 |
Neg logit contributions | |
anco | -1.038 |
sterdam | -1.034 |
ldom | -0.983 |
apest | -0.936 |
merce | -0.927 |
Token | architecture |
Token ID | 10959 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
PASS | +0.473 |
Musk | +0.458 |
RIS | +0.441 |
FISA | +0.436 |
Route | +0.432 |
Neg logit contributions | |
anco | -0.520 |
sterdam | -0.520 |
ldom | -0.495 |
merce | -0.468 |
apest | -0.467 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
PASS | +0.050 |
Musk | +0.047 |
RIS | +0.045 |
FISA | +0.045 |
Route | +0.044 |
Neg logit contributions | |
sterdam | -0.060 |
anco | -0.060 |
ldom | -0.057 |
apest | -0.054 |
merce | -0.054 |
Token | nature |
Token ID | 3450 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
PASS | +0.162 |
Musk | +0.157 |
RIS | +0.149 |
FISA | +0.148 |
Route | +0.147 |
Neg logit contributions | |
sterdam | -0.199 |
anco | -0.199 |
ldom | -0.190 |
apest | -0.180 |
merce | -0.178 |
Token | me |
Token ID | 502 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
sterdam | +1.495 |
anco | +1.488 |
ldom | +1.419 |
apest | +1.336 |
merce | +1.323 |
Neg logit contributions | |
PASS | -1.285 |
Musk | -1.220 |
RIS | -1.178 |
FISA | -1.174 |
Route | -1.147 |
Token | ld |
Token ID | 335 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
PASS | +0.053 |
Musk | +0.051 |
RIS | +0.049 |
FISA | +0.049 |
Route | +0.048 |
Neg logit contributions | |
sterdam | -0.041 |
anco | -0.041 |
ldom | -0.039 |
apest | -0.036 |
merce | -0.036 |
Token | into |
Token ID | 656 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
anco | +4.162 |
sterdam | +4.131 |
ldom | +3.917 |
apest | +3.672 |
pains | +3.639 |
Neg logit contributions | |
PASS | -3.684 |
Musk | -3.496 |
RIS | -3.367 |
FISA | -3.361 |
Route | -3.279 |
Token | one |
Token ID | 530 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
PASS | +0.503 |
Musk | +0.486 |
RIS | +0.467 |
FISA | +0.462 |
Route | +0.458 |
Neg logit contributions | |
anco | -0.590 |
sterdam | -0.589 |
ldom | -0.562 |
apest | -0.534 |
merce | -0.530 |
Token | ($ |
Token ID | 7198 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
PASS | +0.416 |
Musk | +0.400 |
RIS | +0.386 |
FISA | +0.382 |
Route | +0.376 |
Neg logit contributions | |
anco | -0.446 |
sterdam | -0.446 |
ldom | -0.424 |
apest | -0.402 |
merce | -0.399 |
Token | 80 |
Token ID | 1795 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
PASS | +0.511 |
Musk | +0.481 |
RIS | +0.459 |
FISA | +0.454 |
Route | +0.447 |
Neg logit contributions | |
sterdam | -0.751 |
anco | -0.744 |
ldom | -0.715 |
merce | -0.679 |
apest | -0.677 |
Token | , |
Token ID | 11 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
sterdam | +1.699 |
anco | +1.693 |
ldom | +1.620 |
apest | +1.535 |
merce | +1.525 |
Neg logit contributions | |
PASS | -1.305 |
Musk | -1.243 |
RIS | -1.192 |
FISA | -1.182 |
Route | -1.161 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
anco | +0.775 |
sterdam | +0.775 |
ldom | +0.746 |
apest | +0.713 |
merce | +0.708 |
Neg logit contributions | |
PASS | -0.356 |
Musk | -0.331 |
RIS | -0.310 |
FISA | -0.310 |
Route | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
PASS | +0.373 |
Musk | +0.357 |
RIS | +0.344 |
FISA | +0.341 |
Route | +0.338 |
Neg logit contributions | |
sterdam | -0.412 |
anco | -0.405 |
ldom | -0.391 |
merce | -0.369 |
apest | -0.369 |
Token | 4 |
Token ID | 19 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
PASS | +0.365 |
Musk | +0.346 |
RIS | +0.333 |
FISA | +0.330 |
Route | +0.326 |
Neg logit contributions | |
sterdam | -0.437 |
anco | -0.434 |
ldom | -0.415 |
merce | -0.393 |
apest | -0.391 |
Token | yards |
Token ID | 5695 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
sterdam | +0.636 |
anco | +0.633 |
ldom | +0.601 |
apest | +0.564 |
merce | +0.560 |
Neg logit contributions | |
PASS | -0.673 |
Musk | -0.645 |
RIS | -0.623 |
FISA | -0.619 |
Route | -0.610 |
Token | per |
Token ID | 583 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
sterdam | +0.136 |
anco | +0.135 |
ldom | +0.130 |
apest | +0.124 |
merce | +0.123 |
Neg logit contributions | |
PASS | -0.085 |
Musk | -0.080 |
RIS | -0.077 |
FISA | -0.076 |
Route | -0.074 |
Token | carry |
Token ID | 3283 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
PASS | +0.532 |
Musk | +0.511 |
RIS | +0.495 |
FISA | +0.491 |
Route | +0.487 |
Neg logit contributions | |
sterdam | -0.437 |
anco | -0.434 |
ldom | -0.411 |
apest | -0.385 |
merce | -0.382 |
Token | again |
Token ID | 757 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anco | +3.948 |
sterdam | +3.925 |
ldom | +3.758 |
apest | +3.499 |
merce | +3.463 |
Neg logit contributions | |
PASS | -3.780 |
Musk | -3.575 |
FISA | -3.451 |
RIS | -3.429 |
@# | -3.397 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
PASS | +0.688 |
Musk | +0.657 |
RIS | +0.635 |
FISA | +0.623 |
ACC | +0.616 |
Neg logit contributions | |
sterdam | -0.888 |
anco | -0.879 |
ldom | -0.840 |
merce | -0.798 |
apest | -0.797 |
Token | Then |
Token ID | 3244 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
anco | +0.020 |
sterdam | +0.020 |
ldom | +0.019 |
apest | +0.018 |
Indust | +0.018 |
Neg logit contributions | |
PASS | -0.016 |
Musk | -0.015 |
RIS | -0.014 |
FISA | -0.014 |
Route | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
PASS | +0.520 |
Musk | +0.493 |
RIS | +0.471 |
FISA | +0.467 |
Route | +0.458 |
Neg logit contributions | |
sterdam | -0.771 |
anco | -0.768 |
ldom | -0.737 |
apest | -0.701 |
merce | -0.698 |
Token | in |
Token ID | 287 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
PASS | +0.325 |
Musk | +0.309 |
RIS | +0.296 |
FISA | +0.294 |
Route | +0.288 |
Neg logit contributions | |
sterdam | -0.444 |
anco | -0.442 |
ldom | -0.424 |
apest | -0.402 |
merce | -0.400 |
Token | heating |
Token ID | 16930 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
sterdam | +0.881 |
anco | +0.879 |
ldom | +0.839 |
apest | +0.801 |
Indust | +0.787 |
Neg logit contributions | |
PASS | -0.660 |
Musk | -0.623 |
FISA | -0.597 |
RIS | -0.596 |
Route | -0.582 |
Token | up |
Token ID | 510 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
PASS | +0.078 |
Musk | +0.074 |
RIS | +0.070 |
FISA | +0.069 |
Route | +0.068 |
Neg logit contributions | |
sterdam | -0.138 |
anco | -0.138 |
ldom | -0.133 |
apest | -0.127 |
merce | -0.127 |
Token | in |
Token ID | 287 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
sterdam | +1.259 |
anco | +1.255 |
ldom | +1.201 |
apest | +1.139 |
merce | +1.131 |
Neg logit contributions | |
PASS | -0.939 |
Musk | -0.893 |
RIS | -0.856 |
FISA | -0.850 |
Route | -0.833 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
PASS | +0.235 |
Musk | +0.226 |
RIS | +0.215 |
FISA | +0.214 |
Route | +0.210 |
Neg logit contributions | |
sterdam | -0.351 |
anco | -0.350 |
ldom | -0.336 |
apest | -0.320 |
merce | -0.318 |
Token | Irish |
Token ID | 8685 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
sterdam | +0.014 |
anco | +0.014 |
ldom | +0.014 |
apest | +0.013 |
merce | +0.013 |
Neg logit contributions | |
PASS | -0.011 |
Musk | -0.010 |
RIS | -0.010 |
FISA | -0.010 |
Route | -0.010 |
Token | craft |
Token ID | 5977 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
sterdam | +1.119 |
anco | +1.117 |
ldom | +1.059 |
apest | +0.998 |
merce | +0.991 |
Neg logit contributions | |
PASS | -1.128 |
Musk | -1.081 |
RIS | -1.043 |
FISA | -1.037 |
Route | -1.022 |
Token | beer |
Token ID | 6099 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
sterdam | +3.257 |
anco | +3.171 |
ldom | +2.998 |
merce | +2.772 |
apest | +2.764 |
Neg logit contributions | |
PASS | -4.561 |
Musk | -4.340 |
RIS | -4.258 |
FISA | -4.240 |
�醒 | -4.169 |
Token | industry |
Token ID | 2831 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
sterdam | +1.118 |
anco | +1.114 |
ldom | +1.063 |
apest | +1.006 |
merce | +0.997 |
Neg logit contributions | |
PASS | -0.924 |
Musk | -0.878 |
RIS | -0.846 |
FISA | -0.839 |
Route | -0.822 |
Token | right |
Token ID | 826 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
sterdam | +0.711 |
anco | +0.709 |
ldom | +0.678 |
apest | +0.642 |
merce | +0.637 |
Neg logit contributions | |
PASS | -0.581 |
Musk | -0.555 |
RIS | -0.533 |
FISA | -0.529 |
Route | -0.520 |
Token | now |
Token ID | 783 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
PASS | +0.898 |
Musk | +0.841 |
RIS | +0.782 |
FISA | +0.765 |
Route | +0.757 |
Neg logit contributions | |
sterdam | -2.312 |
anco | -2.312 |
ldom | -2.238 |
apest | -2.159 |
merce | -2.155 |
Token | as |
Token ID | 355 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
PASS | +1.079 |
Musk | +1.045 |
RIS | +0.994 |
FISA | +0.983 |
Route | +0.977 |
Neg logit contributions | |
sterdam | -1.358 |
anco | -1.358 |
ldom | -1.302 |
apest | -1.232 |
merce | -1.229 |
Token | . |
Token ID | 13 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
sterdam | +0.889 |
anco | +0.886 |
ldom | +0.840 |
apest | +0.792 |
merce | +0.782 |
Neg logit contributions | |
PASS | -0.908 |
Musk | -0.866 |
RIS | -0.838 |
FISA | -0.833 |
Route | -0.817 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
sterdam | +0.049 |
anco | +0.049 |
ldom | +0.046 |
apest | +0.044 |
merce | +0.043 |
Neg logit contributions | |
PASS | -0.041 |
Musk | -0.039 |
RIS | -0.037 |
FISA | -0.037 |
Route | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
PASS | +0.183 |
Musk | +0.174 |
RIS | +0.168 |
FISA | +0.167 |
Route | +0.163 |
Neg logit contributions | |
anco | -0.220 |
sterdam | -0.220 |
ldom | -0.210 |
apest | -0.199 |
merce | -0.196 |
Token | With |
Token ID | 3152 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
PASS | +0.110 |
Musk | +0.104 |
RIS | +0.100 |
FISA | +0.099 |
Route | +0.097 |
Neg logit contributions | |
sterdam | -0.136 |
anco | -0.135 |
ldom | -0.129 |
merce | -0.122 |
apest | -0.122 |
Token | Josh |
Token ID | 8518 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
sterdam | +0.876 |
anco | +0.873 |
ldom | +0.836 |
apest | +0.792 |
merce | +0.785 |
Neg logit contributions | |
PASS | -0.619 |
Musk | -0.587 |
RIS | -0.561 |
FISA | -0.559 |
Route | -0.544 |
Token | Doct |
Token ID | 32155 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
PASS | +0.503 |
Musk | +0.475 |
RIS | +0.451 |
FISA | +0.446 |
Route | +0.439 |
Neg logit contributions | |
anco | -0.872 |
sterdam | -0.872 |
ldom | -0.838 |
apest | -0.800 |
merce | -0.798 |
Token | son |
Token ID | 1559 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
anco | +3.028 |
sterdam | +2.951 |
ldom | +2.724 |
pains | +2.455 |
roma | +2.447 |
Neg logit contributions | |
PASS | -4.890 |
Musk | -4.676 |
FISA | -4.597 |
RIS | -4.535 |
�醒 | -4.478 |
Token | finally |
Token ID | 3443 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
PASS | +0.072 |
Musk | +0.068 |
RIS | +0.065 |
FISA | +0.065 |
Route | +0.064 |
Neg logit contributions | |
sterdam | -0.104 |
anco | -0.104 |
ldom | -0.099 |
apest | -0.094 |
merce | -0.093 |
Token | becoming |
Token ID | 5033 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
anco | +0.459 |
sterdam | +0.458 |
ldom | +0.438 |
apest | +0.414 |
merce | +0.411 |
Neg logit contributions | |
PASS | -0.318 |
Musk | -0.299 |
FISA | -0.284 |
RIS | -0.284 |
Route | -0.278 |
Token | a |
Token ID | 257 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
sterdam | +0.848 |
anco | +0.847 |
ldom | +0.807 |
apest | +0.760 |
Indust | +0.752 |
Neg logit contributions | |
PASS | -0.724 |
Musk | -0.687 |
RIS | -0.660 |
FISA | -0.657 |
Route | -0.644 |
Token | force |
Token ID | 2700 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
sterdam | +0.471 |
anco | +0.470 |
ldom | +0.449 |
apest | +0.421 |
Indust | +0.417 |
Neg logit contributions | |
PASS | -0.408 |
Musk | -0.388 |
RIS | -0.371 |
FISA | -0.369 |
Route | -0.362 |
Token | era |
Token ID | 8607 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
sterdam | +0.478 |
anco | +0.477 |
ldom | +0.440 |
apest | +0.397 |
merce | +0.392 |
Neg logit contributions | |
PASS | -1.015 |
Musk | -0.985 |
RIS | -0.962 |
FISA | -0.956 |
Route | -0.945 |
Token | standard |
Token ID | 3210 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
PASS | +1.136 |
Musk | +1.081 |
RIS | +1.041 |
FISA | +1.036 |
Route | +1.014 |
Neg logit contributions | |
sterdam | -1.498 |
anco | -1.494 |
ldom | -1.429 |
apest | -1.356 |
merce | -1.348 |
Token | of |
Token ID | 286 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
PASS | +0.844 |
Musk | +0.808 |
RIS | +0.775 |
FISA | +0.773 |
Route | +0.757 |
Neg logit contributions | |
sterdam | -1.016 |
anco | -1.013 |
ldom | -0.968 |
apest | -0.921 |
merce | -0.912 |
Token | " |
Token ID | 366 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
sterdam | +0.059 |
anco | +0.059 |
ldom | +0.057 |
apest | +0.053 |
merce | +0.053 |
Neg logit contributions | |
PASS | -0.045 |
Musk | -0.043 |
RIS | -0.041 |
FISA | -0.040 |
Route | -0.040 |
Token | prep |
Token ID | 46012 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
PASS | +0.480 |
Musk | +0.453 |
RIS | +0.435 |
FISA | +0.433 |
Route | +0.423 |
Neg logit contributions | |
sterdam | -0.655 |
anco | -0.653 |
ldom | -0.624 |
apest | -0.593 |
merce | -0.589 |
Token | onder |
Token ID | 8623 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
sterdam | +0.518 |
anco | +0.513 |
ldom | +0.490 |
apest | +0.468 |
merce | +0.465 |
Neg logit contributions | |
PASS | -0.392 |
Musk | -0.374 |
RIS | -0.361 |
FISA | -0.355 |
ACC | -0.350 |
Token | ance |
Token ID | 590 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
anco | +3.452 |
sterdam | +3.369 |
ldom | +3.231 |
apest | +3.000 |
pains | +2.964 |
Neg logit contributions | |
PASS | -4.291 |
Musk | -4.067 |
RIS | -3.929 |
FISA | -3.917 |
Route | -3.880 |
Token | of |
Token ID | 286 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
sterdam | +0.947 |
anco | +0.947 |
ldom | +0.901 |
apest | +0.849 |
merce | +0.841 |
Neg logit contributions | |
PASS | -0.860 |
Musk | -0.820 |
RIS | -0.789 |
FISA | -0.783 |
Route | -0.771 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
sterdam | +0.393 |
anco | +0.387 |
ldom | +0.373 |
merce | +0.352 |
apest | +0.352 |
Neg logit contributions | |
PASS | -0.304 |
Musk | -0.291 |
RIS | -0.282 |
FISA | -0.280 |
ACC | -0.274 |
Token | evidence |
Token ID | 2370 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
PASS | +0.073 |
Musk | +0.070 |
RIS | +0.067 |
FISA | +0.067 |
ACC | +0.066 |
Neg logit contributions | |
sterdam | -0.082 |
anco | -0.081 |
ldom | -0.077 |
merce | -0.073 |
apest | -0.073 |
Token | ." |
Token ID | 526 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
PASS | +0.145 |
Musk | +0.138 |
RIS | +0.133 |
FISA | +0.133 |
Route | +0.130 |
Neg logit contributions | |
sterdam | -0.170 |
anco | -0.169 |
ldom | -0.161 |
apest | -0.153 |
merce | -0.152 |
Token | said |
Token ID | 531 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
PASS | +0.301 |
Musk | +0.289 |
RIS | +0.278 |
FISA | +0.276 |
Route | +0.272 |
Neg logit contributions | |
sterdam | -0.315 |
anco | -0.314 |
ldom | -0.299 |
apest | -0.281 |
merce | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
sterdam | +0.658 |
anco | +0.657 |
ldom | +0.623 |
apest | +0.585 |
merce | +0.581 |
Neg logit contributions | |
PASS | -0.640 |
Musk | -0.609 |
RIS | -0.587 |
FISA | -0.586 |
Route | -0.575 |
Token | " |
Token ID | 366 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
anco | +0.656 |
sterdam | +0.654 |
ldom | +0.628 |
apest | +0.603 |
Indust | +0.597 |
Neg logit contributions | |
PASS | -0.342 |
Musk | -0.315 |
RIS | -0.299 |
FISA | -0.297 |
@# | -0.289 |
Token | I |
Token ID | 40 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
PASS | +0.375 |
Musk | +0.356 |
RIS | +0.342 |
FISA | +0.340 |
Route | +0.334 |
Neg logit contributions | |
sterdam | -0.449 |
anco | -0.446 |
ldom | -0.427 |
merce | -0.402 |
apest | -0.402 |
Token | love |
Token ID | 1842 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
PASS | +0.188 |
Musk | +0.178 |
RIS | +0.171 |
FISA | +0.170 |
Route | +0.167 |
Neg logit contributions | |
sterdam | -0.231 |
anco | -0.231 |
ldom | -0.220 |
apest | -0.208 |
merce | -0.207 |
Token | Hels |
Token ID | 33889 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
PASS | +0.326 |
Musk | +0.310 |
RIS | +0.297 |
FISA | +0.295 |
Route | +0.289 |
Neg logit contributions | |
sterdam | -0.459 |
anco | -0.457 |
ldom | -0.439 |
apest | -0.416 |
merce | -0.414 |
Token | ing |
Token ID | 278 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
anco | +3.582 |
sterdam | +3.538 |
ldom | +3.365 |
apest | +3.186 |
Indust | +3.162 |
Neg logit contributions | |
PASS | -4.040 |
FISA | -3.802 |
Musk | -3.742 |
RIS | -3.699 |
�醒 | -3.654 |
Token | borg |
Token ID | 23297 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
PASS | +0.828 |
Musk | +0.788 |
RIS | +0.742 |
Route | +0.722 |
FISA | +0.719 |
Neg logit contributions | |
anco | -1.661 |
sterdam | -1.653 |
ldom | -1.590 |
merce | -1.528 |
apest | -1.512 |
Token | and |
Token ID | 290 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
sterdam | +1.773 |
anco | +1.768 |
ldom | +1.690 |
apest | +1.600 |
merce | +1.592 |
Neg logit contributions | |
PASS | -1.381 |
Musk | -1.318 |
RIS | -1.264 |
FISA | -1.253 |
Route | -1.231 |
Token | Sweden |
Token ID | 10710 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
sterdam | +0.284 |
anco | +0.284 |
ldom | +0.272 |
apest | +0.258 |
merce | +0.257 |
Neg logit contributions | |
PASS | -0.198 |
Musk | -0.188 |
RIS | -0.180 |
FISA | -0.178 |
Route | -0.175 |
Token | , |
Token ID | 11 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
sterdam | +1.444 |
anco | +1.440 |
ldom | +1.375 |
apest | +1.301 |
merce | +1.291 |
Neg logit contributions | |
PASS | -1.178 |
Musk | -1.122 |
RIS | -1.078 |
FISA | -1.071 |
Route | -1.051 |
Token | enemy |
Token ID | 4472 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
PASS | +0.426 |
Musk | +0.404 |
RIS | +0.386 |
FISA | +0.383 |
Route | +0.375 |
Neg logit contributions | |
sterdam | -0.647 |
anco | -0.645 |
ldom | -0.619 |
apest | -0.588 |
merce | -0.585 |
Token | minion |
Token ID | 28365 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
anco | +0.802 |
sterdam | +0.801 |
ldom | +0.770 |
apest | +0.740 |
Indust | +0.731 |
Neg logit contributions | |
PASS | -0.372 |
Musk | -0.343 |
RIS | -0.325 |
FISA | -0.323 |
Route | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
PASS | +0.775 |
Musk | +0.740 |
RIS | +0.712 |
FISA | +0.705 |
Route | +0.692 |
Neg logit contributions | |
sterdam | -0.950 |
anco | -0.947 |
ldom | -0.905 |
apest | -0.855 |
merce | -0.852 |
Token | it |
Token ID | 340 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
sterdam | +0.339 |
anco | +0.338 |
ldom | +0.324 |
apest | +0.308 |
Indust | +0.303 |
Neg logit contributions | |
PASS | -0.256 |
Musk | -0.242 |
RIS | -0.232 |
FISA | -0.231 |
Route | -0.226 |
Token | was |
Token ID | 373 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
PASS | +0.507 |
Musk | +0.481 |
RIS | +0.462 |
FISA | +0.460 |
Route | +0.451 |
Neg logit contributions | |
sterdam | -0.631 |
anco | -0.629 |
ldom | -0.601 |
apest | -0.569 |
merce | -0.564 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
PASS | +0.173 |
Musk | +0.164 |
RIS | +0.157 |
FISA | +0.157 |
Route | +0.153 |
Neg logit contributions | |
sterdam | -0.226 |
anco | -0.226 |
ldom | -0.216 |
apest | -0.205 |
merce | -0.202 |
Token | os |
Token ID | 418 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
anco | +1.975 |
sterdam | +1.934 |
ldom | +1.752 |
apest | +1.517 |
Indust | +1.475 |
Neg logit contributions | |
PASS | -5.682 |
Musk | -5.437 |
FISA | -5.394 |
RIS | -5.364 |
Route | -5.277 |
Token | , |
Token ID | 11 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
sterdam | +0.241 |
anco | +0.240 |
ldom | +0.229 |
apest | +0.217 |
merce | +0.216 |
Neg logit contributions | |
PASS | -0.194 |
Musk | -0.186 |
RIS | -0.178 |
FISA | -0.176 |
Route | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
PASS | +0.227 |
Musk | +0.216 |
RIS | +0.207 |
FISA | +0.206 |
Route | +0.202 |
Neg logit contributions | |
sterdam | -0.294 |
anco | -0.293 |
ldom | -0.280 |
apest | -0.265 |
merce | -0.263 |
Token | super |
Token ID | 2208 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
PASS | +0.151 |
Musk | +0.143 |
RIS | +0.137 |
FISA | +0.136 |
Route | +0.133 |
Neg logit contributions | |
sterdam | -0.203 |
anco | -0.203 |
ldom | -0.194 |
apest | -0.184 |
merce | -0.182 |
Token | - |
Token ID | 12 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
PASS | +0.609 |
Musk | +0.576 |
RIS | +0.551 |
FISA | +0.547 |
Route | +0.538 |
Neg logit contributions | |
sterdam | -0.851 |
anco | -0.845 |
ldom | -0.807 |
apest | -0.768 |
merce | -0.766 |
Token | successfully |
Token ID | 37351 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
PASS | +0.329 |
Musk | +0.307 |
RIS | +0.291 |
FISA | +0.288 |
Route | +0.280 |
Neg logit contributions | |
sterdam | -0.690 |
anco | -0.689 |
ldom | -0.663 |
apest | -0.634 |
merce | -0.630 |
Token | ) |
Token ID | 8 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
sterdam | +0.967 |
anco | +0.966 |
ldom | +0.916 |
apest | +0.854 |
merce | +0.847 |
Neg logit contributions | |
PASS | -1.114 |
Musk | -1.064 |
RIS | -1.035 |
FISA | -1.025 |
Route | -1.009 |
Token | to |
Token ID | 284 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
sterdam | +0.364 |
anco | +0.364 |
ldom | +0.347 |
apest | +0.331 |
merce | +0.328 |
Neg logit contributions | |
PASS | -0.255 |
Musk | -0.240 |
RIS | -0.232 |
FISA | -0.229 |
Route | -0.224 |
Token | spray |
Token ID | 11662 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
sterdam | +0.178 |
anco | +0.178 |
ldom | +0.169 |
apest | +0.159 |
merce | +0.158 |
Neg logit contributions | |
PASS | -0.175 |
Musk | -0.168 |
RIS | -0.162 |
FISA | -0.161 |
Route | -0.158 |
Token | anth |
Token ID | 26794 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
sterdam | +0.411 |
anco | +0.410 |
ldom | +0.389 |
apest | +0.365 |
merce | +0.363 |
Neg logit contributions | |
PASS | -0.435 |
Musk | -0.418 |
RIS | -0.404 |
FISA | -0.402 |
Route | -0.395 |
Token | rax |
Token ID | 32040 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
anco | +1.641 |
sterdam | +1.607 |
ldom | +1.521 |
apest | +1.409 |
merce | +1.388 |
Neg logit contributions | |
PASS | -2.073 |
Musk | -1.972 |
FISA | -1.916 |
RIS | -1.901 |
Route | -1.865 |
Token | spores |
Token ID | 47306 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
anco | +3.959 |
sterdam | +3.920 |
ldom | +3.726 |
Indust | +3.531 |
apest | +3.497 |
Neg logit contributions | |
PASS | -3.524 |
Musk | -3.253 |
�醒 | -3.172 |
RIS | -3.121 |
FISA | -3.115 |
Token | over |
Token ID | 625 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
sterdam | +1.421 |
anco | +1.420 |
ldom | +1.355 |
apest | +1.286 |
merce | +1.274 |
Neg logit contributions | |
PASS | -1.018 |
Musk | -0.955 |
RIS | -0.917 |
FISA | -0.913 |
Route | -0.890 |
Token | Tokyo |
Token ID | 11790 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
sterdam | +1.942 |
anco | +1.936 |
ldom | +1.841 |
apest | +1.744 |
Indust | +1.729 |
Neg logit contributions | |
PASS | -1.564 |
Musk | -1.477 |
RIS | -1.425 |
FISA | -1.415 |
@# | -1.385 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
PASS | +0.126 |
Musk | +0.120 |
RIS | +0.115 |
FISA | +0.114 |
Route | +0.113 |
Neg logit contributions | |
sterdam | -0.167 |
anco | -0.166 |
ldom | -0.160 |
apest | -0.152 |
merce | -0.152 |
Token | In |
Token ID | 554 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
PASS | +0.121 |
Musk | +0.116 |
RIS | +0.111 |
FISA | +0.111 |
Route | +0.108 |
Neg logit contributions | |
sterdam | -0.156 |
anco | -0.155 |
ldom | -0.148 |
apest | -0.140 |
merce | -0.140 |
Token | www |
Token ID | 2503 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
sterdam | +1.692 |
anco | +1.680 |
ldom | +1.617 |
apest | +1.512 |
merce | +1.483 |
Neg logit contributions | |
PASS | -1.623 |
Musk | -1.573 |
RIS | -1.515 |
FISA | -1.514 |
�醒 | -1.480 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
anco | +1.574 |
sterdam | +1.546 |
ldom | +1.481 |
apest | +1.402 |
Indust | +1.355 |
Neg logit contributions | |
PASS | -1.824 |
Musk | -1.752 |
�醒 | -1.728 |
RIS | -1.704 |
FISA | -1.697 |
Token | bel |
Token ID | 6667 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
sterdam | +1.928 |
anco | +1.896 |
ldom | +1.831 |
apest | +1.703 |
merce | +1.687 |
Neg logit contributions | |
PASS | -1.620 |
Musk | -1.560 |
FISA | -1.544 |
RIS | -1.497 |
�醒 | -1.474 |
Token | fast |
Token ID | 7217 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
sterdam | +1.257 |
anco | +1.253 |
ldom | +1.163 |
apest | +1.074 |
merce | +1.049 |
Neg logit contributions | |
PASS | -2.058 |
Musk | -1.985 |
RIS | -1.932 |
FISA | -1.926 |
Route | -1.893 |
Token | te |
Token ID | 660 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
anco | +0.441 |
sterdam | +0.439 |
ldom | +0.411 |
merce | +0.395 |
apest | +0.385 |
Neg logit contributions | |
PASS | -0.582 |
Musk | -0.556 |
RIS | -0.550 |
Route | -0.542 |
ACC | -0.540 |
Token | legraph |
Token ID | 16606 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
sterdam | +0.810 |
anco | +0.805 |
ldom | +0.739 |
apest | +0.663 |
merce | +0.653 |
Neg logit contributions | |
PASS | -1.873 |
Musk | -1.816 |
RIS | -1.771 |
FISA | -1.764 |
Route | -1.742 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
anco | +3.310 |
sterdam | +3.301 |
ldom | +3.154 |
apest | +2.977 |
Indust | +2.856 |
Neg logit contributions | |
PASS | -3.962 |
Musk | -3.802 |
RIS | -3.729 |
�醒 | -3.726 |
FISA | -3.693 |
Token | co |
Token ID | 1073 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
sterdam | +1.260 |
anco | +1.256 |
ldom | +1.184 |
apest | +1.104 |
merce | +1.089 |
Neg logit contributions | |
PASS | -1.604 |
Musk | -1.542 |
RIS | -1.494 |
FISA | -1.486 |
Route | -1.463 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
sterdam | +1.144 |
anco | +1.143 |
ldom | +1.086 |
apest | +1.021 |
merce | +1.006 |
Neg logit contributions | |
PASS | -1.169 |
Musk | -1.120 |
RIS | -1.084 |
FISA | -1.078 |
Route | -1.057 |
Token | uk |
Token ID | 2724 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
anco | +1.159 |
sterdam | +1.159 |
ldom | +1.061 |
apest | +0.950 |
merce | +0.935 |
Neg logit contributions | |
PASS | -2.680 |
Musk | -2.601 |
RIS | -2.541 |
FISA | -2.532 |
Route | -2.494 |
Token | / |
Token ID | 14 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
anco | +2.659 |
sterdam | +2.637 |
ldom | +2.535 |
apest | +2.432 |
Indust | +2.381 |
Neg logit contributions | |
PASS | -2.041 |
Musk | -1.916 |
�醒 | -1.883 |
FISA | -1.866 |
RIS | -1.862 |
Token | � |
Token ID | 564 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
anco | +1.344 |
sterdam | +1.340 |
ldom | +1.282 |
apest | +1.200 |
merce | +1.196 |
Neg logit contributions | |
PASS | -1.178 |
Musk | -1.111 |
RIS | -1.076 |
FISA | -1.063 |
�醒 | -1.046 |
Token | � |
Token ID | 250 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
sterdam | +0.917 |
anco | +0.911 |
ldom | +0.862 |
apest | +0.807 |
merce | +0.799 |
Neg logit contributions | |
PASS | -1.082 |
Musk | -1.040 |
RIS | -1.006 |
FISA | -1.002 |
Route | -0.985 |
Token | wild |
Token ID | 21992 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
PASS | +0.193 |
Musk | +0.184 |
RIS | +0.177 |
FISA | +0.176 |
Route | +0.173 |
Neg logit contributions | |
sterdam | -0.223 |
anco | -0.222 |
ldom | -0.211 |
apest | -0.200 |
merce | -0.198 |
Token | ly |
Token ID | 306 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
PASS | +0.077 |
Musk | +0.074 |
RIS | +0.071 |
FISA | +0.070 |
Route | +0.069 |
Neg logit contributions | |
sterdam | -0.091 |
anco | -0.090 |
ldom | -0.086 |
apest | -0.081 |
merce | -0.081 |
Token | unaff |
Token ID | 25312 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
sterdam | +0.047 |
anco | +0.047 |
ldom | +0.045 |
apest | +0.042 |
merce | +0.042 |
Neg logit contributions | |
PASS | -0.046 |
Musk | -0.044 |
RIS | -0.043 |
FISA | -0.042 |
Route | -0.042 |
Token | ordable |
Token ID | 16819 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
sterdam | +0.901 |
anco | +0.901 |
ldom | +0.845 |
apest | +0.786 |
merce | +0.776 |
Neg logit contributions | |
PASS | -1.230 |
Musk | -1.183 |
RIS | -1.154 |
FISA | -1.150 |
Route | -1.128 |
Token | � |
Token ID | 447 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
anco | +3.763 |
sterdam | +3.675 |
ldom | +3.529 |
apest | +3.308 |
merce | +3.286 |
Neg logit contributions | |
PASS | -3.510 |
Musk | -3.286 |
FISA | -3.180 |
RIS | -3.172 |
�醒 | -3.115 |
Token | � |
Token ID | 251 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
sterdam | +0.758 |
anco | +0.753 |
ldom | +0.717 |
apest | +0.677 |
merce | +0.666 |
Neg logit contributions | |
PASS | -0.742 |
Musk | -0.711 |
RIS | -0.685 |
FISA | -0.684 |
Route | -0.670 |
Token | tax |
Token ID | 1687 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
sterdam | +0.546 |
anco | +0.543 |
ldom | +0.518 |
apest | +0.489 |
merce | +0.486 |
Neg logit contributions | |
PASS | -0.479 |
Musk | -0.457 |
RIS | -0.441 |
FISA | -0.437 |
Route | -0.430 |
Token | cuts |
Token ID | 6630 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
PASS | +0.250 |
Musk | +0.239 |
RIS | +0.229 |
FISA | +0.227 |
Route | +0.223 |
Neg logit contributions | |
sterdam | -0.320 |
anco | -0.318 |
ldom | -0.305 |
apest | -0.289 |
merce | -0.286 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
sterdam | +0.208 |
anco | +0.208 |
ldom | +0.198 |
apest | +0.188 |
merce | +0.187 |
Neg logit contributions | |
PASS | -0.157 |
Musk | -0.149 |
RIS | -0.143 |
FISA | -0.142 |
Route | -0.139 |
Token | org |
Token ID | 2398 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
sterdam | +1.094 |
anco | +1.075 |
ldom | +1.030 |
merce | +0.987 |
apest | +0.963 |
Neg logit contributions | |
PASS | -1.069 |
Musk | -1.030 |
RIS | -0.991 |
FISA | -0.981 |
Route | -0.971 |
Token | / |
Token ID | 14 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
anco | +3.028 |
sterdam | +3.019 |
ldom | +2.892 |
apest | +2.748 |
merce | +2.703 |
Neg logit contributions | |
PASS | -2.122 |
Musk | -1.996 |
FISA | -1.918 |
RIS | -1.917 |
Route | -1.857 |
Token | index |
Token ID | 9630 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
sterdam | +1.602 |
anco | +1.588 |
ldom | +1.470 |
merce | +1.334 |
apest | +1.330 |
Neg logit contributions | |
PASS | -3.149 |
Musk | -3.054 |
RIS | -2.952 |
FISA | -2.943 |
Route | -2.931 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
sterdam | +1.656 |
anco | +1.652 |
ldom | +1.569 |
apest | +1.477 |
merce | +1.461 |
Neg logit contributions | |
PASS | -1.652 |
Musk | -1.582 |
RIS | -1.528 |
FISA | -1.518 |
Route | -1.491 |
Token | php |
Token ID | 10121 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
anco | +0.967 |
sterdam | +0.965 |
ldom | +0.884 |
apest | +0.796 |
merce | +0.778 |
Neg logit contributions | |
PASS | -2.270 |
Musk | -2.195 |
RIS | -2.144 |
FISA | -2.135 |
Route | -2.109 |
Token | ? |
Token ID | 30 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
anco | +3.003 |
sterdam | +2.982 |
ldom | +2.801 |
apest | +2.663 |
merce | +2.597 |
Neg logit contributions | |
PASS | -3.147 |
Musk | -3.014 |
RIS | -2.900 |
FISA | -2.896 |
Route | -2.831 |
Token | topic |
Token ID | 26652 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
anco | +4.097 |
sterdam | +4.026 |
ldom | +3.928 |
apest | +3.674 |
merce | +3.624 |
Neg logit contributions | |
PASS | -3.122 |
Musk | -2.995 |
RIS | -2.927 |
FISA | -2.898 |
Route | -2.781 |
Token | = |
Token ID | 28 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
anco | +1.769 |
sterdam | +1.761 |
ldom | +1.699 |
apest | +1.635 |
merce | +1.606 |
Neg logit contributions | |
PASS | -0.736 |
Musk | -0.689 |
RIS | -0.650 |
FISA | -0.642 |
�醒 | -0.614 |
Token | 28 |
Token ID | 2078 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
PASS | +0.364 |
Musk | +0.344 |
RIS | +0.330 |
FISA | +0.328 |
Route | +0.323 |
Neg logit contributions | |
sterdam | -0.492 |
anco | -0.488 |
ldom | -0.467 |
merce | -0.443 |
apest | -0.442 |
Token | 18 |
Token ID | 1507 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
sterdam | +0.343 |
anco | +0.342 |
ldom | +0.327 |
apest | +0.310 |
merce | +0.308 |
Neg logit contributions | |
PASS | -0.258 |
Musk | -0.245 |
RIS | -0.235 |
FISA | -0.233 |
Route | -0.229 |
Token | 48 |
Token ID | 2780 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
PASS | +0.026 |
Musk | +0.025 |
RIS | +0.024 |
FISA | +0.024 |
Route | +0.024 |
Neg logit contributions | |
sterdam | -0.034 |
anco | -0.034 |
ldom | -0.032 |
apest | -0.031 |
merce | -0.031 |
Token | Ratings |
Token ID | 36826 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
sterdam | +0.577 |
anco | +0.571 |
ldom | +0.548 |
apest | +0.516 |
merce | +0.512 |
Neg logit contributions | |
PASS | -0.531 |
Musk | -0.512 |
RIS | -0.494 |
FISA | -0.490 |
Route | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
sterdam | +0.538 |
anco | +0.533 |
ldom | +0.515 |
apest | +0.486 |
merce | +0.484 |
Neg logit contributions | |
PASS | -0.416 |
Musk | -0.400 |
RIS | -0.385 |
FISA | -0.380 |
Route | -0.372 |
Token |
|
Token ID | 198 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
sterdam | +0.371 |
anco | +0.369 |
ldom | +0.354 |
apest | +0.334 |
merce | +0.333 |
Neg logit contributions | |
PASS | -0.292 |
Musk | -0.280 |
RIS | -0.269 |
FISA | -0.267 |
Route | -0.261 |
Token |
|
Token ID | 198 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
anco | +0.583 |
sterdam | +0.580 |
ldom | +0.552 |
apest | +0.525 |
Indust | +0.514 |
Neg logit contributions | |
PASS | -0.504 |
Musk | -0.480 |
RIS | -0.462 |
FISA | -0.460 |
�醒 | -0.454 |
Token | Sl |
Token ID | 11122 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
sterdam | +0.649 |
anco | +0.645 |
ldom | +0.615 |
apest | +0.577 |
merce | +0.575 |
Neg logit contributions | |
PASS | -0.616 |
Musk | -0.587 |
RIS | -0.567 |
FISA | -0.562 |
Route | -0.552 |
Token | ideshow |
Token ID | 42286 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
sterdam | +0.400 |
anco | +0.395 |
ldom | +0.345 |
apest | +0.287 |
merce | +0.282 |
Neg logit contributions | |
PASS | -1.621 |
Musk | -1.580 |
RIS | -1.545 |
FISA | -1.538 |
Route | -1.524 |
Token | ( |
Token ID | 357 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
anco | +3.999 |
sterdam | +3.992 |
ldom | +3.780 |
Indust | +3.622 |
apest | +3.602 |
Neg logit contributions | |
PASS | -3.139 |
Musk | -2.932 |
�醒 | -2.921 |
FISA | -2.810 |
RIS | -2.795 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
anco | +1.143 |
sterdam | +1.139 |
ldom | +1.087 |
apest | +1.036 |
Indust | +1.013 |
Neg logit contributions | |
PASS | -0.964 |
Musk | -0.929 |
RIS | -0.891 |
FISA | -0.889 |
Route | -0.869 |
Token | Images |
Token ID | 5382 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
sterdam | +0.501 |
anco | +0.484 |
ldom | +0.459 |
merce | +0.440 |
apest | +0.430 |
Neg logit contributions | |
PASS | -0.491 |
Musk | -0.469 |
RIS | -0.460 |
Model | -0.450 |
Route | -0.448 |
Token | ) |
Token ID | 8 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
sterdam | +1.264 |
anco | +1.261 |
ldom | +1.193 |
apest | +1.118 |
merce | +1.105 |
Neg logit contributions | |
PASS | -1.421 |
Musk | -1.364 |
RIS | -1.317 |
FISA | -1.311 |
Route | -1.290 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
anco | +1.193 |
sterdam | +1.193 |
ldom | +1.131 |
apest | +1.072 |
merce | +1.059 |
Neg logit contributions | |
PASS | -1.105 |
Musk | -1.050 |
RIS | -1.009 |
FISA | -1.008 |
Route | -0.989 |
Token | to |
Token ID | 284 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
anco | +2.860 |
sterdam | +2.853 |
ldom | +2.725 |
apest | +2.570 |
merce | +2.549 |
Neg logit contributions | |
PASS | -2.063 |
Musk | -1.943 |
FISA | -1.868 |
RIS | -1.867 |
@# | -1.824 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
sterdam | +0.064 |
anco | +0.064 |
ldom | +0.061 |
apest | +0.058 |
merce | +0.058 |
Neg logit contributions | |
PASS | -0.049 |
Musk | -0.047 |
RIS | -0.045 |
FISA | -0.045 |
Route | -0.044 |
Token | ancient |
Token ID | 6156 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
PASS | +0.226 |
Musk | +0.217 |
RIS | +0.207 |
FISA | +0.206 |
Route | +0.204 |
Neg logit contributions | |
sterdam | -0.289 |
anco | -0.289 |
ldom | -0.275 |
merce | -0.260 |
apest | -0.260 |
Token | fortress |
Token ID | 28757 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
PASS | +0.156 |
Musk | +0.150 |
RIS | +0.144 |
FISA | +0.143 |
Route | +0.142 |
Neg logit contributions | |
sterdam | -0.167 |
anco | -0.167 |
ldom | -0.158 |
apest | -0.149 |
merce | -0.149 |
Token | of |
Token ID | 286 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
sterdam | +0.646 |
anco | +0.644 |
ldom | +0.613 |
apest | +0.582 |
merce | +0.582 |
Neg logit contributions | |
PASS | -0.526 |
Musk | -0.503 |
RIS | -0.484 |
FISA | -0.479 |
Route | -0.473 |
Token | Helm |
Token ID | 28351 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
sterdam | +0.272 |
anco | +0.271 |
ldom | +0.260 |
apest | +0.247 |
merce | +0.246 |
Neg logit contributions | |
PASS | -0.183 |
Musk | -0.174 |
RIS | -0.166 |
FISA | -0.165 |
Route | -0.162 |
Token | 's |
Token ID | 338 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
anco | +3.921 |
sterdam | +3.913 |
ldom | +3.763 |
apest | +3.496 |
Indust | +3.485 |
Neg logit contributions | |
PASS | -3.355 |
Musk | -3.145 |
FISA | -3.070 |
RIS | -3.068 |
�醒 | -2.959 |
Token | Deep |
Token ID | 10766 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
sterdam | +0.706 |
anco | +0.702 |
ldom | +0.675 |
apest | +0.647 |
merce | +0.645 |
Neg logit contributions | |
PASS | -0.391 |
Musk | -0.370 |
RIS | -0.351 |
FISA | -0.345 |
Route | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
sterdam | +1.773 |
anco | +1.767 |
ldom | +1.688 |
apest | +1.596 |
merce | +1.583 |
Neg logit contributions | |
PASS | -1.459 |
Musk | -1.389 |
RIS | -1.336 |
FISA | -1.328 |
Route | -1.302 |
Token | while |
Token ID | 981 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
PASS | +0.401 |
Musk | +0.384 |
RIS | +0.371 |
FISA | +0.365 |
Route | +0.363 |
Neg logit contributions | |
sterdam | -0.505 |
anco | -0.502 |
ldom | -0.479 |
merce | -0.456 |
apest | -0.456 |
Token | Gand |
Token ID | 17727 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
PASS | +0.839 |
Musk | +0.798 |
RIS | +0.764 |
FISA | +0.751 |
Route | +0.743 |
Neg logit contributions | |
sterdam | -1.307 |
anco | -1.302 |
ldom | -1.248 |
apest | -1.192 |
merce | -1.184 |
Token | 9 |
Token ID | 860 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
PASS | +0.852 |
Musk | +0.798 |
RIS | +0.763 |
FISA | +0.753 |
Route | +0.737 |
Neg logit contributions | |
sterdam | -1.705 |
anco | -1.699 |
ldom | -1.638 |
apest | -1.565 |
merce | -1.558 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
PASS | +0.745 |
Musk | +0.704 |
RIS | +0.677 |
FISA | +0.670 |
Route | +0.658 |
Neg logit contributions | |
sterdam | -1.335 |
anco | -1.328 |
ldom | -1.284 |
apest | -1.219 |
merce | -1.213 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
PASS | +0.951 |
Musk | +0.896 |
RIS | +0.873 |
FISA | +0.865 |
Route | +0.856 |
Neg logit contributions | |
sterdam | -1.495 |
anco | -1.482 |
ldom | -1.448 |
merce | -1.371 |
apest | -1.366 |
Token | 12 |
Token ID | 1105 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
PASS | +1.112 |
Musk | +1.031 |
RIS | +1.000 |
FISA | +0.989 |
Route | +0.980 |
Neg logit contributions | |
anco | -2.042 |
sterdam | -2.029 |
ldom | -1.970 |
merce | -1.878 |
apest | -1.869 |
Token | 13 |
Token ID | 1511 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
PASS | +1.392 |
Musk | +1.304 |
RIS | +1.257 |
FISA | +1.238 |
Route | +1.222 |
Neg logit contributions | |
sterdam | -2.360 |
anco | -2.356 |
ldom | -2.270 |
apest | -2.156 |
merce | -2.150 |
Token | 14 |
Token ID | 1478 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
PASS | +1.556 |
Musk | +1.434 |
RIS | +1.401 |
FISA | +1.376 |
Route | +1.349 |
Neg logit contributions | |
sterdam | -3.281 |
anco | -3.262 |
ldom | -3.150 |
merce | -3.009 |
apest | -3.005 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
PASS | +1.660 |
Musk | +1.542 |
RIS | +1.475 |
FISA | +1.472 |
Route | +1.433 |
Neg logit contributions | |
sterdam | -3.498 |
anco | -3.492 |
ldom | -3.385 |
merce | -3.214 |
apest | -3.209 |
Token | -- |
Token ID | 1377 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
PASS | +1.773 |
Musk | +1.647 |
RIS | +1.622 |
FISA | +1.603 |
Route | +1.577 |
Neg logit contributions | |
anco | -3.309 |
sterdam | -3.303 |
ldom | -3.181 |
merce | -3.043 |
apest | -3.028 |
Token | Save |
Token ID | 12793 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
PASS | +0.032 |
Musk | +0.031 |
RIS | +0.029 |
FISA | +0.029 |
Route | +0.029 |
Neg logit contributions | |
sterdam | -0.042 |
anco | -0.042 |
ldom | -0.040 |
apest | -0.038 |
merce | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
anco | +1.811 |
sterdam | +1.810 |
ldom | +1.722 |
apest | +1.638 |
merce | +1.623 |
Neg logit contributions | |
PASS | -1.372 |
Musk | -1.304 |
RIS | -1.249 |
FISA | -1.239 |
Route | -1.208 |
Token | results |
Token ID | 2482 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
PASS | +0.330 |
Musk | +0.314 |
RIS | +0.301 |
FISA | +0.299 |
Route | +0.293 |
Neg logit contributions | |
sterdam | -0.452 |
anco | -0.450 |
ldom | -0.431 |
apest | -0.409 |
merce | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
sterdam | +0.536 |
anco | +0.534 |
ldom | +0.510 |
apest | +0.482 |
merce | +0.479 |
Neg logit contributions | |
PASS | -0.443 |
Musk | -0.422 |
RIS | -0.406 |
FISA | -0.404 |
Route | -0.396 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
sterdam | +0.103 |
anco | +0.103 |
ldom | +0.099 |
apest | +0.093 |
merce | +0.093 |
Neg logit contributions | |
PASS | -0.081 |
Musk | -0.077 |
RIS | -0.074 |
FISA | -0.074 |
Route | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
PASS | +0.214 |
Musk | +0.204 |
RIS | +0.196 |
FISA | +0.195 |
Route | +0.191 |
Neg logit contributions | |
anco | -0.259 |
sterdam | -0.259 |
ldom | -0.246 |
apest | -0.233 |
merce | -0.230 |
Token | � |
Token ID | 447 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
sterdam | +0.008 |
anco | +0.008 |
ldom | +0.008 |
merce | +0.007 |
apest | +0.007 |
Neg logit contributions | |
PASS | -0.008 |
Musk | -0.007 |
RIS | -0.007 |
FISA | -0.007 |
Route | -0.007 |
Token | � |
Token ID | 250 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
sterdam | +0.898 |
anco | +0.890 |
ldom | +0.842 |
apest | +0.790 |
merce | +0.782 |
Neg logit contributions | |
PASS | -1.032 |
Musk | -0.991 |
RIS | -0.958 |
FISA | -0.951 |
Route | -0.940 |
Token | Before |
Token ID | 8421 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
sterdam | +0.734 |
anco | +0.729 |
ldom | +0.698 |
apest | +0.659 |
merce | +0.659 |
Neg logit contributions | |
PASS | -0.594 |
Musk | -0.567 |
RIS | -0.547 |
FISA | -0.539 |
Route | -0.532 |
Token | I |
Token ID | 314 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
PASS | +2.064 |
Musk | +2.020 |
RIS | +1.908 |
Route | +1.887 |
FISA | +1.881 |
Neg logit contributions | |
sterdam | -2.982 |
anco | -2.977 |
ldom | -2.835 |
apest | -2.742 |
merce | -2.706 |
Token | came |
Token ID | 1625 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
sterdam | +0.497 |
anco | +0.495 |
ldom | +0.473 |
apest | +0.447 |
merce | +0.445 |
Neg logit contributions | |
PASS | -0.399 |
Musk | -0.380 |
RIS | -0.365 |
FISA | -0.363 |
Route | -0.356 |
Token | here |
Token ID | 994 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
PASS | +0.393 |
Musk | +0.376 |
RIS | +0.354 |
FISA | +0.350 |
Route | +0.349 |
Neg logit contributions | |
anco | -0.674 |
sterdam | -0.672 |
ldom | -0.649 |
apest | -0.619 |
merce | -0.616 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
sterdam | +1.304 |
anco | +1.300 |
ldom | +1.247 |
apest | +1.184 |
merce | +1.177 |
Neg logit contributions | |
PASS | -0.894 |
Musk | -0.848 |
RIS | -0.811 |
FISA | -0.805 |
Route | -0.789 |
Token | I |
Token ID | 314 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
sterdam | +0.245 |
anco | +0.243 |
ldom | +0.233 |
apest | +0.223 |
merce | +0.222 |
Neg logit contributions | |
PASS | -0.161 |
Musk | -0.153 |
RIS | -0.146 |
FISA | -0.145 |
Route | -0.143 |
Token | pressing |
Token ID | 12273 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
PASS | +0.534 |
Musk | +0.508 |
RIS | +0.490 |
FISA | +0.487 |
Route | +0.478 |
Neg logit contributions | |
sterdam | -0.621 |
anco | -0.619 |
ldom | -0.590 |
apest | -0.558 |
merce | -0.554 |
Token | requirements |
Token ID | 5359 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
PASS | +0.214 |
Musk | +0.206 |
RIS | +0.199 |
FISA | +0.198 |
Route | +0.195 |
Neg logit contributions | |
sterdam | -0.201 |
anco | -0.200 |
ldom | -0.190 |
apest | -0.178 |
merce | -0.177 |
Token | , |
Token ID | 11 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
PASS | +0.650 |
Musk | +0.621 |
RIS | +0.592 |
FISA | +0.588 |
Route | +0.577 |
Neg logit contributions | |
sterdam | -0.926 |
anco | -0.921 |
ldom | -0.885 |
apest | -0.841 |
merce | -0.832 |
Token | Mo |
Token ID | 4270 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
PASS | +0.427 |
Musk | +0.407 |
RIS | +0.390 |
FISA | +0.387 |
Route | +0.380 |
Neg logit contributions | |
sterdam | -0.566 |
anco | -0.564 |
ldom | -0.540 |
apest | -0.512 |
merce | -0.508 |
Token | R |
Token ID | 49 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
PASS | +1.443 |
Musk | +1.376 |
RIS | +1.326 |
FISA | +1.299 |
Route | +1.295 |
Neg logit contributions | |
sterdam | -1.541 |
anco | -1.517 |
ldom | -1.470 |
apest | -1.376 |
merce | -1.363 |
Token | TH |
Token ID | 4221 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
PASS | +1.922 |
Musk | +1.819 |
RIS | +1.732 |
FISA | +1.731 |
ACC | +1.697 |
Neg logit contributions | |
sterdam | -2.581 |
anco | -2.552 |
ldom | -2.477 |
apest | -2.341 |
merce | -2.322 |
Token | introduced |
Token ID | 5495 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
PASS | +2.288 |
Musk | +2.155 |
RIS | +2.058 |
FISA | +2.053 |
ACC | +2.027 |
Neg logit contributions | |
sterdam | -2.866 |
anco | -2.833 |
ldom | -2.760 |
apest | -2.590 |
merce | -2.550 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
PASS | +0.603 |
Musk | +0.573 |
RIS | +0.549 |
FISA | +0.545 |
Route | +0.534 |
Neg logit contributions | |
sterdam | -0.827 |
anco | -0.825 |
ldom | -0.790 |
apest | -0.749 |
merce | -0.743 |
Token | Motor |
Token ID | 12533 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
PASS | +0.128 |
Musk | +0.119 |
RIS | +0.113 |
FISA | +0.112 |
Route | +0.109 |
Neg logit contributions | |
sterdam | -0.242 |
anco | -0.241 |
ldom | -0.232 |
apest | -0.221 |
merce | -0.220 |
Token | Vehicle |
Token ID | 21501 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
PASS | +0.027 |
Musk | +0.024 |
RIS | +0.022 |
FISA | +0.021 |
Route | +0.020 |
Neg logit contributions | |
sterdam | -0.122 |
anco | -0.122 |
ldom | -0.118 |
apest | -0.114 |
merce | -0.114 |
Token | ( |
Token ID | 357 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
PASS | +0.993 |
Musk | +0.938 |
RIS | +0.891 |
FISA | +0.884 |
Route | +0.868 |
Neg logit contributions | |
sterdam | -1.683 |
anco | -1.681 |
ldom | -1.614 |
apest | -1.538 |
merce | -1.527 |
Token | P |
Token ID | 47 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
PASS | +0.251 |
Musk | +0.237 |
RIS | +0.229 |
FISA | +0.225 |
ACC | +0.223 |
Neg logit contributions | |
sterdam | -0.284 |
anco | -0.283 |
ldom | -0.270 |
apest | -0.255 |
merce | -0.254 |
Token | OWER |
Token ID | 36048 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
sterdam | +0.427 |
anco | +0.425 |
ldom | +0.406 |
apest | +0.383 |
merce | +0.382 |
Neg logit contributions | |
PASS | -0.370 |
Musk | -0.351 |
RIS | -0.337 |
FISA | -0.334 |
Route | -0.329 |
Token | mag |
Token ID | 19726 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
PASS | +1.781 |
Musk | +1.663 |
RIS | +1.606 |
ACC | +1.571 |
FISA | +1.570 |
Neg logit contributions | |
sterdam | -2.067 |
anco | -2.049 |
ldom | -1.979 |
apest | -1.876 |
merce | -1.848 |
Token | azine |
Token ID | 4994 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
sterdam | +0.380 |
anco | +0.377 |
ldom | +0.356 |
apest | +0.331 |
merce | +0.326 |
Neg logit contributions | |
PASS | -0.529 |
Musk | -0.510 |
RIS | -0.495 |
FISA | -0.492 |
Route | -0.485 |
Token | ) |
Token ID | 8 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
sterdam | +0.687 |
anco | +0.685 |
ldom | +0.652 |
apest | +0.614 |
merce | +0.610 |
Neg logit contributions | |
PASS | -0.639 |
Musk | -0.611 |
RIS | -0.589 |
FISA | -0.585 |
Route | -0.575 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
sterdam | +0.672 |
anco | +0.669 |
ldom | +0.640 |
apest | +0.606 |
merce | +0.603 |
Neg logit contributions | |
PASS | -0.539 |
Musk | -0.513 |
RIS | -0.493 |
FISA | -0.489 |
Route | -0.480 |
Token | C |
Token ID | 34 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
PASS | +2.368 |
Musk | +2.183 |
RIS | +2.087 |
@# | +2.082 |
FISA | +2.070 |
Neg logit contributions | |
sterdam | -2.612 |
anco | -2.591 |
ldom | -2.483 |
merce | -2.354 |
Indust | -2.335 |
Token | it |
Token ID | 270 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sterdam | +0.417 |
anco | +0.415 |
ldom | +0.396 |
apest | +0.374 |
merce | +0.371 |
Neg logit contributions | |
PASS | -0.358 |
Musk | -0.341 |
RIS | -0.328 |
FISA | -0.326 |
Route | -0.320 |
Token | ib |
Token ID | 571 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
PASS | +1.082 |
Musk | +1.024 |
RIS | +0.983 |
FISA | +0.977 |
Route | +0.964 |
Neg logit contributions | |
sterdam | -1.593 |
anco | -1.578 |
ldom | -1.519 |
merce | -1.435 |
apest | -1.430 |
Token | ank |
Token ID | 962 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
sterdam | +0.348 |
anco | +0.338 |
ldom | +0.325 |
merce | +0.301 |
apest | +0.299 |
Neg logit contributions | |
PASS | -0.458 |
Musk | -0.449 |
RIS | -0.435 |
FISA | -0.431 |
Model | -0.425 |
Token | fore |
Token ID | 1674 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
sterdam | +1.448 |
anco | +1.443 |
ldom | +1.377 |
apest | +1.307 |
merce | +1.298 |
Neg logit contributions | |
PASS | -1.096 |
Musk | -1.038 |
RIS | -0.994 |
FISA | -0.988 |
Route | -0.969 |
Token | ID |
Token ID | 4522 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
sterdam | +0.094 |
anco | +0.093 |
ldom | +0.089 |
apest | +0.085 |
merce | +0.084 |
Neg logit contributions | |
PASS | -0.073 |
Musk | -0.069 |
RIS | -0.067 |
FISA | -0.066 |
Route | -0.065 |
Token | I |
Token ID | 314 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
sterdam | +0.432 |
anco | +0.430 |
ldom | +0.411 |
apest | +0.388 |
merce | +0.387 |
Neg logit contributions | |
PASS | -0.376 |
Musk | -0.356 |
RIS | -0.344 |
FISA | -0.340 |
Route | -0.334 |
Token | got |
Token ID | 1392 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
PASS | +0.115 |
Musk | +0.109 |
RIS | +0.106 |
FISA | +0.104 |
ACC | +0.102 |
Neg logit contributions | |
sterdam | -0.144 |
anco | -0.142 |
ldom | -0.137 |
apest | -0.129 |
merce | -0.128 |
Token | is |
Token ID | 318 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
PASS | +0.190 |
Musk | +0.181 |
RIS | +0.175 |
FISA | +0.172 |
Route | +0.169 |
Neg logit contributions | |
sterdam | -0.265 |
anco | -0.263 |
ldom | -0.254 |
apest | -0.242 |
merce | -0.240 |
Token | a |
Token ID | 257 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
PASS | +0.160 |
Musk | +0.152 |
RIS | +0.146 |
FISA | +0.145 |
Route | +0.142 |
Neg logit contributions | |
sterdam | -0.211 |
anco | -0.210 |
ldom | -0.201 |
apest | -0.191 |
merce | -0.190 |
Token | bus |
Token ID | 1323 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
PASS | +0.458 |
Musk | +0.438 |
RIS | +0.425 |
FISA | +0.421 |
Route | +0.413 |
Neg logit contributions | |
sterdam | -0.490 |
anco | -0.489 |
ldom | -0.465 |
apest | -0.438 |
merce | -0.432 |
Token | pass |
Token ID | 1208 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
PASS | +2.072 |
Musk | +1.912 |
RIS | +1.858 |
Route | +1.853 |
ACC | +1.825 |
Neg logit contributions | |
sterdam | -2.804 |
anco | -2.751 |
ldom | -2.704 |
merce | -2.537 |
apest | -2.494 |
Token | with |
Token ID | 351 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
PASS | +0.293 |
Musk | +0.279 |
RIS | +0.268 |
FISA | +0.265 |
Route | +0.261 |
Neg logit contributions | |
sterdam | -0.377 |
anco | -0.375 |
ldom | -0.360 |
apest | -0.340 |
merce | -0.338 |
Token | my |
Token ID | 616 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
sterdam | +0.686 |
anco | +0.684 |
ldom | +0.653 |
apest | +0.618 |
merce | +0.614 |
Neg logit contributions | |
PASS | -0.553 |
Musk | -0.526 |
RIS | -0.506 |
FISA | -0.502 |
Route | -0.493 |
Token | picture |
Token ID | 4286 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
PASS | +0.478 |
Musk | +0.454 |
RIS | +0.439 |
FISA | +0.435 |
Route | +0.430 |
Neg logit contributions | |
sterdam | -0.534 |
anco | -0.531 |
ldom | -0.507 |
apest | -0.477 |
merce | -0.475 |
Token | on |
Token ID | 319 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
PASS | +0.071 |
Musk | +0.067 |
RIS | +0.065 |
FISA | +0.064 |
Route | +0.063 |
Neg logit contributions | |
sterdam | -0.093 |
anco | -0.093 |
ldom | -0.089 |
merce | -0.085 |
apest | -0.084 |
Token | offered |
Token ID | 4438 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
PASS | +0.585 |
Musk | +0.557 |
RIS | +0.538 |
FISA | +0.533 |
Route | +0.521 |
Neg logit contributions | |
sterdam | -0.742 |
anco | -0.740 |
ldom | -0.707 |
apest | -0.670 |
merce | -0.667 |
Token | by |
Token ID | 416 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
PASS | +0.034 |
Musk | +0.033 |
RIS | +0.031 |
FISA | +0.031 |
Route | +0.031 |
Neg logit contributions | |
sterdam | -0.048 |
anco | -0.048 |
ldom | -0.046 |
apest | -0.044 |
merce | -0.044 |
Token | every |
Token ID | 790 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
sterdam | +0.287 |
anco | +0.286 |
ldom | +0.274 |
apest | +0.261 |
merce | +0.260 |
Neg logit contributions | |
PASS | -0.219 |
Musk | -0.209 |
RIS | -0.202 |
FISA | -0.199 |
Route | -0.195 |
Token | other |
Token ID | 584 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
PASS | +0.148 |
Musk | +0.143 |
RIS | +0.138 |
FISA | +0.137 |
ACC | +0.135 |
Neg logit contributions | |
sterdam | -0.139 |
anco | -0.138 |
ldom | -0.131 |
apest | -0.124 |
merce | -0.123 |
Token | major |
Token ID | 1688 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
sterdam | +0.034 |
anco | +0.033 |
ldom | +0.032 |
apest | +0.030 |
merce | +0.030 |
Neg logit contributions | |
PASS | -0.033 |
Musk | -0.032 |
RIS | -0.031 |
FISA | -0.030 |
ACC | -0.030 |
Token | satellite |
Token ID | 11210 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
sterdam | +1.411 |
anco | +1.408 |
ldom | +1.327 |
apest | +1.237 |
merce | +1.225 |
Neg logit contributions | |
PASS | -1.711 |
Musk | -1.643 |
RIS | -1.589 |
FISA | -1.580 |
Route | -1.557 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
PASS | +1.485 |
Musk | +1.424 |
ACC | +1.370 |
RIS | +1.369 |
FISA | +1.364 |
Neg logit contributions | |
sterdam | -1.827 |
anco | -1.803 |
ldom | -1.728 |
apest | -1.678 |
merce | -1.669 |
Token | cable |
Token ID | 7862 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
PASS | +0.084 |
Musk | +0.081 |
RIS | +0.079 |
FISA | +0.079 |
ACC | +0.078 |
Neg logit contributions | |
sterdam | -0.051 |
anco | -0.051 |
ldom | -0.048 |
apest | -0.044 |
merce | -0.044 |
Token | TV |
Token ID | 3195 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
PASS | +0.609 |
Musk | +0.581 |
RIS | +0.561 |
FISA | +0.559 |
ACC | +0.554 |
Neg logit contributions | |
sterdam | -0.736 |
anco | -0.730 |
ldom | -0.702 |
apest | -0.669 |
merce | -0.667 |
Token | provider |
Token ID | 10131 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
PASS | +0.580 |
Musk | +0.556 |
RIS | +0.536 |
FISA | +0.531 |
ACC | +0.525 |
Neg logit contributions | |
sterdam | -0.758 |
anco | -0.754 |
ldom | -0.727 |
apest | -0.692 |
merce | -0.691 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
PASS | +0.092 |
Musk | +0.088 |
RIS | +0.085 |
FISA | +0.084 |
ACC | +0.082 |
Neg logit contributions | |
sterdam | -0.114 |
anco | -0.113 |
ldom | -0.108 |
apest | -0.103 |
merce | -0.102 |
Token | a |
Token ID | 257 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
PASS | +0.414 |
Musk | +0.397 |
RIS | +0.379 |
FISA | +0.375 |
Route | +0.372 |
Neg logit contributions | |
sterdam | -0.589 |
anco | -0.583 |
ldom | -0.560 |
apest | -0.534 |
merce | -0.531 |
Token | Bren |
Token ID | 20465 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
PASS | +0.392 |
Musk | +0.373 |
RIS | +0.355 |
FISA | +0.352 |
Route | +0.346 |
Neg logit contributions | |
sterdam | -0.635 |
anco | -0.633 |
ldom | -0.608 |
apest | -0.579 |
merce | -0.577 |
Token | ham |
Token ID | 2763 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
sterdam | +0.084 |
anco | +0.084 |
ldom | +0.080 |
merce | +0.076 |
apest | +0.076 |
Neg logit contributions | |
PASS | -0.069 |
Musk | -0.067 |
RIS | -0.064 |
FISA | -0.063 |
Route | -0.063 |
Token | Republican |
Token ID | 3415 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
sterdam | +0.490 |
anco | +0.488 |
ldom | +0.465 |
apest | +0.440 |
merce | +0.435 |
Neg logit contributions | |
PASS | -0.417 |
Musk | -0.396 |
RIS | -0.382 |
FISA | -0.380 |
Route | -0.371 |
Token | who |
Token ID | 508 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
PASS | +0.458 |
Musk | +0.438 |
RIS | +0.417 |
FISA | +0.415 |
Route | +0.409 |
Neg logit contributions | |
sterdam | -0.633 |
anco | -0.630 |
ldom | -0.602 |
apest | -0.574 |
merce | -0.568 |
Token | authored |
Token ID | 33941 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
PASS | +0.206 |
Musk | +0.198 |
RIS | +0.190 |
FISA | +0.189 |
Route | +0.186 |
Neg logit contributions | |
sterdam | -0.225 |
anco | -0.224 |
ldom | -0.213 |
apest | -0.202 |
merce | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
PASS | +0.924 |
Musk | +0.886 |
RIS | +0.843 |
FISA | +0.839 |
Route | +0.828 |
Neg logit contributions | |
sterdam | -1.250 |
anco | -1.243 |
ldom | -1.190 |
apest | -1.133 |
merce | -1.121 |
Token | bill |
Token ID | 2855 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
PASS | +0.057 |
Musk | +0.055 |
RIS | +0.053 |
FISA | +0.053 |
Route | +0.052 |
Neg logit contributions | |
sterdam | -0.061 |
anco | -0.061 |
ldom | -0.058 |
apest | -0.055 |
merce | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
sterdam | +0.006 |
anco | +0.006 |
ldom | +0.006 |
apest | +0.005 |
merce | +0.005 |
Neg logit contributions | |
PASS | -0.004 |
Musk | -0.004 |
RIS | -0.004 |
FISA | -0.004 |
Route | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
sterdam | +0.529 |
anco | +0.527 |
ldom | +0.501 |
apest | +0.472 |
merce | +0.469 |
Neg logit contributions | |
PASS | -0.501 |
Musk | -0.479 |
RIS | -0.462 |
FISA | -0.459 |
Route | -0.451 |
Token | her |
Token ID | 607 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
sterdam | +0.422 |
anco | +0.421 |
ldom | +0.402 |
apest | +0.382 |
merce | +0.379 |
Neg logit contributions | |
PASS | -0.308 |
Musk | -0.293 |
RIS | -0.280 |
FISA | -0.278 |
Route | -0.273 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
sterdam | +0.112 |
anco | +0.112 |
ldom | +0.107 |
apest | +0.101 |
merce | +0.100 |
Neg logit contributions | |
PASS | -0.094 |
Musk | -0.090 |
RIS | -0.087 |
FISA | -0.086 |
Route | -0.085 |
Token | slightly |
Token ID | 4622 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
sterdam | +0.222 |
anco | +0.222 |
ldom | +0.212 |
apest | +0.201 |
merce | +0.199 |
Neg logit contributions | |
PASS | -0.167 |
Musk | -0.158 |
RIS | -0.152 |
FISA | -0.151 |
Route | -0.148 |
Token | more |
Token ID | 517 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
sterdam | +0.123 |
anco | +0.122 |
ldom | +0.117 |
apest | +0.110 |
merce | +0.109 |
Neg logit contributions | |
PASS | -0.101 |
Musk | -0.096 |
RIS | -0.093 |
FISA | -0.092 |
Route | -0.090 |
Token | gang |
Token ID | 7706 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
PASS | +0.280 |
Musk | +0.268 |
RIS | +0.258 |
FISA | +0.256 |
Route | +0.252 |
Neg logit contributions | |
sterdam | -0.307 |
anco | -0.305 |
ldom | -0.291 |
apest | -0.274 |
merce | -0.273 |
Token | ster |
Token ID | 1706 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
PASS | +0.644 |
Musk | +0.617 |
RIS | +0.577 |
FISA | +0.559 |
Route | +0.558 |
Neg logit contributions | |
sterdam | -1.257 |
anco | -1.250 |
ldom | -1.221 |
apest | -1.158 |
merce | -1.147 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
sterdam | +0.465 |
anco | +0.463 |
ldom | +0.443 |
apest | +0.420 |
merce | +0.417 |
Neg logit contributions | |
PASS | -0.351 |
Musk | -0.335 |
RIS | -0.320 |
FISA | -0.318 |
Route | -0.312 |
Token | overweight |
Token ID | 22652 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
PASS | +0.280 |
Musk | +0.268 |
RIS | +0.258 |
FISA | +0.255 |
Route | +0.251 |
Neg logit contributions | |
sterdam | -0.336 |
anco | -0.335 |
ldom | -0.320 |
apest | -0.303 |
merce | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
sterdam | +0.347 |
anco | +0.347 |
ldom | +0.332 |
apest | +0.315 |
merce | +0.312 |
Neg logit contributions | |
PASS | -0.251 |
Musk | -0.236 |
RIS | -0.227 |
FISA | -0.226 |
Route | -0.221 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
PASS | +0.011 |
Musk | +0.011 |
RIS | +0.010 |
FISA | +0.010 |
Route | +0.010 |
Neg logit contributions | |
sterdam | -0.014 |
anco | -0.014 |
ldom | -0.013 |
apest | -0.012 |
merce | -0.012 |
Token | started |
Token ID | 2067 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
PASS | +0.117 |
Musk | +0.112 |
RIS | +0.107 |
FISA | +0.107 |
Route | +0.105 |
Neg logit contributions | |
sterdam | -0.145 |
anco | -0.144 |
ldom | -0.138 |
apest | -0.130 |
merce | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
sterdam | +1.581 |
anco | +1.580 |
ldom | +1.507 |
apest | +1.425 |
merce | +1.413 |
Neg logit contributions | |
PASS | -1.226 |
Musk | -1.162 |
FISA | -1.115 |
RIS | -1.115 |
Route | -1.086 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
sterdam | +0.311 |
anco | +0.310 |
ldom | +0.296 |
apest | +0.280 |
merce | +0.278 |
Neg logit contributions | |
PASS | -0.240 |
Musk | -0.228 |
RIS | -0.219 |
FISA | -0.218 |
Route | -0.213 |
Token | poor |
Token ID | 3595 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
PASS | +0.108 |
Musk | +0.103 |
RIS | +0.099 |
FISA | +0.098 |
Route | +0.097 |
Neg logit contributions | |
sterdam | -0.119 |
anco | -0.118 |
ldom | -0.113 |
apest | -0.106 |
merce | -0.105 |
Token | choice |
Token ID | 3572 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
PASS | +1.150 |
Musk | +1.106 |
RIS | +1.071 |
FISA | +1.062 |
Route | +1.047 |
Neg logit contributions | |
sterdam | -1.126 |
anco | -1.122 |
ldom | -1.070 |
apest | -0.997 |
merce | -0.996 |
Token | . |
Token ID | 13 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
sterdam | +0.023 |
anco | +0.023 |
ldom | +0.022 |
apest | +0.020 |
merce | +0.020 |
Neg logit contributions | |
PASS | -0.018 |
Musk | -0.017 |
RIS | -0.017 |
FISA | -0.017 |
Route | -0.016 |
Token | I |
Token ID | 314 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
PASS | +0.201 |
Musk | +0.190 |
RIS | +0.183 |
FISA | +0.182 |
Route | +0.178 |
Neg logit contributions | |
anco | -0.254 |
sterdam | -0.254 |
ldom | -0.242 |
apest | -0.229 |
merce | -0.227 |
Token | didnt |
Token ID | 42547 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
PASS | +0.097 |
Musk | +0.093 |
RIS | +0.089 |
FISA | +0.089 |
Route | +0.087 |
Neg logit contributions | |
sterdam | -0.118 |
anco | -0.118 |
ldom | -0.113 |
apest | -0.107 |
merce | -0.106 |
Token | finish |
Token ID | 5461 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
PASS | +0.733 |
Musk | +0.697 |
RIS | +0.668 |
FISA | +0.662 |
Route | +0.652 |
Neg logit contributions | |
sterdam | -0.983 |
anco | -0.976 |
ldom | -0.936 |
apest | -0.886 |
merce | -0.880 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
sterdam | +0.282 |
anco | +0.281 |
ldom | +0.269 |
apest | +0.255 |
merce | +0.253 |
Neg logit contributions | |
PASS | -0.211 |
Musk | -0.201 |
RIS | -0.193 |
FISA | -0.191 |
Route | -0.188 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
sterdam | +0.210 |
anco | +0.209 |
ldom | +0.199 |
apest | +0.187 |
merce | +0.186 |
Neg logit contributions | |
PASS | -0.205 |
Musk | -0.196 |
RIS | -0.189 |
FISA | -0.188 |
Route | -0.185 |
Token | in |
Token ID | 287 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
PASS | +0.769 |
Musk | +0.737 |
RIS | +0.704 |
FISA | +0.701 |
Route | +0.687 |
Neg logit contributions | |
sterdam | -1.023 |
anco | -1.015 |
ldom | -0.976 |
apest | -0.926 |
merce | -0.916 |
Token | time |
Token ID | 640 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
PASS | +0.091 |
Musk | +0.087 |
RIS | +0.083 |
FISA | +0.082 |
Route | +0.081 |
Neg logit contributions | |
sterdam | -0.131 |
anco | -0.131 |
ldom | -0.125 |
apest | -0.119 |
merce | -0.118 |
Token | massacre |
Token ID | 19050 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
sterdam | +0.703 |
anco | +0.701 |
ldom | +0.667 |
apest | +0.627 |
merce | +0.622 |
Neg logit contributions | |
PASS | -0.681 |
Musk | -0.653 |
RIS | -0.629 |
FISA | -0.628 |
Route | -0.617 |
Token | of |
Token ID | 286 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
sterdam | +0.260 |
anco | +0.258 |
ldom | +0.247 |
apest | +0.236 |
merce | +0.235 |
Neg logit contributions | |
PASS | -0.189 |
Musk | -0.181 |
RIS | -0.173 |
FISA | -0.173 |
Route | -0.170 |
Token | September |
Token ID | 2693 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
sterdam | +0.423 |
anco | +0.421 |
ldom | +0.404 |
apest | +0.383 |
merce | +0.382 |
Neg logit contributions | |
PASS | -0.299 |
Musk | -0.285 |
RIS | -0.272 |
FISA | -0.271 |
Route | -0.266 |
Token | 1986 |
Token ID | 12113 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
PASS | +0.744 |
Musk | +0.704 |
RIS | +0.667 |
FISA | +0.664 |
Route | +0.648 |
Neg logit contributions | |
sterdam | -1.344 |
anco | -1.336 |
ldom | -1.286 |
merce | -1.228 |
apest | -1.226 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
PASS | +0.479 |
Musk | +0.462 |
RIS | +0.441 |
FISA | +0.440 |
Route | +0.433 |
Neg logit contributions | |
sterdam | -0.611 |
anco | -0.609 |
ldom | -0.583 |
apest | -0.556 |
merce | -0.554 |
Token | Evidence |
Token ID | 21259 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
PASS | +0.122 |
Musk | +0.118 |
FISA | +0.112 |
RIS | +0.112 |
Route | +0.110 |
Neg logit contributions | |
sterdam | -0.163 |
anco | -0.163 |
ldom | -0.156 |
merce | -0.148 |
apest | -0.147 |
Token | suggested |
Token ID | 5220 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
PASS | +1.019 |
Musk | +0.983 |
FISA | +0.943 |
RIS | +0.943 |
Route | +0.919 |
Neg logit contributions | |
sterdam | -1.240 |
anco | -1.230 |
ldom | -1.188 |
apest | -1.131 |
merce | -1.118 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
sterdam | +0.731 |
anco | +0.729 |
ldom | +0.696 |
apest | +0.659 |
merce | +0.655 |
Neg logit contributions | |
PASS | -0.603 |
Musk | -0.578 |
RIS | -0.555 |
FISA | -0.552 |
Route | -0.542 |
Token | aid |
Token ID | 6133 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
PASS | +0.544 |
Musk | +0.532 |
FISA | +0.514 |
RIS | +0.513 |
Route | +0.504 |
Neg logit contributions | |
sterdam | -0.516 |
anco | -0.510 |
ldom | -0.485 |
merce | -0.461 |
apest | -0.456 |
Token | to |
Token ID | 284 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
sterdam | +0.100 |
anco | +0.100 |
ldom | +0.095 |
apest | +0.090 |
merce | +0.089 |
Neg logit contributions | |
PASS | -0.092 |
Musk | -0.088 |
RIS | -0.085 |
FISA | -0.085 |
Route | -0.084 |
Token | both |
Token ID | 1111 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
PASS | +0.125 |
Musk | +0.120 |
RIS | +0.115 |
FISA | +0.115 |
Route | +0.112 |
Neg logit contributions | |
sterdam | -0.175 |
anco | -0.174 |
ldom | -0.167 |
apest | -0.159 |
merce | -0.158 |
Token | 've |
Token ID | 1053 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
sterdam | +0.420 |
anco | +0.419 |
ldom | +0.401 |
apest | +0.381 |
merce | +0.379 |
Neg logit contributions | |
PASS | -0.298 |
Musk | -0.283 |
RIS | -0.271 |
FISA | -0.269 |
Route | -0.264 |
Token | read |
Token ID | 1100 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
sterdam | +1.605 |
anco | +1.604 |
ldom | +1.523 |
apest | +1.427 |
merce | +1.415 |
Neg logit contributions | |
PASS | -1.635 |
Musk | -1.560 |
RIS | -1.506 |
FISA | -1.497 |
Route | -1.471 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
sterdam | +1.342 |
anco | +1.340 |
ldom | +1.285 |
apest | +1.214 |
merce | +1.207 |
Neg logit contributions | |
PASS | -0.938 |
Musk | -0.885 |
RIS | -0.850 |
FISA | -0.841 |
Route | -0.823 |
Token | legal |
Token ID | 2742 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
sterdam | +0.080 |
anco | +0.080 |
ldom | +0.076 |
apest | +0.072 |
merce | +0.071 |
Neg logit contributions | |
PASS | -0.067 |
Musk | -0.064 |
RIS | -0.062 |
FISA | -0.061 |
Route | -0.060 |
Token | documents |
Token ID | 4963 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
PASS | +0.232 |
Musk | +0.223 |
RIS | +0.216 |
FISA | +0.214 |
Route | +0.211 |
Neg logit contributions | |
sterdam | -0.211 |
anco | -0.210 |
ldom | -0.199 |
apest | -0.187 |
merce | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
sterdam | +0.789 |
anco | +0.787 |
ldom | +0.752 |
apest | +0.712 |
merce | +0.707 |
Neg logit contributions | |
PASS | -0.630 |
Musk | -0.600 |
RIS | -0.577 |
FISA | -0.573 |
Route | -0.562 |
Token | maybe |
Token ID | 3863 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
sterdam | +0.090 |
anco | +0.090 |
ldom | +0.086 |
apest | +0.081 |
merce | +0.080 |
Neg logit contributions | |
PASS | -0.082 |
Musk | -0.079 |
RIS | -0.076 |
FISA | -0.076 |
Route | -0.074 |
Token | not |
Token ID | 407 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
PASS | +0.372 |
Musk | +0.353 |
FISA | +0.337 |
RIS | +0.336 |
Route | +0.330 |
Neg logit contributions | |
sterdam | -0.546 |
anco | -0.543 |
ldom | -0.520 |
merce | -0.496 |
apest | -0.496 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
sterdam | +0.184 |
anco | +0.183 |
ldom | +0.175 |
apest | +0.166 |
merce | +0.165 |
Neg logit contributions | |
PASS | -0.153 |
Musk | -0.146 |
RIS | -0.140 |
FISA | -0.140 |
Route | -0.137 |
Token | Here |
Token ID | 3423 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
sterdam | +0.870 |
anco | +0.868 |
ldom | +0.830 |
apest | +0.788 |
Indust | +0.780 |
Neg logit contributions | |
PASS | -0.628 |
Musk | -0.593 |
RIS | -0.570 |
FISA | -0.564 |
Route | -0.553 |
Token | 's |
Token ID | 338 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
sterdam | +1.237 |
anco | +1.233 |
ldom | +1.175 |
apest | +1.109 |
merce | +1.099 |
Neg logit contributions | |
PASS | -1.075 |
Musk | -1.019 |
RIS | -0.984 |
FISA | -0.976 |
Route | -0.959 |
Token | this |
Token ID | 428 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
PASS | +0.721 |
Musk | +0.693 |
RIS | +0.661 |
FISA | +0.658 |
Route | +0.645 |
Neg logit contributions | |
sterdam | -0.992 |
anco | -0.988 |
ldom | -0.946 |
apest | -0.902 |
merce | -0.896 |
Token | in |
Token ID | 287 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
PASS | +0.198 |
Musk | +0.191 |
RIS | +0.183 |
FISA | +0.182 |
Route | +0.179 |
Neg logit contributions | |
sterdam | -0.234 |
anco | -0.234 |
ldom | -0.223 |
apest | -0.211 |
merce | -0.210 |
Token | a |
Token ID | 257 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
sterdam | +0.518 |
anco | +0.516 |
ldom | +0.494 |
apest | +0.468 |
merce | +0.465 |
Neg logit contributions | |
PASS | -0.384 |
Musk | -0.365 |
RIS | -0.349 |
FISA | -0.347 |
Route | -0.340 |
Token | week |
Token ID | 1285 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
PASS | +0.179 |
Musk | +0.171 |
RIS | +0.165 |
FISA | +0.164 |
Route | +0.161 |
Neg logit contributions | |
sterdam | -0.217 |
anco | -0.216 |
ldom | -0.206 |
apest | -0.195 |
merce | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
anco | +0.260 |
sterdam | +0.260 |
ldom | +0.247 |
apest | +0.234 |
merce | +0.234 |
Neg logit contributions | |
PASS | -0.224 |
Musk | -0.216 |
RIS | -0.206 |
FISA | -0.205 |
Route | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
sterdam | +0.180 |
anco | +0.180 |
ldom | +0.172 |
apest | +0.163 |
merce | +0.162 |
Neg logit contributions | |
PASS | -0.130 |
Musk | -0.123 |
RIS | -0.118 |
FISA | -0.117 |
Route | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
sterdam | +0.199 |
anco | +0.198 |
ldom | +0.189 |
apest | +0.179 |
merce | +0.178 |
Neg logit contributions | |
PASS | -0.160 |
Musk | -0.152 |
RIS | -0.146 |
FISA | -0.146 |
Route | -0.143 |
Token | Still |
Token ID | 9590 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
sterdam | +0.287 |
anco | +0.286 |
ldom | +0.273 |
apest | +0.258 |
merce | +0.256 |
Neg logit contributions | |
PASS | -0.246 |
Musk | -0.234 |
RIS | -0.225 |
FISA | -0.223 |
Route | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
PASS | +0.764 |
Musk | +0.729 |
RIS | +0.697 |
FISA | +0.688 |
Route | +0.678 |
Neg logit contributions | |
sterdam | -1.135 |
anco | -1.132 |
ldom | -1.089 |
apest | -1.030 |
merce | -1.028 |
Token | there |
Token ID | 612 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
PASS | +0.323 |
Musk | +0.310 |
RIS | +0.295 |
FISA | +0.293 |
Route | +0.288 |
Neg logit contributions | |
sterdam | -0.456 |
anco | -0.453 |
ldom | -0.435 |
apest | -0.415 |
merce | -0.411 |
Token | is |
Token ID | 318 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
sterdam | +0.073 |
anco | +0.073 |
ldom | +0.070 |
apest | +0.066 |
merce | +0.065 |
Neg logit contributions | |
PASS | -0.064 |
Musk | -0.061 |
RIS | -0.059 |
FISA | -0.058 |
Route | -0.057 |
Token | two |
Token ID | 734 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
PASS | +0.643 |
Musk | +0.616 |
RIS | +0.595 |
FISA | +0.588 |
Route | +0.581 |
Neg logit contributions | |
sterdam | -0.717 |
anco | -0.716 |
ldom | -0.680 |
apest | -0.646 |
merce | -0.636 |
Token | new |
Token ID | 649 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
sterdam | +2.179 |
anco | +2.168 |
ldom | +2.069 |
apest | +1.939 |
merce | +1.939 |
Neg logit contributions | |
PASS | -1.962 |
Musk | -1.868 |
FISA | -1.789 |
RIS | -1.787 |
Route | -1.748 |
Token | methods |
Token ID | 5050 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
sterdam | +0.607 |
anco | +0.605 |
ldom | +0.577 |
apest | +0.545 |
merce | +0.541 |
Neg logit contributions | |
PASS | -0.519 |
Musk | -0.495 |
RIS | -0.477 |
FISA | -0.473 |
Route | -0.465 |
Token | of |
Token ID | 286 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
sterdam | +0.045 |
anco | +0.045 |
ldom | +0.043 |
apest | +0.040 |
merce | +0.040 |
Neg logit contributions | |
PASS | -0.037 |
Musk | -0.036 |
RIS | -0.034 |
FISA | -0.034 |
Route | -0.033 |
Token | packaging |
Token ID | 16846 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
PASS | +0.044 |
Musk | +0.042 |
RIS | +0.040 |
FISA | +0.040 |
Route | +0.039 |
Neg logit contributions | |
sterdam | -0.048 |
anco | -0.048 |
ldom | -0.046 |
apest | -0.043 |
merce | -0.043 |
Token | software |
Token ID | 3788 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
PASS | +0.459 |
Musk | +0.441 |
RIS | +0.425 |
FISA | +0.421 |
Route | +0.415 |
Neg logit contributions | |
sterdam | -0.558 |
anco | -0.555 |
ldom | -0.531 |
apest | -0.503 |
merce | -0.498 |
Token | have |
Token ID | 423 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
sterdam | +0.415 |
anco | +0.414 |
ldom | +0.395 |
apest | +0.374 |
merce | +0.371 |
Neg logit contributions | |
PASS | -0.333 |
Musk | -0.318 |
RIS | -0.305 |
FISA | -0.303 |
Route | -0.297 |
Token | been |
Token ID | 587 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
sterdam | +0.086 |
anco | +0.086 |
ldom | +0.082 |
apest | +0.078 |
merce | +0.077 |
Neg logit contributions | |
PASS | -0.070 |
Musk | -0.066 |
RIS | -0.064 |
FISA | -0.063 |
Route | -0.062 |
Token | getting |
Token ID | 1972 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
sterdam | +1.072 |
anco | +1.069 |
ldom | +1.018 |
apest | +0.963 |
merce | +0.955 |
Neg logit contributions | |
PASS | -0.909 |
Musk | -0.864 |
RIS | -0.832 |
FISA | -0.827 |
Route | -0.812 |
Token | a |
Token ID | 257 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
PASS | +0.448 |
Musk | +0.429 |
RIS | +0.410 |
FISA | +0.409 |
Route | +0.401 |
Neg logit contributions | |
sterdam | -0.552 |
anco | -0.550 |
ldom | -0.526 |
apest | -0.500 |
merce | -0.499 |
Token | lot |
Token ID | 1256 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
sterdam | +0.053 |
anco | +0.053 |
ldom | +0.051 |
apest | +0.048 |
merce | +0.047 |
Neg logit contributions | |
PASS | -0.053 |
Musk | -0.051 |
RIS | -0.049 |
FISA | -0.049 |
Route | -0.048 |
Token | A |
Token ID | 317 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
PASS | +0.841 |
Musk | +0.813 |
RIS | +0.768 |
FISA | +0.764 |
Route | +0.751 |
Neg logit contributions | |
sterdam | -1.252 |
anco | -1.242 |
ldom | -1.196 |
merce | -1.139 |
apest | -1.132 |
Token | . |
Token ID | 13 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
PASS | +0.390 |
Musk | +0.374 |
RIS | +0.360 |
FISA | +0.358 |
Route | +0.352 |
Neg logit contributions | |
sterdam | -0.412 |
anco | -0.410 |
ldom | -0.390 |
apest | -0.368 |
merce | -0.365 |
Token | Ra |
Token ID | 7567 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
PASS | +0.305 |
Musk | +0.291 |
RIS | +0.277 |
FISA | +0.275 |
Route | +0.270 |
Neg logit contributions | |
sterdam | -0.450 |
anco | -0.448 |
ldom | -0.430 |
apest | -0.408 |
merce | -0.407 |
Token | ich |
Token ID | 488 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
PASS | +0.321 |
Musk | +0.308 |
RIS | +0.295 |
FISA | +0.293 |
Route | +0.290 |
Neg logit contributions | |
sterdam | -0.327 |
anco | -0.324 |
ldom | -0.308 |
apest | -0.290 |
merce | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
sterdam | +0.320 |
anco | +0.319 |
ldom | +0.305 |
apest | +0.289 |
merce | +0.286 |
Neg logit contributions | |
PASS | -0.266 |
Musk | -0.254 |
RIS | -0.244 |
FISA | -0.243 |
Route | -0.238 |
Token | a |
Token ID | 257 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
PASS | +0.361 |
Musk | +0.347 |
RIS | +0.332 |
FISA | +0.328 |
Route | +0.323 |
Neg logit contributions | |
sterdam | -0.489 |
anco | -0.489 |
ldom | -0.469 |
apest | -0.446 |
merce | -0.444 |
Token | leading |
Token ID | 3756 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
PASS | +0.158 |
Musk | +0.152 |
RIS | +0.146 |
FISA | +0.145 |
Route | +0.142 |
Neg logit contributions | |
anco | -0.198 |
sterdam | -0.197 |
ldom | -0.189 |
apest | -0.179 |
merce | -0.178 |
Token | marijuana |
Token ID | 5727 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
PASS | +0.201 |
Musk | +0.194 |
RIS | +0.187 |
FISA | +0.185 |
Route | +0.182 |
Neg logit contributions | |
anco | -0.230 |
sterdam | -0.230 |
ldom | -0.221 |
apest | -0.208 |
merce | -0.207 |
Token | attorney |
Token ID | 6136 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
sterdam | +0.212 |
anco | +0.211 |
ldom | +0.201 |
apest | +0.191 |
merce | +0.189 |
Neg logit contributions | |
PASS | -0.173 |
Musk | -0.164 |
RIS | -0.158 |
FISA | -0.157 |
Route | -0.154 |
Token | most |
Token ID | 749 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
sterdam | +1.526 |
anco | +1.522 |
ldom | +1.447 |
apest | +1.361 |
merce | +1.356 |
Neg logit contributions | |
PASS | -1.289 |
Musk | -1.215 |
RIS | -1.171 |
FISA | -1.163 |
Route | -1.144 |
Token | remarkable |
Token ID | 11004 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
sterdam | +0.123 |
anco | +0.122 |
ldom | +0.116 |
apest | +0.109 |
merce | +0.109 |
Neg logit contributions | |
PASS | -0.122 |
Musk | -0.117 |
RIS | -0.113 |
FISA | -0.112 |
Route | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
PASS | +0.224 |
Musk | +0.214 |
RIS | +0.206 |
FISA | +0.204 |
Route | +0.200 |
Neg logit contributions | |
anco | -0.263 |
sterdam | -0.262 |
ldom | -0.250 |
apest | -0.237 |
Indust | -0.233 |
Token | To |
Token ID | 2514 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
PASS | +0.044 |
Musk | +0.042 |
RIS | +0.040 |
FISA | +0.040 |
Route | +0.039 |
Neg logit contributions | |
sterdam | -0.049 |
anco | -0.049 |
ldom | -0.047 |
apest | -0.044 |
merce | -0.044 |
Token | try |
Token ID | 1949 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
sterdam | +0.062 |
anco | +0.062 |
ldom | +0.059 |
apest | +0.056 |
merce | +0.055 |
Neg logit contributions | |
PASS | -0.056 |
Musk | -0.053 |
RIS | -0.051 |
FISA | -0.051 |
Route | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
PASS | +1.037 |
Musk | +0.983 |
RIS | +0.951 |
FISA | +0.946 |
Route | +0.920 |
Neg logit contributions | |
anco | -1.522 |
sterdam | -1.521 |
ldom | -1.461 |
apest | -1.389 |
merce | -1.379 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
sterdam | +0.801 |
anco | +0.798 |
ldom | +0.762 |
apest | +0.728 |
merce | +0.724 |
Neg logit contributions | |
PASS | -0.495 |
Musk | -0.466 |
RIS | -0.442 |
FISA | -0.439 |
Route | -0.431 |
Token | click |
Token ID | 3904 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
sterdam | +0.451 |
anco | +0.450 |
ldom | +0.431 |
apest | +0.409 |
merce | +0.406 |
Neg logit contributions | |
PASS | -0.321 |
Musk | -0.304 |
RIS | -0.291 |
FISA | -0.290 |
Route | -0.283 |
Token | the |
Token ID | 262 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
sterdam | +1.229 |
anco | +1.222 |
ldom | +1.169 |
apest | +1.109 |
merce | +1.103 |
Neg logit contributions | |
PASS | -0.893 |
Musk | -0.848 |
RIS | -0.808 |
FISA | -0.802 |
Route | -0.786 |
Token | " |
Token ID | 366 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
PASS | +0.185 |
Musk | +0.177 |
RIS | +0.172 |
FISA | +0.170 |
Route | +0.167 |
Neg logit contributions | |
sterdam | -0.222 |
anco | -0.222 |
ldom | -0.212 |
apest | -0.199 |
merce | -0.198 |
Token | F |
Token ID | 37 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
PASS | +0.960 |
Musk | +0.902 |
RIS | +0.878 |
FISA | +0.873 |
Route | +0.859 |
Neg logit contributions | |
sterdam | -0.938 |
anco | -0.936 |
ldom | -0.891 |
apest | -0.831 |
merce | -0.827 |
Token | EN |
Token ID | 1677 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
PASS | +0.061 |
Musk | +0.058 |
RIS | +0.056 |
FISA | +0.056 |
Route | +0.055 |
Neg logit contributions | |
sterdam | -0.065 |
anco | -0.065 |
ldom | -0.062 |
merce | -0.059 |
apest | -0.059 |
Token | & |
Token ID | 1222 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
PASS | +0.194 |
Musk | +0.184 |
RIS | +0.178 |
FISA | +0.176 |
Route | +0.173 |
Neg logit contributions | |
sterdam | -0.246 |
anco | -0.245 |
ldom | -0.235 |
apest | -0.222 |
merce | -0.221 |
Token | op |
Token ID | 1034 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
PASS | +0.183 |
Musk | +0.175 |
RIS | +0.168 |
FISA | +0.167 |
Route | +0.164 |
Neg logit contributions | |
sterdam | -0.208 |
anco | -0.207 |
ldom | -0.197 |
apest | -0.186 |
merce | -0.185 |
Token | - |
Token ID | 12 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
PASS | +0.269 |
Musk | +0.260 |
FISA | +0.245 |
RIS | +0.244 |
Route | +0.241 |
Neg logit contributions | |
sterdam | -0.404 |
anco | -0.402 |
ldom | -0.386 |
apest | -0.371 |
merce | -0.366 |
Token | ed |
Token ID | 276 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
sterdam | +0.153 |
anco | +0.151 |
ldom | +0.139 |
apest | +0.127 |
merce | +0.127 |
Neg logit contributions | |
PASS | -0.338 |
Musk | -0.330 |
RIS | -0.320 |
FISA | -0.319 |
Route | -0.316 |
Token | for |
Token ID | 329 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
PASS | +0.494 |
Musk | +0.478 |
RIS | +0.453 |
FISA | +0.450 |
Route | +0.441 |
Neg logit contributions | |
sterdam | -0.662 |
anco | -0.654 |
ldom | -0.626 |
apest | -0.601 |
merce | -0.596 |
Token | The |
Token ID | 383 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
PASS | +0.203 |
Musk | +0.196 |
RIS | +0.188 |
FISA | +0.186 |
Route | +0.183 |
Neg logit contributions | |
sterdam | -0.265 |
anco | -0.260 |
ldom | -0.252 |
merce | -0.240 |
apest | -0.238 |
Token | Guardian |
Token ID | 8283 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
sterdam | +0.650 |
anco | +0.646 |
ldom | +0.622 |
merce | +0.589 |
apest | +0.588 |
Neg logit contributions | |
PASS | -0.445 |
Musk | -0.423 |
RIS | -0.407 |
FISA | -0.402 |
Route | -0.395 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
anco | +3.116 |
sterdam | +3.110 |
ldom | +2.973 |
apest | +2.818 |
Indust | +2.796 |
Neg logit contributions | |
PASS | -2.274 |
Musk | -2.137 |
RIS | -2.049 |
FISA | -2.046 |
Route | -2.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
sterdam | +0.025 |
anco | +0.025 |
ldom | +0.024 |
apest | +0.023 |
merce | +0.022 |
Neg logit contributions | |
PASS | -0.016 |
Musk | -0.016 |
RIS | -0.015 |
FISA | -0.015 |
Route | -0.014 |
Token | Oscar |
Token ID | 15694 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
sterdam | +0.017 |
anco | +0.017 |
ldom | +0.016 |
apest | +0.015 |
merce | +0.015 |
Neg logit contributions | |
PASS | -0.013 |
Musk | -0.012 |
RIS | -0.012 |
FISA | -0.012 |
Route | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
PASS | +0.227 |
Musk | +0.217 |
RIS | +0.207 |
FISA | +0.205 |
Route | +0.202 |
Neg logit contributions | |
sterdam | -0.314 |
anco | -0.313 |
ldom | -0.300 |
apest | -0.284 |
merce | -0.284 |
Token | winning |
Token ID | 14463 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
sterdam | +0.546 |
anco | +0.544 |
ldom | +0.520 |
apest | +0.492 |
merce | +0.488 |
Neg logit contributions | |
PASS | -0.454 |
Musk | -0.432 |
RIS | -0.416 |
FISA | -0.413 |
Route | -0.405 |
Token | of |
Token ID | 286 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
PASS | +1.187 |
Musk | +1.144 |
FISA | +1.094 |
RIS | +1.085 |
Route | +1.074 |
Neg logit contributions | |
sterdam | -1.539 |
anco | -1.511 |
ldom | -1.469 |
merce | -1.418 |
apest | -1.391 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
anco | +0.054 |
sterdam | +0.054 |
ldom | +0.052 |
merce | +0.049 |
apest | +0.049 |
Neg logit contributions | |
PASS | -0.039 |
Musk | -0.037 |
RIS | -0.036 |
FISA | -0.036 |
Route | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
sterdam | +0.175 |
anco | +0.175 |
ldom | +0.168 |
apest | +0.158 |
merce | +0.158 |
Neg logit contributions | |
PASS | -0.145 |
Musk | -0.140 |
RIS | -0.135 |
FISA | -0.134 |
Route | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
sterdam | +0.710 |
anco | +0.707 |
ldom | +0.676 |
apest | +0.637 |
merce | +0.634 |
Neg logit contributions | |
PASS | -0.606 |
Musk | -0.578 |
RIS | -0.556 |
FISA | -0.553 |
Route | -0.543 |
Token |
|
Token ID | 198 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
anco | +0.513 |
sterdam | +0.510 |
ldom | +0.485 |
apest | +0.462 |
Indust | +0.452 |
Neg logit contributions | |
PASS | -0.450 |
Musk | -0.429 |
RIS | -0.414 |
FISA | -0.411 |
�醒 | -0.408 |
Token | Explore |
Token ID | 35433 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
sterdam | +0.582 |
anco | +0.579 |
ldom | +0.553 |
apest | +0.520 |
merce | +0.520 |
Neg logit contributions | |
PASS | -0.521 |
Musk | -0.495 |
RIS | -0.476 |
FISA | -0.473 |
Route | -0.465 |
Token | further |
Token ID | 2252 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
sterdam | +2.080 |
anco | +2.076 |
ldom | +1.950 |
apest | +1.848 |
merce | +1.816 |
Neg logit contributions | |
PASS | -2.203 |
Musk | -2.061 |
RIS | -2.030 |
FISA | -2.000 |
@# | -1.981 |
Token | : |
Token ID | 25 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
PASS | +0.050 |
Musk | +0.047 |
RIS | +0.045 |
FISA | +0.045 |
Route | +0.044 |
Neg logit contributions | |
sterdam | -0.064 |
anco | -0.064 |
ldom | -0.061 |
apest | -0.058 |
merce | -0.057 |
Token | New |
Token ID | 968 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
sterdam | +1.083 |
anco | +1.078 |
ldom | +1.025 |
Indust | +0.982 |
apest | +0.980 |
Neg logit contributions | |
PASS | -0.743 |
Musk | -0.689 |
RIS | -0.668 |
FISA | -0.662 |
@# | -0.651 |
Token | Insight |
Token ID | 39917 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
sterdam | +1.171 |
anco | +1.161 |
ldom | +1.097 |
apest | +1.046 |
Indust | +1.033 |
Neg logit contributions | |
PASS | -1.009 |
Musk | -0.952 |
RIS | -0.918 |
FISA | -0.912 |
Route | -0.895 |
Token | Into |
Token ID | 20008 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
PASS | +0.369 |
Musk | +0.349 |
RIS | +0.332 |
FISA | +0.328 |
Route | +0.323 |
Neg logit contributions | |
sterdam | -0.639 |
anco | -0.638 |
ldom | -0.614 |
apest | -0.586 |
merce | -0.583 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
PASS | +0.651 |
Musk | +0.626 |
RIS | +0.603 |
FISA | +0.590 |
Route | +0.583 |
Neg logit contributions | |
sterdam | -0.835 |
anco | -0.832 |
ldom | -0.800 |
apest | -0.757 |
merce | -0.753 |
Token |
|
Token ID | 198 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
sterdam | +0.268 |
anco | +0.267 |
ldom | +0.256 |
apest | +0.243 |
merce | +0.242 |
Neg logit contributions | |
PASS | -0.173 |
Musk | -0.164 |
RIS | -0.156 |
FISA | -0.155 |
Route | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
PASS | +0.003 |
Musk | +0.003 |
RIS | +0.002 |
FISA | +0.002 |
Route | +0.002 |
Neg logit contributions | |
sterdam | -0.003 |
anco | -0.003 |
ldom | -0.003 |
apest | -0.003 |
merce | -0.003 |
Token | It |
Token ID | 1026 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
sterdam | +0.244 |
anco | +0.242 |
ldom | +0.231 |
apest | +0.218 |
merce | +0.217 |
Neg logit contributions | |
PASS | -0.215 |
Musk | -0.205 |
RIS | -0.197 |
FISA | -0.196 |
Route | -0.192 |
Token | 's |
Token ID | 338 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
sterdam | +0.200 |
anco | +0.199 |
ldom | +0.190 |
apest | +0.180 |
merce | +0.178 |
Neg logit contributions | |
PASS | -0.170 |
Musk | -0.162 |
RIS | -0.156 |
FISA | -0.155 |
Route | -0.152 |
Token | interesting |
Token ID | 3499 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
sterdam | +1.590 |
anco | +1.586 |
ldom | +1.513 |
apest | +1.427 |
Indust | +1.412 |
Neg logit contributions | |
PASS | -1.300 |
Musk | -1.229 |
RIS | -1.181 |
FISA | -1.180 |
Route | -1.152 |
Token | here |
Token ID | 994 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
sterdam | +2.455 |
anco | +2.449 |
ldom | +2.338 |
apest | +2.208 |
merce | +2.190 |
Neg logit contributions | |
PASS | -1.882 |
Musk | -1.768 |
RIS | -1.714 |
FISA | -1.695 |
Route | -1.659 |
Token | because |
Token ID | 780 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
sterdam | +1.159 |
anco | +1.155 |
ldom | +1.103 |
apest | +1.044 |
merce | +1.037 |
Neg logit contributions | |
PASS | -0.943 |
Musk | -0.900 |
RIS | -0.864 |
FISA | -0.858 |
Route | -0.843 |
Token | this |
Token ID | 428 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
anco | +1.781 |
sterdam | +1.780 |
ldom | +1.701 |
apest | +1.610 |
Indust | +1.600 |
Neg logit contributions | |
PASS | -1.261 |
Musk | -1.174 |
RIS | -1.136 |
FISA | -1.128 |
Route | -1.104 |
Token | is |
Token ID | 318 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
sterdam | +0.092 |
anco | +0.092 |
ldom | +0.087 |
apest | +0.083 |
merce | +0.082 |
Neg logit contributions | |
PASS | -0.078 |
Musk | -0.075 |
RIS | -0.072 |
FISA | -0.072 |
Route | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
sterdam | +1.134 |
anco | +1.131 |
ldom | +1.081 |
apest | +1.023 |
merce | +1.015 |
Neg logit contributions | |
PASS | -0.851 |
Musk | -0.803 |
RIS | -0.773 |
FISA | -0.768 |
Route | -0.752 |
Token | by |
Token ID | 416 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
sterdam | +2.151 |
anco | +2.140 |
ldom | +2.039 |
apest | +1.921 |
merce | +1.901 |
Neg logit contributions | |
PASS | -1.931 |
Musk | -1.842 |
RIS | -1.769 |
FISA | -1.758 |
Route | -1.724 |
Token | Paula |
Token ID | 36025 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
sterdam | +0.714 |
anco | +0.711 |
ldom | +0.682 |
apest | +0.647 |
merce | +0.645 |
Neg logit contributions | |
PASS | -0.497 |
Musk | -0.473 |
RIS | -0.454 |
FISA | -0.450 |
Route | -0.440 |
Token | Bron |
Token ID | 8923 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
sterdam | +0.532 |
anco | +0.529 |
ldom | +0.508 |
apest | +0.482 |
merce | +0.481 |
Neg logit contributions | |
PASS | -0.356 |
Musk | -0.340 |
RIS | -0.324 |
FISA | -0.321 |
Route | -0.315 |
Token | stein |
Token ID | 5714 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
sterdam | +0.070 |
anco | +0.069 |
ldom | +0.066 |
apest | +0.061 |
merce | +0.061 |
Neg logit contributions | |
PASS | -0.079 |
Musk | -0.076 |
RIS | -0.073 |
FISA | -0.073 |
Route | -0.072 |
Token | / |
Token ID | 14 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
sterdam | +1.231 |
anco | +1.227 |
ldom | +1.175 |
apest | +1.115 |
merce | +1.108 |
Neg logit contributions | |
PASS | -0.891 |
Musk | -0.846 |
RIS | -0.812 |
FISA | -0.805 |
Route | -0.789 |
Token | Getty |
Token ID | 6633 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
sterdam | +0.248 |
anco | +0.246 |
ldom | +0.234 |
merce | +0.218 |
apest | +0.218 |
Neg logit contributions | |
PASS | -0.292 |
Musk | -0.278 |
RIS | -0.271 |
FISA | -0.269 |
Route | -0.265 |
Token | Images |
Token ID | 5382 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
sterdam | +1.784 |
anco | +1.776 |
ldom | +1.675 |
apest | +1.559 |
merce | +1.545 |
Neg logit contributions | |
PASS | -2.316 |
Musk | -2.229 |
RIS | -2.161 |
FISA | -2.151 |
Route | -2.118 |
Token | ) |
Token ID | 8 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
sterdam | +1.749 |
anco | +1.744 |
ldom | +1.654 |
apest | +1.551 |
merce | +1.537 |
Neg logit contributions | |
PASS | -1.877 |
Musk | -1.798 |
RIS | -1.737 |
FISA | -1.726 |
Route | -1.699 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sterdam | +1.211 |
anco | +1.206 |
ldom | +1.153 |
apest | +1.091 |
merce | +1.084 |
Neg logit contributions | |
PASS | -0.959 |
Musk | -0.914 |
RIS | -0.878 |
FISA | -0.872 |
Route | -0.855 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anco | +1.226 |
sterdam | +1.204 |
ldom | +1.148 |
apest | +1.098 |
Indust | +1.070 |
Neg logit contributions | |
PASS | -1.137 |
Musk | -1.092 |
�醒 | -1.062 |
RIS | -1.052 |
FISA | -1.046 |
Token | The |
Token ID | 464 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
sterdam | +1.421 |
anco | +1.417 |
ldom | +1.347 |
apest | +1.269 |
merce | +1.257 |
Neg logit contributions | |
PASS | -1.376 |
Musk | -1.319 |
RIS | -1.273 |
FISA | -1.266 |
Route | -1.244 |
Token | ations |
Token ID | 602 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
sterdam | +0.384 |
anco | +0.379 |
ldom | +0.361 |
apest | +0.338 |
merce | +0.337 |
Neg logit contributions | |
PASS | -0.413 |
Musk | -0.396 |
RIS | -0.382 |
FISA | -0.380 |
Route | -0.375 |
Token | chool |
Token ID | 1251 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
PASS | +0.626 |
Musk | +0.589 |
RIS | +0.572 |
FISA | +0.566 |
ACC | +0.563 |
Neg logit contributions | |
sterdam | -0.684 |
anco | -0.682 |
ldom | -0.651 |
apest | -0.612 |
merce | -0.610 |
Token | sc |
Token ID | 1416 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
PASS | +0.218 |
Musk | +0.207 |
RIS | +0.201 |
FISA | +0.199 |
ACC | +0.197 |
Neg logit contributions | |
sterdam | -0.215 |
anco | -0.214 |
ldom | -0.204 |
apest | -0.191 |
merce | -0.190 |
Token | up |
Token ID | 929 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
sterdam | +0.617 |
anco | +0.615 |
ldom | +0.586 |
apest | +0.553 |
merce | +0.552 |
Neg logit contributions | |
PASS | -0.527 |
Musk | -0.502 |
RIS | -0.484 |
FISA | -0.478 |
Route | -0.472 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
sterdam | +0.831 |
anco | +0.829 |
ldom | +0.789 |
apest | +0.743 |
merce | +0.737 |
Neg logit contributions | |
PASS | -0.771 |
Musk | -0.736 |
RIS | -0.711 |
FISA | -0.705 |
Route | -0.693 |
Token | com |
Token ID | 785 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
sterdam | +0.706 |
anco | +0.704 |
ldom | +0.667 |
apest | +0.626 |
merce | +0.621 |
Neg logit contributions | |
PASS | -0.758 |
Musk | -0.726 |
RIS | -0.702 |
FISA | -0.698 |
Route | -0.687 |
Token | for |
Token ID | 329 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
sterdam | +2.399 |
anco | +2.393 |
ldom | +2.280 |
apest | +2.169 |
merce | +2.138 |
Neg logit contributions | |
PASS | -1.892 |
Musk | -1.787 |
RIS | -1.719 |
FISA | -1.716 |
Route | -1.673 |
Token | more |
Token ID | 517 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
sterdam | +0.703 |
anco | +0.701 |
ldom | +0.667 |
apest | +0.629 |
merce | +0.623 |
Neg logit contributions | |
PASS | -0.645 |
Musk | -0.616 |
RIS | -0.594 |
FISA | -0.590 |
Route | -0.579 |
Token | information |
Token ID | 1321 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
sterdam | +0.188 |
anco | +0.187 |
ldom | +0.176 |
apest | +0.162 |
merce | +0.161 |
Neg logit contributions | |
PASS | -0.295 |
Musk | -0.285 |
RIS | -0.277 |
FISA | -0.276 |
Route | -0.272 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
sterdam | +0.352 |
anco | +0.352 |
ldom | +0.336 |
apest | +0.317 |
merce | +0.315 |
Neg logit contributions | |
PASS | -0.313 |
Musk | -0.299 |
RIS | -0.288 |
FISA | -0.286 |
Route | -0.282 |
Token | CNN |
Token ID | 18474 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
PASS | +2.374 |
Musk | +2.187 |
RIS | +2.089 |
@# | +2.085 |
FISA | +2.072 |
Neg logit contributions | |
sterdam | -2.620 |
anco | -2.600 |
ldom | -2.491 |
merce | -2.362 |
Indust | -2.341 |