Token | 14 |
Token ID | 1415 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Line | +0.414 |
Tig | +0.394 |
Beet | +0.393 |
metaphor | +0.348 |
Vide | +0.345 |
Neg logit contributions | |
ibaba | -0.423 |
naires | -0.395 |
unin | -0.389 |
ivo | -0.381 |
naire | -0.377 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ibaba | +0.349 |
naires | +0.331 |
unin | +0.328 |
ivo | +0.323 |
naire | +0.320 |
Neg logit contributions | |
Line | -0.211 |
Tig | -0.199 |
Beet | -0.198 |
metaphor | -0.169 |
Vide | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ibaba | +1.711 |
naires | +1.607 |
unin | +1.585 |
ivo | +1.554 |
naire | +1.540 |
Neg logit contributions | |
Line | -1.604 |
Tig | -1.530 |
Beet | -1.524 |
metaphor | -1.350 |
Vide | -1.334 |
Token |
|
Token ID | 198 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ibaba | +0.495 |
naires | +0.460 |
unin | +0.456 |
ivo | +0.448 |
orsche | +0.446 |
Neg logit contributions | |
Line | -0.440 |
Tig | -0.419 |
Beet | -0.414 |
metaphor | -0.367 |
Vide | -0.364 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ibaba | +0.350 |
naires | +0.325 |
unin | +0.320 |
ivo | +0.312 |
naire | +0.308 |
Neg logit contributions | |
Line | -0.504 |
Tig | -0.486 |
Beet | -0.486 |
metaphor | -0.439 |
Vide | -0.435 |
Token | Share |
Token ID | 8734 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
ibaba | +2.301 |
naires | +2.153 |
unin | +2.126 |
ivo | +2.081 |
naire | +2.063 |
Neg logit contributions | |
Line | -2.197 |
Tig | -2.095 |
Beet | -2.078 |
metaphor | -1.842 |
Vide | -1.829 |
Token | this |
Token ID | 428 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ibaba | +3.988 |
naires | +3.736 |
unin | +3.668 |
ivo | +3.621 |
naire | +3.585 |
Neg logit contributions | |
Line | -4.396 |
Beet | -4.277 |
Tig | -4.131 |
wart | -3.791 |
metaphor | -3.768 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ibaba | +1.983 |
naires | +1.891 |
unin | +1.870 |
ivo | +1.849 |
orsche | +1.833 |
Neg logit contributions | |
Line | -0.876 |
Tig | -0.811 |
Beet | -0.791 |
metaphor | -0.649 |
Vide | -0.637 |
Token | on |
Token ID | 319 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
Line | +0.069 |
Tig | +0.066 |
Beet | +0.064 |
polarized | +0.055 |
Passive | +0.055 |
Neg logit contributions | |
ibaba | -0.101 |
unin | -0.094 |
naires | -0.092 |
orsche | -0.091 |
ivo | -0.091 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Line | +0.469 |
Tig | +0.439 |
Beet | +0.422 |
metaphor | +0.375 |
Vide | +0.369 |
Neg logit contributions | |
ibaba | -0.676 |
naires | -0.640 |
unin | -0.628 |
ivo | -0.623 |
orsche | -0.614 |
Token | Share |
Token ID | 8734 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ibaba | +0.946 |
naires | +0.885 |
unin | +0.879 |
ivo | +0.865 |
orsche | +0.849 |
Neg logit contributions | |
Line | -0.828 |
Tig | -0.793 |
Beet | -0.776 |
metaphor | -0.677 |
Vide | -0.674 |
Token | or |
Token ID | 273 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Line | +0.597 |
Tig | +0.571 |
Beet | +0.565 |
metaphor | +0.508 |
Vide | +0.504 |
Neg logit contributions | |
ibaba | -0.549 |
naires | -0.511 |
unin | -0.505 |
ivo | -0.489 |
naire | -0.485 |
Token |
|
Token ID | 198 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ibaba | +1.225 |
naires | +1.157 |
unin | +1.133 |
naire | +1.121 |
ivo | +1.119 |
Neg logit contributions | |
Line | -1.207 |
Tig | -1.158 |
Beet | -1.157 |
metaphor | -1.039 |
polarized | -1.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ibaba | +0.271 |
naires | +0.250 |
unin | +0.249 |
orsche | +0.245 |
ivo | +0.244 |
Neg logit contributions | |
Line | -0.235 |
Tig | -0.223 |
Beet | -0.220 |
metaphor | -0.194 |
Vide | -0.193 |
Token | H |
Token ID | 39 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ibaba | +0.144 |
naires | +0.135 |
unin | +0.133 |
ivo | +0.130 |
naire | +0.129 |
Neg logit contributions | |
Line | -0.133 |
Tig | -0.127 |
Beet | -0.127 |
metaphor | -0.112 |
Vide | -0.111 |
Token | orn |
Token ID | 1211 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ibaba | +1.814 |
naires | +1.700 |
unin | +1.680 |
ivo | +1.647 |
naire | +1.626 |
Neg logit contributions | |
Line | -1.768 |
Tig | -1.690 |
Beet | -1.686 |
metaphor | -1.496 |
Vide | -1.479 |
Token | of |
Token ID | 286 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ibaba | +3.828 |
naires | +3.672 |
naire | +3.573 |
ivo | +3.567 |
unin | +3.544 |
Neg logit contributions | |
Line | -3.241 |
Tig | -3.099 |
Beet | -3.099 |
metaphor | -2.782 |
polarized | -2.746 |
Token | Plenty |
Token ID | 43257 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ibaba | +4.806 |
naires | +4.496 |
unin | +4.440 |
ivo | +4.412 |
naire | +4.333 |
Neg logit contributions | |
Line | -3.317 |
Tig | -3.139 |
Beet | -3.117 |
metaphor | -2.818 |
polarized | -2.773 |
Token | vs |
Token ID | 3691 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ibaba | +0.469 |
naires | +0.446 |
unin | +0.439 |
ivo | +0.433 |
naire | +0.431 |
Neg logit contributions | |
Line | -0.301 |
Tig | -0.284 |
Beet | -0.284 |
metaphor | -0.243 |
Vide | -0.239 |
Token | Lore |
Token ID | 15639 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Line | +0.335 |
Tig | +0.318 |
Beet | +0.316 |
metaphor | +0.273 |
Vide | +0.271 |
Neg logit contributions | |
ibaba | -0.454 |
naires | -0.429 |
unin | -0.424 |
ivo | -0.416 |
orsche | -0.413 |
Token | Se |
Token ID | 1001 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
ibaba | +2.703 |
naires | +2.570 |
unin | +2.529 |
ivo | +2.494 |
naire | +2.483 |
Neg logit contributions | |
Line | -2.151 |
Tig | -2.056 |
Beet | -2.050 |
metaphor | -1.814 |
polarized | -1.778 |
Token | eker |
Token ID | 28233 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ibaba | +0.507 |
naires | +0.467 |
unin | +0.460 |
ivo | +0.448 |
naire | +0.442 |
Neg logit contributions | |
Line | -0.757 |
Tig | -0.729 |
Beet | -0.728 |
metaphor | -0.661 |
Vide | -0.654 |
Token | wrote |
Token ID | 2630 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Line | +1.174 |
Tig | +1.113 |
Beet | +1.107 |
metaphor | +0.960 |
Vide | +0.946 |
Neg logit contributions | |
ibaba | -1.619 |
naires | -1.531 |
unin | -1.513 |
ivo | -1.486 |
naire | -1.474 |
Token | : |
Token ID | 25 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
ibaba | +0.459 |
naires | +0.426 |
unin | +0.423 |
ivo | +0.415 |
orsche | +0.414 |
Neg logit contributions | |
Line | -0.382 |
Tig | -0.362 |
Beet | -0.357 |
metaphor | -0.315 |
Vide | -0.313 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ibaba | +0.648 |
naires | +0.604 |
unin | +0.599 |
ivo | +0.587 |
orsche | +0.584 |
Neg logit contributions | |
Line | -0.578 |
Tig | -0.551 |
Beet | -0.544 |
metaphor | -0.482 |
Vide | -0.478 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ibaba | +0.018 |
naires | +0.017 |
unin | +0.017 |
ivo | +0.016 |
orsche | +0.016 |
Neg logit contributions | |
Line | -0.015 |
Tig | -0.015 |
Beet | -0.014 |
metaphor | -0.013 |
Vide | -0.013 |
Token | Show |
Token ID | 15307 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Line | +0.192 |
Tig | +0.179 |
Beet | +0.177 |
metaphor | +0.148 |
Vide | +0.145 |
Neg logit contributions | |
ibaba | -0.381 |
naires | -0.362 |
unin | -0.357 |
ivo | -0.352 |
naire | -0.350 |
Token | nested |
Token ID | 28376 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ibaba | +1.872 |
naires | +1.737 |
unin | +1.736 |
ivo | +1.676 |
humane | +1.659 |
Neg logit contributions | |
Line | -2.517 |
Beet | -2.460 |
Tig | -2.418 |
metaphor | -2.181 |
polarized | -2.159 |
Token | quote |
Token ID | 9577 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ibaba | +3.530 |
naires | +3.257 |
unin | +3.254 |
humane | +3.064 |
ivo | +3.045 |
Neg logit contributions | |
Beet | -4.591 |
Line | -4.493 |
Tig | -4.374 |
wart | -4.056 |
Vide | -3.980 |
Token | + |
Token ID | 1343 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ibaba | +1.464 |
naires | +1.444 |
ivo | +1.396 |
naire | +1.383 |
unin | +1.379 |
Neg logit contributions | |
Line | -0.891 |
Beet | -0.864 |
Tig | -0.847 |
Vide | -0.756 |
metaphor | -0.724 |
Token |
|
Token ID | 198 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
ibaba | +0.363 |
naires | +0.339 |
unin | +0.335 |
ivo | +0.329 |
orsche | +0.326 |
Neg logit contributions | |
Line | -0.332 |
Tig | -0.316 |
Beet | -0.314 |
metaphor | -0.278 |
Vide | -0.275 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ibaba | +0.394 |
naires | +0.365 |
unin | +0.363 |
ivo | +0.356 |
orsche | +0.355 |
Neg logit contributions | |
Line | -0.343 |
Tig | -0.327 |
Beet | -0.322 |
metaphor | -0.284 |
Vide | -0.282 |
Token | On |
Token ID | 2202 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ibaba | +0.091 |
naires | +0.085 |
unin | +0.084 |
ivo | +0.082 |
naire | +0.082 |
Neg logit contributions | |
Line | -0.090 |
Tig | -0.086 |
Beet | -0.086 |
metaphor | -0.076 |
Vide | -0.075 |
Token | Charm |
Token ID | 30225 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ibaba | +0.190 |
naires | +0.180 |
unin | +0.178 |
ivo | +0.175 |
naire | +0.173 |
Neg logit contributions | |
Line | -0.134 |
Tig | -0.126 |
Beet | -0.126 |
metaphor | -0.109 |
Vide | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ibaba | +0.121 |
naires | +0.114 |
unin | +0.113 |
ivo | +0.111 |
naire | +0.110 |
Neg logit contributions | |
Line | -0.112 |
Tig | -0.107 |
Beet | -0.106 |
metaphor | -0.094 |
Vide | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ibaba | +0.424 |
naires | +0.393 |
unin | +0.390 |
ivo | +0.383 |
orsche | +0.382 |
Neg logit contributions | |
Line | -0.371 |
Tig | -0.353 |
Beet | -0.348 |
metaphor | -0.307 |
Vide | -0.305 |
Token | Sc |
Token ID | 3351 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ibaba | +0.204 |
naires | +0.192 |
unin | +0.189 |
ivo | +0.185 |
naire | +0.184 |
Neg logit contributions | |
Line | -0.189 |
Tig | -0.181 |
Beet | -0.180 |
metaphor | -0.159 |
Vide | -0.157 |
Token | ourge |
Token ID | 14501 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
ibaba | +1.665 |
naires | +1.551 |
unin | +1.540 |
ivo | +1.516 |
orsche | +1.494 |
Neg logit contributions | |
Line | -1.563 |
Tig | -1.502 |
Beet | -1.498 |
metaphor | -1.328 |
Vide | -1.311 |
Token | of |
Token ID | 286 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
ibaba | +1.589 |
naires | +1.511 |
unin | +1.476 |
ivo | +1.463 |
naire | +1.461 |
Neg logit contributions | |
Line | -1.302 |
Tig | -1.242 |
Beet | -1.241 |
metaphor | -1.097 |
Vide | -1.076 |
Token | Fle |
Token ID | 12005 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ibaba | +4.569 |
naires | +4.314 |
unin | +4.249 |
ivo | +4.171 |
naire | +4.141 |
Neg logit contributions | |
Line | -3.408 |
Tig | -3.228 |
Beet | -3.222 |
metaphor | -2.937 |
polarized | -2.866 |
Token | ets |
Token ID | 1039 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ibaba | +0.325 |
naires | +0.301 |
unin | +0.295 |
ivo | +0.288 |
naire | +0.285 |
Neg logit contributions | |
Line | -0.443 |
Tig | -0.426 |
Beet | -0.424 |
metaphor | -0.383 |
Vide | -0.380 |
Token | vs |
Token ID | 3691 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ibaba | +1.791 |
naires | +1.711 |
unin | +1.676 |
ivo | +1.664 |
naire | +1.663 |
Neg logit contributions | |
Line | -1.193 |
Beet | -1.134 |
Tig | -1.131 |
metaphor | -0.978 |
Vide | -0.956 |
Token | Crypt |
Token ID | 15126 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Line | +0.233 |
Tig | +0.221 |
Beet | +0.220 |
metaphor | +0.190 |
Vide | +0.188 |
Neg logit contributions | |
ibaba | -0.318 |
naires | -0.301 |
unin | -0.297 |
ivo | -0.292 |
orsche | -0.290 |
Token | Gh |
Token ID | 11972 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ibaba | +2.366 |
naires | +2.238 |
unin | +2.210 |
ivo | +2.180 |
naire | +2.151 |
Neg logit contributions | |
Line | -1.921 |
Tig | -1.828 |
Beet | -1.827 |
metaphor | -1.627 |
polarized | -1.586 |
Token | Passage |
Token ID | 46169 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ibaba | +1.648 |
naires | +1.555 |
unin | +1.535 |
ivo | +1.515 |
naire | +1.499 |
Neg logit contributions | |
Line | -1.276 |
Tig | -1.219 |
Beet | -1.211 |
metaphor | -1.068 |
polarized | -1.050 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ibaba | +1.913 |
naires | +1.822 |
unin | +1.786 |
naire | +1.764 |
ivo | +1.761 |
Neg logit contributions | |
Line | -1.524 |
Tig | -1.458 |
Beet | -1.455 |
metaphor | -1.287 |
polarized | -1.259 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ibaba | +1.150 |
naires | +1.076 |
unin | +1.063 |
ivo | +1.043 |
orsche | +1.034 |
Neg logit contributions | |
Line | -1.058 |
Tig | -1.009 |
Beet | -1.001 |
metaphor | -0.887 |
Vide | -0.877 |
Token | M |
Token ID | 44 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ibaba | +1.040 |
naires | +0.978 |
unin | +0.965 |
ivo | +0.946 |
naire | +0.938 |
Neg logit contributions | |
Line | -0.967 |
Tig | -0.923 |
Beet | -0.920 |
metaphor | -0.814 |
Vide | -0.804 |
Token | ael |
Token ID | 3010 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ibaba | +2.535 |
naires | +2.380 |
unin | +2.372 |
ivo | +2.304 |
naire | +2.287 |
Neg logit contributions | |
Line | -2.507 |
Beet | -2.409 |
Tig | -2.399 |
metaphor | -2.145 |
Vide | -2.133 |
Token | strom |
Token ID | 20282 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
ibaba | +1.893 |
naires | +1.789 |
unin | +1.775 |
ivo | +1.752 |
naire | +1.724 |
Neg logit contributions | |
Line | -1.396 |
Tig | -1.325 |
Beet | -1.324 |
metaphor | -1.171 |
Vide | -1.145 |
Token | Pulse |
Token ID | 25062 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
ibaba | +4.699 |
naires | +4.454 |
unin | +4.423 |
naire | +4.396 |
ivo | +4.390 |
Neg logit contributions | |
Line | -3.162 |
Beet | -3.053 |
Tig | -3.009 |
metaphor | -2.641 |
Passive | -2.593 |
Token | vs |
Token ID | 3691 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ibaba | +4.279 |
naires | +4.085 |
naire | +3.996 |
ivo | +3.977 |
unin | +3.974 |
Neg logit contributions | |
Line | -3.100 |
Beet | -2.972 |
Tig | -2.972 |
metaphor | -2.616 |
Vide | -2.538 |
Token | Paradise |
Token ID | 20494 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ibaba | +1.473 |
naires | +1.400 |
unin | +1.383 |
ivo | +1.359 |
naire | +1.354 |
Neg logit contributions | |
Line | -1.026 |
Tig | -0.971 |
Beet | -0.971 |
metaphor | -0.852 |
polarized | -0.828 |
Token | M |
Token ID | 337 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ibaba | +1.834 |
naires | +1.737 |
unin | +1.714 |
ivo | +1.689 |
naire | +1.683 |
Neg logit contributions | |
Line | -1.282 |
Tig | -1.215 |
Beet | -1.212 |
metaphor | -1.056 |
Vide | -1.032 |
Token | antle |
Token ID | 16941 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ibaba | +1.274 |
naires | +1.189 |
unin | +1.169 |
ivo | +1.144 |
naire | +1.132 |
Neg logit contributions | |
Line | -1.477 |
Tig | -1.416 |
Beet | -1.409 |
metaphor | -1.264 |
Vide | -1.250 |
Token |
|
Token ID | 198 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
ibaba | +0.841 |
naires | +0.783 |
unin | +0.776 |
ivo | +0.761 |
orsche | +0.757 |
Neg logit contributions | |
Line | -0.756 |
Tig | -0.720 |
Beet | -0.713 |
metaphor | -0.631 |
Vide | -0.625 |
Token | Joe |
Token ID | 19585 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ibaba | +0.687 |
naires | +0.649 |
unin | +0.640 |
ivo | +0.629 |
naire | +0.623 |
Neg logit contributions | |
Line | -0.560 |
Tig | -0.533 |
Beet | -0.531 |
metaphor | -0.465 |
Vide | -0.459 |
Token | V |
Token ID | 569 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ibaba | +0.128 |
naires | +0.121 |
unin | +0.120 |
ivo | +0.117 |
naire | +0.117 |
Neg logit contributions | |
Line | -0.101 |
Tig | -0.096 |
Beet | -0.096 |
metaphor | -0.084 |
Vide | -0.083 |
Token | itt |
Token ID | 715 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ibaba | +1.023 |
naires | +0.962 |
unin | +0.952 |
ivo | +0.937 |
naire | +0.923 |
Neg logit contributions | |
Line | -0.936 |
Tig | -0.898 |
Beet | -0.893 |
metaphor | -0.791 |
Vide | -0.781 |
Token | Aff |
Token ID | 6708 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
ibaba | +1.828 |
naires | +1.731 |
unin | +1.698 |
ivo | +1.685 |
naire | +1.663 |
Neg logit contributions | |
Line | -1.610 |
Tig | -1.546 |
Beet | -1.544 |
metaphor | -1.362 |
Vide | -1.338 |
Token | idav |
Token ID | 20331 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ibaba | +2.120 |
naires | +1.985 |
unin | +1.962 |
ivo | +1.909 |
naire | +1.897 |
Neg logit contributions | |
Line | -2.587 |
Beet | -2.500 |
Tig | -2.498 |
metaphor | -2.293 |
polarized | -2.252 |
Token | it |
Token ID | 270 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
ibaba | +3.534 |
naires | +3.364 |
naire | +3.293 |
unin | +3.276 |
ivo | +3.261 |
Neg logit contributions | |
Line | -4.400 |
Beet | -4.321 |
Tig | -4.300 |
metaphor | -3.887 |
polarized | -3.865 |
Token |
|
Token ID | 198 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
ibaba | +2.222 |
naires | +2.125 |
unin | +2.066 |
ivo | +2.051 |
naire | +2.050 |
Neg logit contributions | |
Line | -1.887 |
Beet | -1.811 |
Tig | -1.806 |
metaphor | -1.603 |
polarized | -1.571 |
Token |
|
Token ID | 198 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ibaba | +0.400 |
naires | +0.371 |
unin | +0.368 |
ivo | +0.361 |
orsche | +0.361 |
Neg logit contributions | |
Line | -0.351 |
Tig | -0.334 |
Beet | -0.329 |
metaphor | -0.291 |
Vide | -0.289 |
Token | Scott |
Token ID | 19040 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ibaba | +0.504 |
naires | +0.474 |
unin | +0.468 |
ivo | +0.459 |
naire | +0.455 |
Neg logit contributions | |
Line | -0.430 |
Tig | -0.409 |
Beet | -0.407 |
metaphor | -0.358 |
Vide | -0.354 |
Token | ie |
Token ID | 494 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ibaba | +0.499 |
naires | +0.471 |
unin | +0.465 |
ivo | +0.456 |
naire | +0.452 |
Neg logit contributions | |
Line | -0.399 |
Tig | -0.380 |
Beet | -0.378 |
metaphor | -0.331 |
Vide | -0.326 |
Token | Why |
Token ID | 5195 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ibaba | +1.099 |
naires | +1.039 |
unin | +1.025 |
ivo | +1.008 |
naire | +0.998 |
Neg logit contributions | |
Line | -0.924 |
Tig | -0.881 |
Beet | -0.880 |
metaphor | -0.770 |
Vide | -0.759 |
Token | it |
Token ID | 340 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ibaba | +1.055 |
naires | +0.996 |
unin | +0.980 |
ivo | +0.966 |
naire | +0.957 |
Neg logit contributions | |
Line | -0.865 |
Tig | -0.825 |
Beet | -0.823 |
metaphor | -0.719 |
Vide | -0.709 |
Token | � |
Token ID | 447 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ibaba | +2.161 |
naires | +2.046 |
unin | +2.027 |
ivo | +1.982 |
naire | +1.969 |
Neg logit contributions | |
Line | -1.638 |
Beet | -1.564 |
Tig | -1.548 |
metaphor | -1.339 |
Passive | -1.332 |
Token | � |
Token ID | 247 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ibaba | +0.940 |
naires | +0.872 |
unin | +0.855 |
ivo | +0.832 |
naire | +0.826 |
Neg logit contributions | |
Line | -1.304 |
Tig | -1.258 |
Beet | -1.255 |
metaphor | -1.134 |
Vide | -1.124 |
Token | s |
Token ID | 82 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ibaba | +0.936 |
naires | +0.884 |
unin | +0.873 |
ivo | +0.858 |
naire | +0.851 |
Neg logit contributions | |
Line | -0.729 |
Tig | -0.692 |
Beet | -0.689 |
metaphor | -0.601 |
Vide | -0.593 |
Token | important |
Token ID | 1593 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
Line | +0.128 |
Tig | +0.122 |
Beet | +0.121 |
metaphor | +0.108 |
Vide | +0.106 |
Neg logit contributions | |
ibaba | -0.134 |
naires | -0.126 |
unin | -0.124 |
ivo | -0.122 |
naire | -0.121 |
Token | to |
Token ID | 284 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ibaba | +4.002 |
naires | +3.731 |
unin | +3.647 |
ivo | +3.640 |
naire | +3.583 |
Neg logit contributions | |
Line | -3.855 |
Beet | -3.765 |
Tig | -3.738 |
wart | -3.254 |
polarized | -3.218 |
Token | get |
Token ID | 651 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ibaba | +2.648 |
naires | +2.515 |
unin | +2.478 |
ivo | +2.453 |
naire | +2.428 |
Neg logit contributions | |
Line | -2.038 |
Beet | -1.957 |
Tig | -1.942 |
metaphor | -1.671 |
wart | -1.669 |
Token | customers |
Token ID | 4297 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ibaba | +1.556 |
naires | +1.466 |
unin | +1.442 |
ivo | +1.421 |
naire | +1.404 |
Neg logit contributions | |
Line | -1.367 |
Tig | -1.304 |
Beet | -1.301 |
metaphor | -1.143 |
Vide | -1.130 |
Token | before |
Token ID | 878 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ibaba | +0.470 |
naires | +0.442 |
unin | +0.437 |
ivo | +0.428 |
naire | +0.425 |
Neg logit contributions | |
Line | -0.402 |
Tig | -0.383 |
Beet | -0.381 |
metaphor | -0.336 |
Vide | -0.331 |
Token | building |
Token ID | 2615 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ibaba | +0.334 |
naires | +0.312 |
unin | +0.309 |
ivo | +0.300 |
naire | +0.299 |
Neg logit contributions | |
Line | -0.341 |
Tig | -0.325 |
Beet | -0.322 |
metaphor | -0.289 |
Vide | -0.286 |
Token | is |
Token ID | 318 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ibaba | +0.062 |
naires | +0.059 |
unin | +0.058 |
ivo | +0.057 |
naire | +0.057 |
Neg logit contributions | |
Line | -0.042 |
Tig | -0.040 |
Beet | -0.039 |
metaphor | -0.034 |
Vide | -0.033 |
Token | therefore |
Token ID | 4361 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
Line | +0.246 |
Tig | +0.234 |
Beet | +0.232 |
metaphor | +0.204 |
Vide | +0.201 |
Neg logit contributions | |
ibaba | -0.298 |
naires | -0.281 |
unin | -0.278 |
ivo | -0.273 |
naire | -0.271 |
Token | in |
Token ID | 287 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ibaba | +0.050 |
naires | +0.047 |
unin | +0.046 |
ivo | +0.045 |
naire | +0.045 |
Neg logit contributions | |
Line | -0.044 |
Tig | -0.042 |
Beet | -0.042 |
metaphor | -0.037 |
Vide | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ibaba | +0.385 |
naires | +0.362 |
unin | +0.357 |
ivo | +0.350 |
naire | +0.347 |
Neg logit contributions | |
Line | -0.341 |
Tig | -0.324 |
Beet | -0.323 |
metaphor | -0.285 |
Vide | -0.281 |
Token | best |
Token ID | 1266 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
ibaba | +0.888 |
naires | +0.837 |
unin | +0.826 |
ivo | +0.811 |
naire | +0.804 |
Neg logit contributions | |
Line | -0.759 |
Tig | -0.723 |
Beet | -0.720 |
metaphor | -0.633 |
Vide | -0.625 |
Token | interests |
Token ID | 5353 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
Line | +0.770 |
Tig | +0.739 |
Beet | +0.736 |
metaphor | +0.667 |
Vide | +0.658 |
Neg logit contributions | |
ibaba | -0.592 |
naires | -0.547 |
unin | -0.540 |
ivo | -0.525 |
naire | -0.520 |
Token | of |
Token ID | 286 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ibaba | +3.812 |
naires | +3.604 |
ivo | +3.525 |
unin | +3.523 |
orsche | +3.418 |
Neg logit contributions | |
Line | -3.939 |
Beet | -3.838 |
Tig | -3.775 |
Vide | -3.332 |
Passive | -3.302 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ibaba | +0.149 |
naires | +0.141 |
unin | +0.138 |
ivo | +0.136 |
naire | +0.135 |
Neg logit contributions | |
Line | -0.131 |
Tig | -0.125 |
Beet | -0.124 |
metaphor | -0.109 |
Vide | -0.108 |
Token | ruling |
Token ID | 6922 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Line | +0.821 |
Tig | +0.779 |
Beet | +0.772 |
metaphor | +0.677 |
Vide | +0.666 |
Neg logit contributions | |
ibaba | -1.068 |
naires | -1.007 |
unin | -0.991 |
ivo | -0.977 |
naire | -0.968 |
Token | class |
Token ID | 1398 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Line | +1.411 |
Tig | +1.346 |
Beet | +1.328 |
metaphor | +1.191 |
Vide | +1.172 |
Neg logit contributions | |
ibaba | -1.457 |
naires | -1.355 |
unin | -1.341 |
ivo | -1.320 |
orsche | -1.308 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Line | +0.531 |
Tig | +0.505 |
Beet | +0.500 |
metaphor | +0.442 |
Vide | +0.433 |
Neg logit contributions | |
ibaba | -0.653 |
naires | -0.613 |
unin | -0.608 |
ivo | -0.596 |
naire | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Line | +0.725 |
Tig | +0.690 |
Beet | +0.686 |
metaphor | +0.594 |
Vide | +0.590 |
Neg logit contributions | |
ibaba | -0.888 |
naires | -0.838 |
unin | -0.827 |
ivo | -0.811 |
orsche | -0.806 |
Token |
|
Token ID | 198 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ibaba | +0.649 |
naires | +0.603 |
unin | +0.598 |
ivo | +0.587 |
orsche | +0.585 |
Neg logit contributions | |
Line | -0.577 |
Tig | -0.549 |
Beet | -0.542 |
metaphor | -0.479 |
Vide | -0.475 |
Token | Ph |
Token ID | 2725 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ibaba | +0.595 |
naires | +0.559 |
unin | +0.552 |
ivo | +0.541 |
naire | +0.536 |
Neg logit contributions | |
Line | -0.559 |
Tig | -0.533 |
Beet | -0.531 |
metaphor | -0.471 |
Vide | -0.465 |
Token | y |
Token ID | 88 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ibaba | +2.224 |
naires | +2.093 |
unin | +2.088 |
ivo | +2.047 |
naire | +2.016 |
Neg logit contributions | |
Line | -1.759 |
Beet | -1.676 |
Tig | -1.670 |
metaphor | -1.464 |
Vide | -1.447 |
Token | rex |
Token ID | 21510 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ibaba | +1.244 |
naires | +1.150 |
unin | +1.134 |
ivo | +1.105 |
naire | +1.091 |
Neg logit contributions | |
Line | -1.763 |
Tig | -1.695 |
Beet | -1.690 |
metaphor | -1.536 |
Vide | -1.520 |
Token | ian |
Token ID | 666 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
ibaba | +2.685 |
naires | +2.538 |
unin | +2.502 |
ivo | +2.464 |
naire | +2.430 |
Neg logit contributions | |
Line | -2.637 |
Tig | -2.523 |
Beet | -2.519 |
metaphor | -2.275 |
polarized | -2.224 |
Token | Ob |
Token ID | 1835 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ibaba | +4.622 |
naires | +4.457 |
naire | +4.361 |
ivo | +4.332 |
unin | +4.329 |
Neg logit contributions | |
Line | -2.962 |
Beet | -2.812 |
Tig | -2.809 |
metaphor | -2.514 |
polarized | -2.467 |
Token | liter |
Token ID | 17201 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ibaba | +1.818 |
naires | +1.717 |
unin | +1.692 |
naire | +1.655 |
ivo | +1.652 |
Neg logit contributions | |
Line | -1.815 |
Beet | -1.743 |
Tig | -1.742 |
metaphor | -1.562 |
polarized | -1.530 |
Token | ator |
Token ID | 1352 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Line | +0.693 |
Tig | +0.647 |
Beet | +0.640 |
Vide | +0.539 |
metaphor | +0.538 |
Neg logit contributions | |
ibaba | -1.130 |
naires | -1.064 |
unin | -1.061 |
ivo | -1.031 |
orsche | -1.028 |
Token | vs |
Token ID | 3691 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
ibaba | +1.964 |
naires | +1.870 |
unin | +1.828 |
ivo | +1.819 |
naire | +1.818 |
Neg logit contributions | |
Line | -1.320 |
Tig | -1.258 |
Beet | -1.257 |
metaphor | -1.091 |
Vide | -1.067 |
Token | Brig |
Token ID | 16917 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Line | +0.034 |
Tig | +0.033 |
Beet | +0.032 |
metaphor | +0.028 |
Vide | +0.028 |
Neg logit contributions | |
ibaba | -0.046 |
naires | -0.044 |
unin | -0.043 |
ivo | -0.043 |
naire | -0.042 |
Token | ept |
Token ID | 19598 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ibaba | +1.681 |
naires | +1.574 |
unin | +1.564 |
ivo | +1.531 |
naire | +1.518 |
Neg logit contributions | |
Line | -1.500 |
Tig | -1.435 |
Beet | -1.428 |
metaphor | -1.269 |
polarized | -1.241 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ibaba | +0.781 |
naires | +0.737 |
unin | +0.722 |
ivo | +0.711 |
naire | +0.711 |
Neg logit contributions | |
Line | -0.746 |
Beet | -0.716 |
Tig | -0.715 |
metaphor | -0.636 |
Vide | -0.625 |
Token |
|
Token ID | 198 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ibaba | +0.944 |
naires | +0.881 |
unin | +0.872 |
ivo | +0.855 |
orsche | +0.849 |
Neg logit contributions | |
Line | -0.858 |
Tig | -0.817 |
Beet | -0.810 |
metaphor | -0.718 |
Vide | -0.710 |
Token | Eye |
Token ID | 24876 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ibaba | +0.499 |
naires | +0.469 |
unin | +0.462 |
ivo | +0.453 |
naire | +0.449 |
Neg logit contributions | |
Line | -0.463 |
Tig | -0.442 |
Beet | -0.440 |
metaphor | -0.390 |
Vide | -0.385 |
Token | of |
Token ID | 286 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
ibaba | +2.850 |
naires | +2.683 |
unin | +2.645 |
ivo | +2.611 |
naire | +2.605 |
Neg logit contributions | |
Line | -2.533 |
Tig | -2.450 |
Beet | -2.437 |
metaphor | -2.164 |
Vide | -2.149 |
Token | Doom |
Token ID | 18688 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
ibaba | +3.408 |
naires | +3.192 |
unin | +3.135 |
ivo | +3.120 |
naire | +3.091 |
Neg logit contributions | |
Line | -2.550 |
Tig | -2.414 |
Beet | -2.406 |
metaphor | -2.163 |
polarized | -2.121 |
Token | vs |
Token ID | 3691 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ibaba | +4.416 |
naires | +4.244 |
naire | +4.190 |
unin | +4.118 |
ivo | +4.118 |
Neg logit contributions | |
Line | -3.158 |
Beet | -3.048 |
Tig | -3.026 |
metaphor | -2.686 |
Vide | -2.613 |
Token | Moment |
Token ID | 29278 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ibaba | +0.467 |
naires | +0.442 |
unin | +0.437 |
ivo | +0.429 |
naire | +0.427 |
Neg logit contributions | |
Line | -0.338 |
Tig | -0.320 |
Beet | -0.319 |
metaphor | -0.278 |
Vide | -0.272 |
Token | ous |
Token ID | 516 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ibaba | +1.311 |
naires | +1.236 |
unin | +1.215 |
ivo | +1.196 |
naire | +1.189 |
Neg logit contributions | |
Line | -1.196 |
Tig | -1.142 |
Beet | -1.140 |
metaphor | -1.013 |
Vide | -0.995 |
Token | Fall |
Token ID | 7218 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ibaba | +2.547 |
naires | +2.409 |
unin | +2.372 |
ivo | +2.353 |
naire | +2.334 |
Neg logit contributions | |
Line | -1.692 |
Tig | -1.599 |
Beet | -1.596 |
metaphor | -1.405 |
polarized | -1.381 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ibaba | +1.280 |
naires | +1.208 |
unin | +1.187 |
ivo | +1.169 |
naire | +1.169 |
Neg logit contributions | |
Line | -1.219 |
Beet | -1.170 |
Tig | -1.169 |
metaphor | -1.046 |
polarized | -1.025 |
Token | Gerr |
Token ID | 45140 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ibaba | +1.981 |
naires | +1.846 |
unin | +1.816 |
ivo | +1.775 |
naire | +1.759 |
Neg logit contributions | |
Line | -2.375 |
Tig | -2.279 |
Beet | -2.270 |
metaphor | -2.041 |
Vide | -2.020 |
Token | ans |
Token ID | 504 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ibaba | +2.523 |
naires | +2.332 |
unin | +2.272 |
ivo | +2.243 |
naire | +2.232 |
Neg logit contributions | |
Line | -3.725 |
Beet | -3.677 |
Tig | -3.647 |
metaphor | -3.315 |
polarized | -3.296 |
Token | ( |
Token ID | 357 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
ibaba | +1.302 |
naires | +1.225 |
unin | +1.216 |
ivo | +1.187 |
orsche | +1.178 |
Neg logit contributions | |
Line | -1.059 |
Tig | -1.006 |
Beet | -0.993 |
metaphor | -0.868 |
Vide | -0.864 |
Token | Green |
Token ID | 13719 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ibaba | +0.731 |
naires | +0.689 |
unin | +0.679 |
ivo | +0.666 |
orsche | +0.665 |
Neg logit contributions | |
Line | -0.448 |
Tig | -0.421 |
Beet | -0.416 |
metaphor | -0.356 |
Vide | -0.352 |
Token | Edge |
Token ID | 37021 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ibaba | +2.281 |
naires | +2.173 |
unin | +2.131 |
ivo | +2.120 |
naire | +2.094 |
Neg logit contributions | |
Line | -1.633 |
Beet | -1.573 |
Tig | -1.568 |
metaphor | -1.361 |
Vide | -1.335 |
Token | Cycling |
Token ID | 25550 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
ibaba | +2.378 |
naires | +2.289 |
unin | +2.238 |
ivo | +2.220 |
naire | +2.214 |
Neg logit contributions | |
Line | -1.427 |
Beet | -1.355 |
Tig | -1.349 |
metaphor | -1.168 |
polarized | -1.141 |
Token | Team |
Token ID | 4816 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ibaba | +3.946 |
naires | +3.879 |
naire | +3.736 |
ivo | +3.731 |
unin | +3.727 |
Neg logit contributions | |
Beet | -3.365 |
Line | -3.361 |
Tig | -3.287 |
polarized | -2.990 |
metaphor | -2.949 |
Token | ) |
Token ID | 8 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ibaba | +1.792 |
naires | +1.715 |
unin | +1.690 |
ivo | +1.664 |
naire | +1.655 |
Neg logit contributions | |
Line | -1.064 |
Beet | -1.007 |
Tig | -1.003 |
metaphor | -0.853 |
Vide | -0.835 |
Token | s |
Token ID | 264 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
ibaba | +1.752 |
naires | +1.612 |
unin | +1.583 |
ivo | +1.549 |
orsche | +1.536 |
Neg logit contributions | |
Line | -2.301 |
Tig | -2.213 |
Beet | -2.211 |
metaphor | -2.004 |
Vide | -1.983 |
Token | . |
Token ID | 13 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Line | +0.444 |
Tig | +0.416 |
Beet | +0.407 |
metaphor | +0.350 |
Vide | +0.347 |
Neg logit contributions | |
ibaba | -0.707 |
naires | -0.662 |
unin | -0.660 |
ivo | -0.648 |
orsche | -0.648 |
Token | t |
Token ID | 83 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Line | +0.229 |
Tig | +0.217 |
Beet | +0.212 |
metaphor | +0.186 |
Vide | +0.185 |
Neg logit contributions | |
ibaba | -0.307 |
naires | -0.287 |
unin | -0.282 |
orsche | -0.279 |
ivo | -0.279 |
Token | A |
Token ID | 317 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Line | +0.123 |
Tig | +0.117 |
Beet | +0.116 |
metaphor | +0.103 |
Vide | +0.102 |
Neg logit contributions | |
ibaba | -0.131 |
naires | -0.123 |
unin | -0.122 |
ivo | -0.119 |
naire | -0.118 |
Token | US |
Token ID | 2937 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ibaba | +0.875 |
naires | +0.822 |
unin | +0.805 |
naire | +0.786 |
ivo | +0.785 |
Neg logit contributions | |
Line | -0.963 |
Tig | -0.923 |
Beet | -0.916 |
metaphor | -0.819 |
Vide | -0.813 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ibaba | +2.019 |
naires | +1.890 |
unin | +1.859 |
ivo | +1.832 |
naire | +1.808 |
Neg logit contributions | |
Line | -2.074 |
Tig | -1.990 |
Beet | -1.981 |
metaphor | -1.778 |
Vide | -1.747 |
Token | Mark |
Token ID | 2940 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ibaba | +1.079 |
naires | +1.021 |
unin | +1.006 |
ivo | +0.991 |
naire | +0.982 |
Neg logit contributions | |
Line | -0.855 |
Beet | -0.811 |
Tig | -0.811 |
metaphor | -0.712 |
polarized | -0.699 |
Token | R |
Token ID | 371 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ibaba | +1.746 |
naires | +1.631 |
unin | +1.618 |
ivo | +1.591 |
orsche | +1.573 |
Neg logit contributions | |
Line | -1.525 |
Beet | -1.456 |
Tig | -1.452 |
metaphor | -1.297 |
polarized | -1.275 |
Token | ens |
Token ID | 641 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
ibaba | +1.506 |
naires | +1.406 |
unin | +1.387 |
ivo | +1.360 |
orsche | +1.338 |
Neg logit contributions | |
Line | -1.802 |
Tig | -1.728 |
Beet | -1.727 |
metaphor | -1.554 |
Vide | -1.536 |
Token | haw |
Token ID | 26615 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ibaba | +3.837 |
naires | +3.585 |
unin | +3.539 |
ivo | +3.465 |
humane | +3.443 |
Neg logit contributions | |
Line | -3.899 |
Tig | -3.747 |
Beet | -3.740 |
Vide | -3.285 |
Passive | -3.284 |
Token | ( |
Token ID | 357 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ibaba | +0.104 |
naires | +0.098 |
unin | +0.097 |
ivo | +0.095 |
naire | +0.094 |
Neg logit contributions | |
Line | -0.087 |
Tig | -0.082 |
Beet | -0.082 |
metaphor | -0.072 |
Vide | -0.071 |
Token | R |
Token ID | 49 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ibaba | +1.214 |
naires | +1.135 |
unin | +1.118 |
ivo | +1.094 |
naire | +1.085 |
Neg logit contributions | |
Line | -1.303 |
Tig | -1.248 |
Beet | -1.243 |
metaphor | -1.111 |
Vide | -1.098 |
Token | ab |
Token ID | 397 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ibaba | +1.385 |
naires | +1.302 |
unin | +1.285 |
ivo | +1.260 |
naire | +1.249 |
Neg logit contributions | |
Line | -1.250 |
Tig | -1.192 |
Beet | -1.187 |
metaphor | -1.048 |
Vide | -1.035 |
Token | ob |
Token ID | 672 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ibaba | +0.552 |
naires | +0.472 |
unin | +0.440 |
naire | +0.420 |
ivo | +0.416 |
Neg logit contributions | |
Line | -2.307 |
Tig | -2.256 |
Beet | -2.241 |
metaphor | -2.092 |
wart | -2.079 |
Token | Ed |
Token ID | 1717 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ibaba | +0.826 |
naires | +0.781 |
unin | +0.770 |
ivo | +0.758 |
naire | +0.751 |
Neg logit contributions | |
Line | -0.653 |
Tig | -0.620 |
Beet | -0.619 |
metaphor | -0.543 |
Vide | -0.533 |
Token | v |
Token ID | 85 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ibaba | +2.082 |
naires | +1.966 |
unin | +1.938 |
ivo | +1.902 |
naire | +1.889 |
Neg logit contributions | |
Line | -1.777 |
Tig | -1.692 |
Beet | -1.683 |
metaphor | -1.477 |
Vide | -1.463 |
Token | ald |
Token ID | 1940 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ibaba | +0.519 |
naires | +0.490 |
unin | +0.484 |
ivo | +0.473 |
naire | +0.471 |
Neg logit contributions | |
Line | -0.431 |
Tig | -0.409 |
Beet | -0.406 |
metaphor | -0.356 |
Vide | -0.351 |
Token | Bo |
Token ID | 3248 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ibaba | +2.010 |
naires | +1.903 |
unin | +1.876 |
ivo | +1.841 |
naire | +1.831 |
Neg logit contributions | |
Line | -1.538 |
Tig | -1.459 |
Beet | -1.450 |
metaphor | -1.261 |
Vide | -1.245 |
Token | ass |
Token ID | 562 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ibaba | +1.854 |
naires | +1.711 |
unin | +1.694 |
ivo | +1.667 |
orsche | +1.640 |
Neg logit contributions | |
Line | -2.131 |
Tig | -2.057 |
Beet | -2.048 |
metaphor | -1.851 |
polarized | -1.839 |
Token | on |
Token ID | 261 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
ibaba | +2.373 |
naires | +2.246 |
unin | +2.238 |
ivo | +2.200 |
naire | +2.168 |
Neg logit contributions | |
Line | -1.905 |
Tig | -1.826 |
Beet | -1.824 |
metaphor | -1.597 |
Vide | -1.572 |
Token | H |
Token ID | 367 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ibaba | +3.417 |
naires | +3.201 |
unin | +3.122 |
naire | +3.081 |
ivo | +3.043 |
Neg logit contributions | |
Line | -4.163 |
Beet | -4.061 |
Tig | -4.021 |
metaphor | -3.705 |
polarized | -3.651 |
Token | agen |
Token ID | 11286 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
ibaba | +1.952 |
naires | +1.835 |
unin | +1.812 |
ivo | +1.795 |
orsche | +1.767 |
Neg logit contributions | |
Line | -1.689 |
Beet | -1.621 |
Tig | -1.618 |
metaphor | -1.420 |
Vide | -1.409 |
Token | ( |
Token ID | 357 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
ibaba | +2.522 |
naires | +2.365 |
unin | +2.337 |
ivo | +2.294 |
naire | +2.280 |
Neg logit contributions | |
Line | -2.220 |
Beet | -2.126 |
Tig | -2.117 |
metaphor | -1.877 |
Vide | -1.841 |
Token | Sky |
Token ID | 22308 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ibaba | +1.658 |
naires | +1.546 |
unin | +1.523 |
ivo | +1.489 |
naire | +1.476 |
Neg logit contributions | |
Line | -1.784 |
Tig | -1.707 |
Beet | -1.699 |
metaphor | -1.520 |
Vide | -1.504 |
Token | Pro |
Token ID | 1041 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ibaba | +1.598 |
naires | +1.517 |
unin | +1.507 |
ivo | +1.492 |
naire | +1.466 |
Neg logit contributions | |
Line | -1.214 |
Beet | -1.169 |
Tig | -1.164 |
metaphor | -1.021 |
polarized | -1.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ibaba | +1.913 |
naires | +1.822 |
unin | +1.786 |
naire | +1.764 |
ivo | +1.761 |
Neg logit contributions | |
Line | -1.524 |
Tig | -1.458 |
Beet | -1.455 |
metaphor | -1.287 |
polarized | -1.259 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ibaba | +1.150 |
naires | +1.076 |
unin | +1.063 |
ivo | +1.043 |
orsche | +1.034 |
Neg logit contributions | |
Line | -1.058 |
Tig | -1.009 |
Beet | -1.001 |
metaphor | -0.887 |
Vide | -0.877 |
Token | M |
Token ID | 44 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ibaba | +1.040 |
naires | +0.978 |
unin | +0.965 |
ivo | +0.946 |
naire | +0.938 |
Neg logit contributions | |
Line | -0.967 |
Tig | -0.923 |
Beet | -0.920 |
metaphor | -0.814 |
Vide | -0.804 |
Token | ael |
Token ID | 3010 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ibaba | +2.535 |
naires | +2.380 |
unin | +2.372 |
ivo | +2.304 |
naire | +2.287 |
Neg logit contributions | |
Line | -2.507 |
Beet | -2.409 |
Tig | -2.399 |
metaphor | -2.145 |
Vide | -2.133 |
Token | strom |
Token ID | 20282 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
ibaba | +1.893 |
naires | +1.789 |
unin | +1.775 |
ivo | +1.752 |
naire | +1.724 |
Neg logit contributions | |
Line | -1.396 |
Tig | -1.325 |
Beet | -1.324 |
metaphor | -1.171 |
Vide | -1.145 |
Token | Pulse |
Token ID | 25062 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
ibaba | +4.699 |
naires | +4.454 |
unin | +4.423 |
naire | +4.396 |
ivo | +4.390 |
Neg logit contributions | |
Line | -3.162 |
Beet | -3.053 |
Tig | -3.009 |
metaphor | -2.641 |
Passive | -2.593 |
Token | vs |
Token ID | 3691 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ibaba | +4.279 |
naires | +4.085 |
naire | +3.996 |
ivo | +3.977 |
unin | +3.974 |
Neg logit contributions | |
Line | -3.100 |
Beet | -2.972 |
Tig | -2.972 |
metaphor | -2.616 |
Vide | -2.538 |
Token | Paradise |
Token ID | 20494 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ibaba | +1.473 |
naires | +1.400 |
unin | +1.383 |
ivo | +1.359 |
naire | +1.354 |
Neg logit contributions | |
Line | -1.026 |
Tig | -0.971 |
Beet | -0.971 |
metaphor | -0.852 |
polarized | -0.828 |
Token | M |
Token ID | 337 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ibaba | +1.834 |
naires | +1.737 |
unin | +1.714 |
ivo | +1.689 |
naire | +1.683 |
Neg logit contributions | |
Line | -1.282 |
Tig | -1.215 |
Beet | -1.212 |
metaphor | -1.056 |
Vide | -1.032 |
Token | antle |
Token ID | 16941 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ibaba | +1.274 |
naires | +1.189 |
unin | +1.169 |
ivo | +1.144 |
naire | +1.132 |
Neg logit contributions | |
Line | -1.477 |
Tig | -1.416 |
Beet | -1.409 |
metaphor | -1.264 |
Vide | -1.250 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ibaba | +1.289 |
naires | +1.216 |
unin | +1.196 |
naire | +1.176 |
ivo | +1.176 |
Neg logit contributions | |
Line | -1.218 |
Tig | -1.173 |
Beet | -1.166 |
metaphor | -1.040 |
Vide | -1.024 |
Token | s |
Token ID | 82 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ibaba | +1.266 |
naires | +1.198 |
unin | +1.180 |
ivo | +1.162 |
naire | +1.148 |
Neg logit contributions | |
Line | -1.044 |
Tig | -0.997 |
Beet | -0.992 |
metaphor | -0.874 |
Vide | -0.860 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Line | +0.724 |
Beet | +0.669 |
Tig | +0.667 |
metaphor | +0.545 |
Vide | +0.534 |
Neg logit contributions | |
ibaba | -1.562 |
naires | -1.494 |
unin | -1.481 |
naire | -1.457 |
ivo | -1.454 |
Token | 53 |
Token ID | 7192 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
ibaba | +2.331 |
naires | +2.200 |
unin | +2.134 |
naire | +2.106 |
ivo | +2.105 |
Neg logit contributions | |
Line | -2.540 |
Tig | -2.453 |
Beet | -2.445 |
metaphor | -2.207 |
polarized | -2.165 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ibaba | +0.572 |
naires | +0.540 |
unin | +0.535 |
ivo | +0.526 |
orsche | +0.523 |
Neg logit contributions | |
Line | -0.379 |
Tig | -0.357 |
Beet | -0.354 |
metaphor | -0.304 |
Vide | -0.300 |
Token | e |
Token ID | 304 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Line | +0.155 |
Tig | +0.146 |
Beet | +0.146 |
Passive | +0.125 |
Vide | +0.125 |
Neg logit contributions | |
ibaba | -0.210 |
naires | -0.197 |
unin | -0.197 |
ivo | -0.191 |
orsche | -0.190 |
Token | 6 |
Token ID | 21 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
ibaba | +0.305 |
naires | +0.288 |
unin | +0.283 |
naire | +0.277 |
ivo | +0.276 |
Neg logit contributions | |
Line | -0.256 |
Tig | -0.243 |
Beet | -0.240 |
metaphor | -0.211 |
Vide | -0.209 |
Token | { |
Token ID | 1391 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
ibaba | +3.865 |
naires | +3.681 |
unin | +3.588 |
ivo | +3.558 |
naire | +3.523 |
Neg logit contributions | |
Line | -3.480 |
Tig | -3.341 |
Beet | -3.331 |
metaphor | -2.975 |
wart | -2.923 |
Token | ( |
Token ID | 7 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ibaba | +0.488 |
naires | +0.450 |
unin | +0.442 |
ivo | +0.433 |
naire | +0.426 |
Neg logit contributions | |
Line | -0.694 |
Tig | -0.669 |
Beet | -0.667 |
metaphor | -0.605 |
Vide | -0.598 |
Token | 8 |
Token ID | 23 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ibaba | +0.533 |
naires | +0.500 |
unin | +0.493 |
ivo | +0.484 |
naire | +0.479 |
Neg logit contributions | |
Line | -0.510 |
Tig | -0.487 |
Beet | -0.485 |
metaphor | -0.430 |
Vide | -0.425 |
Token | s |
Token ID | 82 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ibaba | +0.593 |
naires | +0.560 |
unin | +0.551 |
ivo | +0.543 |
naire | +0.536 |
Neg logit contributions | |
Line | -0.493 |
Tig | -0.471 |
Beet | -0.469 |
metaphor | -0.412 |
Vide | -0.407 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
Line | +0.688 |
Tig | +0.638 |
Beet | +0.637 |
metaphor | +0.525 |
Vide | +0.515 |
Neg logit contributions | |
ibaba | -1.417 |
naires | -1.354 |
unin | -1.340 |
ivo | -1.318 |
naire | -1.316 |
Token | [ |
Token ID | 685 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ibaba | +0.795 |
naires | +0.753 |
unin | +0.744 |
ivo | +0.731 |
naire | +0.726 |
Neg logit contributions | |
Line | -0.567 |
Tig | -0.537 |
Beet | -0.535 |
metaphor | -0.463 |
Vide | -0.456 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ibaba | +1.125 |
naires | +1.057 |
unin | +1.042 |
ivo | +1.023 |
naire | +1.014 |
Neg logit contributions | |
Line | -0.967 |
Tig | -0.920 |
Beet | -0.914 |
metaphor | -0.807 |
Vide | -0.796 |
Token | : |
Token ID | 25 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ibaba | +1.675 |
naires | +1.584 |
unin | +1.559 |
ivo | +1.530 |
naire | +1.519 |
Neg logit contributions | |
Line | -1.510 |
Tig | -1.441 |
Beet | -1.440 |
metaphor | -1.270 |
Vide | -1.252 |
Token | 47 |
Token ID | 2857 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ibaba | +1.460 |
naires | +1.355 |
unin | +1.342 |
ivo | +1.314 |
orsche | +1.284 |
Neg logit contributions | |
Line | -1.747 |
Tig | -1.673 |
Beet | -1.663 |
metaphor | -1.495 |
Vide | -1.487 |
Token | ] |
Token ID | 60 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ibaba | +0.363 |
naires | +0.336 |
unin | +0.334 |
orsche | +0.329 |
ivo | +0.328 |
Neg logit contributions | |
Line | -0.276 |
Tig | -0.261 |
Beet | -0.256 |
metaphor | -0.224 |
Vide | -0.223 |
Token | <@ |
Token ID | 32406 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
ibaba | +0.643 |
naires | +0.587 |
unin | +0.575 |
ivo | +0.559 |
naire | +0.552 |
Neg logit contributions | |
Line | -1.132 |
Tig | -1.094 |
Beet | -1.091 |
metaphor | -0.996 |
Vide | -0.988 |
Token | t |
Token ID | 83 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ibaba | +3.703 |
unin | +3.505 |
naires | +3.482 |
ivo | +3.378 |
naire | +3.334 |
Neg logit contributions | |
Line | -3.722 |
Beet | -3.583 |
Tig | -3.535 |
metaphor | -3.163 |
polarized | -3.134 |
Token | ay |
Token ID | 323 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ibaba | +3.544 |
unin | +3.342 |
ivo | +3.334 |
naires | +3.311 |
orsche | +3.254 |
Neg logit contributions | |
Line | -2.514 |
Beet | -2.398 |
Tig | -2.376 |
metaphor | -2.049 |
polarized | -2.031 |
Token | l |
Token ID | 75 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ibaba | +2.286 |
naires | +2.141 |
unin | +2.124 |
ivo | +2.090 |
naire | +2.062 |
Neg logit contributions | |
Line | -2.082 |
Tig | -1.986 |
Beet | -1.984 |
metaphor | -1.751 |
Vide | -1.732 |
Token | ort |
Token ID | 419 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ibaba | +1.693 |
naires | +1.563 |
unin | +1.546 |
ivo | +1.511 |
orsche | +1.488 |
Neg logit contributions | |
Line | -2.338 |
Tig | -2.244 |
Beet | -2.242 |
metaphor | -2.030 |
Vide | -2.008 |
Token | ot |
Token ID | 313 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ibaba | +1.270 |
naires | +1.192 |
unin | +1.176 |
ivo | +1.161 |
naire | +1.146 |
Neg logit contributions | |
Line | -1.171 |
Tig | -1.121 |
Beet | -1.118 |
metaphor | -0.989 |
Vide | -0.978 |
Token |
|
Token ID | 198 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ibaba | +0.751 |
naires | +0.708 |
unin | +0.696 |
ivo | +0.684 |
naire | +0.681 |
Neg logit contributions | |
Line | -0.705 |
Tig | -0.675 |
Beet | -0.672 |
metaphor | -0.600 |
Vide | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ibaba | +0.477 |
naires | +0.442 |
unin | +0.439 |
ivo | +0.430 |
orsche | +0.430 |
Neg logit contributions | |
Line | -0.419 |
Tig | -0.398 |
Beet | -0.393 |
metaphor | -0.347 |
Vide | -0.345 |
Token | Ph |
Token ID | 2725 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ibaba | +0.386 |
naires | +0.362 |
unin | +0.357 |
ivo | +0.350 |
naire | +0.347 |
Neg logit contributions | |
Line | -0.364 |
Tig | -0.347 |
Beet | -0.346 |
metaphor | -0.306 |
Vide | -0.303 |
Token | y |
Token ID | 88 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ibaba | +1.637 |
naires | +1.535 |
unin | +1.525 |
ivo | +1.492 |
naire | +1.472 |
Neg logit contributions | |
Line | -1.550 |
Beet | -1.480 |
Tig | -1.479 |
metaphor | -1.312 |
Vide | -1.298 |
Token | rex |
Token ID | 21510 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ibaba | +0.462 |
naires | +0.430 |
unin | +0.420 |
ivo | +0.411 |
naire | +0.407 |
Neg logit contributions | |
Line | -0.593 |
Tig | -0.570 |
Beet | -0.569 |
metaphor | -0.510 |
Vide | -0.505 |
Token | ian |
Token ID | 666 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
ibaba | +1.673 |
naires | +1.580 |
unin | +1.561 |
ivo | +1.534 |
naire | +1.515 |
Neg logit contributions | |
Line | -1.454 |
Tig | -1.384 |
Beet | -1.379 |
metaphor | -1.229 |
Vide | -1.203 |
Token | Tower |
Token ID | 8765 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ibaba | +4.365 |
naires | +4.201 |
naire | +4.100 |
ivo | +4.087 |
unin | +4.079 |
Neg logit contributions | |
Line | -2.873 |
Tig | -2.724 |
Beet | -2.715 |
metaphor | -2.420 |
polarized | -2.374 |
Token | vs |
Token ID | 3691 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
ibaba | +3.136 |
naires | +3.003 |
naire | +2.937 |
unin | +2.921 |
ivo | +2.914 |
Neg logit contributions | |
Line | -2.272 |
Beet | -2.180 |
Tig | -2.180 |
metaphor | -1.909 |
polarized | -1.868 |
Token | Sands |
Token ID | 35359 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ibaba | +0.590 |
naires | +0.559 |
unin | +0.552 |
ivo | +0.542 |
naire | +0.538 |
Neg logit contributions | |
Line | -0.432 |
Tig | -0.409 |
Beet | -0.408 |
metaphor | -0.355 |
Vide | -0.349 |
Token | of |
Token ID | 286 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ibaba | +2.804 |
naires | +2.659 |
unin | +2.628 |
ivo | +2.594 |
naire | +2.575 |
Neg logit contributions | |
Line | -2.173 |
Tig | -2.079 |
Beet | -2.067 |
metaphor | -1.829 |
polarized | -1.792 |
Token | Time |
Token ID | 3862 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ibaba | +1.978 |
naires | +1.856 |
unin | +1.849 |
ivo | +1.813 |
naire | +1.800 |
Neg logit contributions | |
Line | -1.316 |
Tig | -1.246 |
Beet | -1.246 |
metaphor | -1.095 |
polarized | -1.066 |
Token | Head |
Token ID | 7123 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ibaba | +0.167 |
naires | +0.158 |
unin | +0.156 |
ivo | +0.153 |
naire | +0.152 |
Neg logit contributions | |
Line | -0.113 |
Tig | -0.107 |
Beet | -0.106 |
metaphor | -0.091 |
Vide | -0.090 |
Token | Athletic |
Token ID | 29007 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ibaba | +0.610 |
naires | +0.581 |
unin | +0.575 |
ivo | +0.566 |
naire | +0.562 |
Neg logit contributions | |
Line | -0.378 |
Tig | -0.358 |
Beet | -0.357 |
metaphor | -0.306 |
polarized | -0.299 |
Token | Trainer |
Token ID | 31924 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Line | +0.171 |
Tig | +0.161 |
Beet | +0.160 |
metaphor | +0.138 |
Vide | +0.136 |
Neg logit contributions | |
ibaba | -0.256 |
naires | -0.243 |
unin | -0.240 |
ivo | -0.235 |
naire | -0.234 |
Token | ) |
Token ID | 8 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ibaba | +0.210 |
naires | +0.200 |
unin | +0.197 |
ivo | +0.194 |
naire | +0.193 |
Neg logit contributions | |
Line | -0.133 |
Tig | -0.126 |
Beet | -0.125 |
metaphor | -0.107 |
Vide | -0.105 |
Token | Aff |
Token ID | 6708 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ibaba | +1.877 |
naires | +1.787 |
unin | +1.757 |
ivo | +1.730 |
naire | +1.721 |
Neg logit contributions | |
Line | -1.396 |
Tig | -1.329 |
Beet | -1.327 |
metaphor | -1.161 |
polarized | -1.136 |
Token | idav |
Token ID | 20331 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ibaba | +1.677 |
naires | +1.570 |
unin | +1.549 |
ivo | +1.515 |
naire | +1.503 |
Neg logit contributions | |
Line | -1.803 |
Beet | -1.736 |
Tig | -1.736 |
metaphor | -1.563 |
polarized | -1.541 |
Token | it |
Token ID | 270 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ibaba | +3.391 |
naires | +3.172 |
unin | +3.128 |
ivo | +3.086 |
naire | +3.068 |
Neg logit contributions | |
Line | -3.951 |
Beet | -3.877 |
Tig | -3.844 |
metaphor | -3.448 |
polarized | -3.425 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ibaba | +1.897 |
naires | +1.808 |
unin | +1.758 |
ivo | +1.744 |
naire | +1.739 |
Neg logit contributions | |
Line | -1.815 |
Beet | -1.745 |
Tig | -1.742 |
metaphor | -1.557 |
polarized | -1.529 |
Token |
|
Token ID | 198 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
ibaba | +0.828 |
naires | +0.771 |
unin | +0.764 |
ivo | +0.750 |
orsche | +0.745 |
Neg logit contributions | |
Line | -0.745 |
Tig | -0.710 |
Beet | -0.702 |
metaphor | -0.621 |
Vide | -0.616 |
Token | V |
Token ID | 53 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ibaba | +0.730 |
naires | +0.687 |
unin | +0.678 |
ivo | +0.665 |
naire | +0.660 |
Neg logit contributions | |
Line | -0.655 |
Tig | -0.624 |
Beet | -0.622 |
metaphor | -0.549 |
Vide | -0.542 |
Token | il |
Token ID | 346 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ibaba | +0.426 |
naires | +0.399 |
unin | +0.395 |
ivo | +0.390 |
naire | +0.383 |
Neg logit contributions | |
Line | -0.406 |
Tig | -0.388 |
Beet | -0.388 |
metaphor | -0.343 |
Vide | -0.339 |
Token | identifying |
Token ID | 13720 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ibaba | +0.825 |
naires | +0.773 |
unin | +0.764 |
ivo | +0.749 |
naire | +0.743 |
Neg logit contributions | |
Line | -0.724 |
Tig | -0.688 |
Beet | -0.685 |
metaphor | -0.606 |
Vide | -0.596 |
Token | objects |
Token ID | 5563 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Line | +0.182 |
Tig | +0.173 |
Beet | +0.172 |
metaphor | +0.153 |
polarized | +0.151 |
Neg logit contributions | |
ibaba | -0.205 |
naires | -0.192 |
unin | -0.190 |
ivo | -0.186 |
naire | -0.185 |
Token | that |
Token ID | 326 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Line | +0.453 |
Tig | +0.431 |
Beet | +0.427 |
metaphor | +0.376 |
polarized | +0.369 |
Neg logit contributions | |
ibaba | -0.580 |
naires | -0.544 |
unin | -0.537 |
ivo | -0.527 |
naire | -0.524 |
Token | were |
Token ID | 547 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Line | +0.744 |
Tig | +0.700 |
Beet | +0.690 |
metaphor | +0.604 |
polarized | +0.594 |
Neg logit contributions | |
ibaba | -1.144 |
naires | -1.066 |
unin | -1.064 |
ivo | -1.045 |
naire | -1.035 |
Token | too |
Token ID | 1165 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Line | +0.768 |
Tig | +0.729 |
Beet | +0.723 |
metaphor | +0.641 |
polarized | +0.632 |
Neg logit contributions | |
ibaba | -0.972 |
naires | -0.906 |
unin | -0.892 |
ivo | -0.881 |
naire | -0.874 |
Token | dim |
Token ID | 5391 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
Line | +1.198 |
Tig | +1.136 |
Beet | +1.121 |
metaphor | +0.995 |
polarized | +0.983 |
Neg logit contributions | |
ibaba | -1.587 |
naires | -1.484 |
unin | -1.466 |
ivo | -1.444 |
naire | -1.435 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ibaba | +3.726 |
naires | +3.480 |
unin | +3.480 |
humane | +3.398 |
ivo | +3.397 |
Neg logit contributions | |
Line | -3.563 |
Beet | -3.445 |
Tig | -3.432 |
Vide | -3.018 |
metaphor | -2.959 |
Token | or |
Token ID | 393 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ibaba | +0.903 |
naires | +0.853 |
unin | +0.842 |
ivo | +0.827 |
naire | +0.820 |
Neg logit contributions | |
Line | -0.717 |
Tig | -0.682 |
Beet | -0.679 |
metaphor | -0.594 |
Vide | -0.585 |
Token | were |
Token ID | 547 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ibaba | +0.169 |
naires | +0.158 |
unin | +0.157 |
ivo | +0.154 |
naire | +0.153 |
Neg logit contributions | |
Line | -0.137 |
Tig | -0.131 |
Beet | -0.129 |
metaphor | -0.115 |
polarized | -0.113 |
Token | difficult |
Token ID | 2408 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
ibaba | +0.014 |
naires | +0.013 |
unin | +0.013 |
ivo | +0.013 |
naire | +0.013 |
Neg logit contributions | |
Line | -0.013 |
Tig | -0.013 |
Beet | -0.012 |
metaphor | -0.011 |
polarized | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Line | +0.585 |
Tig | +0.556 |
Beet | +0.553 |
metaphor | +0.487 |
Vide | +0.479 |
Neg logit contributions | |
ibaba | -0.705 |
naires | -0.663 |
unin | -0.655 |
ivo | -0.643 |
naire | -0.638 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ibaba | +0.852 |
naires | +0.803 |
unin | +0.792 |
ivo | +0.777 |
naire | +0.770 |
Neg logit contributions | |
Line | -0.764 |
Tig | -0.730 |
Beet | -0.726 |
metaphor | -0.641 |
Vide | -0.632 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Line | +0.162 |
Tig | +0.153 |
Beet | +0.152 |
metaphor | +0.134 |
Vide | +0.132 |
Neg logit contributions | |
ibaba | -0.207 |
naires | -0.195 |
unin | -0.193 |
ivo | -0.189 |
naire | -0.188 |
Token | name |
Token ID | 3672 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Line | +0.976 |
Beet | +0.917 |
Tig | +0.917 |
metaphor | +0.824 |
Passive | +0.816 |
Neg logit contributions | |
ibaba | -0.978 |
naires | -0.913 |
unin | -0.887 |
naire | -0.874 |
ivo | -0.870 |
Token | "> |
Token ID | 23984 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Line | +0.190 |
Tig | +0.181 |
Beet | +0.180 |
metaphor | +0.156 |
Vide | +0.154 |
Neg logit contributions | |
ibaba | -0.250 |
naires | -0.237 |
unin | -0.234 |
ivo | -0.230 |
naire | -0.228 |
Token | span |
Token ID | 12626 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ibaba | +1.377 |
naires | +1.281 |
unin | +1.264 |
ivo | +1.234 |
naire | +1.219 |
Neg logit contributions | |
Line | -1.710 |
Tig | -1.646 |
Beet | -1.644 |
metaphor | -1.473 |
Vide | -1.461 |
Token | > |
Token ID | 29 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
ibaba | +1.051 |
naires | +0.984 |
unin | +0.970 |
ivo | +0.949 |
naire | +0.941 |
Neg logit contributions | |
Line | -1.120 |
Tig | -1.075 |
Beet | -1.073 |
metaphor | -0.956 |
Vide | -0.946 |
Token | < |
Token ID | 1279 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ibaba | +2.327 |
naires | +2.108 |
unin | +2.024 |
ivo | +2.017 |
naire | +1.968 |
Neg logit contributions | |
Line | -4.872 |
Tig | -4.813 |
Beet | -4.780 |
metaphor | -4.393 |
polarized | -4.348 |
Token | p |
Token ID | 79 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ibaba | +0.382 |
naires | +0.357 |
unin | +0.352 |
ivo | +0.345 |
naire | +0.341 |
Neg logit contributions | |
Line | -0.411 |
Tig | -0.394 |
Beet | -0.393 |
metaphor | -0.351 |
Vide | -0.347 |
Token | ng |
Token ID | 23370 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
ibaba | +0.840 |
naires | +0.785 |
unin | +0.775 |
ivo | +0.760 |
orsche | +0.753 |
Neg logit contributions | |
Line | -0.886 |
Tig | -0.852 |
Beet | -0.849 |
metaphor | -0.755 |
Vide | -0.748 |
Token | - |
Token ID | 12 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Line | +0.057 |
Tig | +0.054 |
Beet | +0.053 |
metaphor | +0.046 |
Passive | +0.046 |
Neg logit contributions | |
ibaba | -0.076 |
naires | -0.072 |
unin | -0.071 |
ivo | -0.070 |
orsche | -0.069 |
Token | bind |
Token ID | 21653 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ibaba | +0.191 |
naires | +0.179 |
unin | +0.175 |
ivo | +0.172 |
naire | +0.171 |
Neg logit contributions | |
Line | -0.201 |
Tig | -0.191 |
Beet | -0.191 |
metaphor | -0.171 |
Passive | -0.169 |
Token | of |
Token ID | 286 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Line | +1.110 |
Tig | +1.068 |
Beet | +1.043 |
metaphor | +0.920 |
polarized | +0.892 |
Neg logit contributions | |
ibaba | -1.583 |
naires | -1.489 |
unin | -1.483 |
ivo | -1.451 |
orsche | -1.451 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ibaba | +0.068 |
naires | +0.064 |
unin | +0.064 |
ivo | +0.062 |
naire | +0.062 |
Neg logit contributions | |
Line | -0.053 |
Tig | -0.050 |
Beet | -0.050 |
metaphor | -0.044 |
Vide | -0.043 |
Token | Muslims |
Token ID | 7045 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
Line | +0.073 |
Tig | +0.069 |
Beet | +0.069 |
metaphor | +0.059 |
Vide | +0.058 |
Neg logit contributions | |
ibaba | -0.111 |
naires | -0.105 |
unin | -0.104 |
ivo | -0.102 |
naire | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ibaba | +0.086 |
naires | +0.081 |
unin | +0.080 |
ivo | +0.079 |
orsche | +0.078 |
Neg logit contributions | |
Line | -0.065 |
Tig | -0.062 |
Beet | -0.061 |
metaphor | -0.054 |
Vide | -0.053 |
Token | Kh |
Token ID | 5311 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ibaba | +0.526 |
naires | +0.496 |
unin | +0.490 |
ivo | +0.481 |
naire | +0.477 |
Neg logit contributions | |
Line | -0.430 |
Tig | -0.409 |
Beet | -0.408 |
metaphor | -0.357 |
Vide | -0.352 |
Token | all |
Token ID | 439 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
ibaba | +0.009 |
naires | +0.008 |
unin | +0.008 |
ivo | +0.008 |
naire | +0.008 |
Neg logit contributions | |
Line | -0.009 |
Tig | -0.009 |
Beet | -0.009 |
metaphor | -0.008 |
Vide | -0.008 |
Token | ad |
Token ID | 324 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Line | +4.299 |
Tig | +4.127 |
Beet | +4.019 |
ath | +3.577 |
Vide | +3.573 |
Neg logit contributions | |
ibaba | -3.989 |
naires | -3.862 |
unin | -3.706 |
catentry | -3.698 |
orsche | -3.661 |
Token | bin |
Token ID | 9874 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
ibaba | +1.390 |
naires | +1.300 |
unin | +1.288 |
ivo | +1.265 |
naire | +1.249 |
Neg logit contributions | |
Line | -1.274 |
Beet | -1.213 |
Tig | -1.211 |
metaphor | -1.076 |
Vide | -1.058 |
Token | Su |
Token ID | 1778 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Line | +0.059 |
Tig | +0.056 |
Beet | +0.056 |
metaphor | +0.049 |
Vide | +0.048 |
Neg logit contributions | |
ibaba | -0.075 |
naires | -0.070 |
unin | -0.069 |
ivo | -0.068 |
naire | -0.068 |
Token | w |
Token ID | 86 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Line | +0.571 |
Tig | +0.542 |
Beet | +0.538 |
metaphor | +0.474 |
Vide | +0.467 |
Neg logit contributions | |
ibaba | -0.643 |
naires | -0.615 |
unin | -0.596 |
naire | -0.586 |
ivo | -0.585 |
Token | aid |
Token ID | 1698 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Line | +0.282 |
Tig | +0.271 |
Beet | +0.267 |
wart | +0.241 |
metaphor | +0.241 |
Neg logit contributions | |
ibaba | -0.205 |
naires | -0.194 |
unin | -0.185 |
orsche | -0.184 |
ivo | -0.184 |
Token | er |
Token ID | 263 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ibaba | +0.400 |
naires | +0.365 |
unin | +0.359 |
ivo | +0.353 |
naire | +0.346 |
Neg logit contributions | |
Line | -0.634 |
Tig | -0.611 |
Beet | -0.607 |
metaphor | -0.555 |
Vide | -0.549 |
Token | ." |
Token ID | 526 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ibaba | +0.838 |
naires | +0.796 |
unin | +0.782 |
ivo | +0.766 |
naire | +0.762 |
Neg logit contributions | |
Line | -0.673 |
Tig | -0.638 |
Beet | -0.638 |
metaphor | -0.558 |
Vide | -0.550 |
Token |
|
Token ID | 198 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ibaba | +0.015 |
naires | +0.014 |
unin | +0.014 |
ivo | +0.013 |
naire | +0.013 |
Neg logit contributions | |
Line | -0.014 |
Tig | -0.013 |
Beet | -0.013 |
metaphor | -0.012 |
polarized | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Line | +0.480 |
Tig | +0.455 |
Beet | +0.445 |
metaphor | +0.394 |
Vide | +0.392 |
Neg logit contributions | |
ibaba | -0.577 |
naires | -0.529 |
unin | -0.528 |
orsche | -0.520 |
ivo | -0.519 |
Token | R |
Token ID | 49 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Line | +0.411 |
Tig | +0.391 |
Beet | +0.388 |
metaphor | +0.341 |
Vide | +0.338 |
Neg logit contributions | |
ibaba | -0.494 |
naires | -0.464 |
unin | -0.457 |
ivo | -0.448 |
naire | -0.446 |
Token | ever |
Token ID | 964 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Line | +0.706 |
Tig | +0.672 |
Beet | +0.667 |
metaphor | +0.587 |
Vide | +0.578 |
Neg logit contributions | |
ibaba | -0.837 |
naires | -0.790 |
unin | -0.777 |
ivo | -0.762 |
naire | -0.760 |
Token | se |
Token ID | 325 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Line | +4.396 |
Beet | +4.214 |
Tig | +4.201 |
Vide | +3.724 |
metaphor | +3.694 |
Neg logit contributions | |
ibaba | -3.916 |
naires | -3.637 |
unin | -3.510 |
naire | -3.422 |
humane | -3.420 |
Token | side |
Token ID | 1735 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Line | +1.653 |
Tig | +1.546 |
Beet | +1.537 |
metaphor | +1.351 |
Vide | +1.327 |
Neg logit contributions | |
ibaba | -2.224 |
naires | -2.099 |
unin | -2.075 |
ivo | -2.033 |
naire | -2.023 |
Token | of |
Token ID | 286 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
ibaba | +1.288 |
naires | +1.223 |
unin | +1.202 |
ivo | +1.180 |
naire | +1.171 |
Neg logit contributions | |
Line | -1.097 |
Tig | -1.057 |
Beet | -1.050 |
metaphor | -0.920 |
Vide | -0.912 |
Token | flyer |
Token ID | 42464 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ibaba | +0.077 |
naires | +0.072 |
unin | +0.071 |
ivo | +0.070 |
naire | +0.069 |
Neg logit contributions | |
Line | -0.074 |
Tig | -0.071 |
Beet | -0.070 |
metaphor | -0.062 |
Vide | -0.062 |
Token | ( |
Token ID | 357 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ibaba | +0.395 |
naires | +0.376 |
unin | +0.369 |
ivo | +0.363 |
naire | +0.361 |
Neg logit contributions | |
Line | -0.312 |
Tig | -0.297 |
Beet | -0.296 |
metaphor | -0.258 |
Passive | -0.255 |
Token | benevolent |
Token ID | 45599 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ibaba | +0.124 |
naires | +0.117 |
unin | +0.115 |
ivo | +0.113 |
naire | +0.112 |
Neg logit contributions | |
Line | -0.103 |
Tig | -0.098 |
Beet | -0.098 |
metaphor | -0.085 |
Vide | -0.085 |
Token | its |
Token ID | 663 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
ibaba | +0.913 |
naires | +0.864 |
unin | +0.852 |
ivo | +0.838 |
naire | +0.831 |
Neg logit contributions | |
Line | -0.683 |
Tig | -0.648 |
Beet | -0.647 |
metaphor | -0.560 |
Vide | -0.555 |
Token | happening |
Token ID | 5836 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Line | +0.578 |
Tig | +0.548 |
Beet | +0.545 |
metaphor | +0.482 |
Vide | +0.469 |
Neg logit contributions | |
ibaba | -0.736 |
naires | -0.693 |
unin | -0.686 |
ivo | -0.674 |
naire | -0.668 |
Token | is |
Token ID | 318 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ibaba | +1.458 |
naires | +1.389 |
unin | +1.364 |
ivo | +1.338 |
naire | +1.326 |
Neg logit contributions | |
Line | -1.159 |
Beet | -1.102 |
Tig | -1.099 |
Vide | -0.949 |
Passive | -0.946 |
Token | depends |
Token ID | 8338 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Line | +0.123 |
Tig | +0.117 |
Beet | +0.117 |
metaphor | +0.103 |
Vide | +0.101 |
Neg logit contributions | |
ibaba | -0.147 |
naires | -0.139 |
unin | -0.137 |
ivo | -0.134 |
naire | -0.133 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
Line | +0.662 |
Tig | +0.630 |
Beet | +0.627 |
metaphor | +0.552 |
Vide | +0.544 |
Neg logit contributions | |
ibaba | -0.788 |
naires | -0.743 |
unin | -0.733 |
ivo | -0.719 |
naire | -0.713 |
Token | whether |
Token ID | 1771 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Line | +3.904 |
Tig | +3.687 |
Beet | +3.556 |
metaphor | +3.370 |
polarized | +3.231 |
Neg logit contributions | |
ibaba | -4.389 |
naires | -4.065 |
unin | -4.040 |
ivo | -3.999 |
orsche | -3.988 |
Token | you |
Token ID | 345 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Line | +1.845 |
Tig | +1.759 |
Beet | +1.738 |
metaphor | +1.573 |
Vide | +1.534 |
Neg logit contributions | |
ibaba | -1.851 |
naires | -1.727 |
unin | -1.713 |
ivo | -1.671 |
naire | -1.663 |
Token | � |
Token ID | 447 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
Line | +0.961 |
Tig | +0.910 |
Beet | +0.900 |
metaphor | +0.795 |
Vide | +0.772 |
Neg logit contributions | |
ibaba | -1.320 |
naires | -1.249 |
unin | -1.235 |
ivo | -1.208 |
naire | -1.203 |
Token | � |
Token ID | 247 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Line | +0.059 |
Tig | +0.056 |
Beet | +0.056 |
metaphor | +0.051 |
Passive | +0.050 |
Neg logit contributions | |
ibaba | -0.043 |
naires | -0.040 |
unin | -0.039 |
ivo | -0.039 |
orsche | -0.038 |
Token | re |
Token ID | 260 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Line | +0.244 |
Tig | +0.232 |
Beet | +0.230 |
metaphor | +0.204 |
Vide | +0.201 |
Neg logit contributions | |
ibaba | -0.272 |
naires | -0.255 |
unin | -0.252 |
ivo | -0.246 |
orsche | -0.245 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ibaba | +0.309 |
naires | +0.291 |
unin | +0.287 |
ivo | +0.282 |
naire | +0.280 |
Neg logit contributions | |
Line | -0.249 |
Tig | -0.237 |
Beet | -0.236 |
metaphor | -0.207 |
Vide | -0.204 |
Token | Continue |
Token ID | 10054 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ibaba | +0.194 |
naires | +0.182 |
unin | +0.178 |
naire | +0.173 |
ivo | +0.173 |
Neg logit contributions | |
Line | -0.217 |
Tig | -0.208 |
Beet | -0.206 |
metaphor | -0.185 |
Vide | -0.184 |
Token | reading |
Token ID | 3555 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Line | +0.282 |
Tig | +0.262 |
Beet | +0.258 |
metaphor | +0.213 |
Vide | +0.208 |
Neg logit contributions | |
ibaba | -0.624 |
naires | -0.594 |
unin | -0.589 |
ivo | -0.580 |
orsche | -0.577 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
Line | +0.638 |
Tig | +0.607 |
Beet | +0.594 |
metaphor | +0.530 |
Vide | +0.524 |
Neg logit contributions | |
ibaba | -0.732 |
naires | -0.683 |
unin | -0.675 |
ivo | -0.662 |
orsche | -0.659 |
Token | main |
Token ID | 1388 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Line | +0.013 |
Tig | +0.012 |
Beet | +0.012 |
metaphor | +0.011 |
Passive | +0.011 |
Neg logit contributions | |
ibaba | -0.011 |
naires | -0.010 |
unin | -0.010 |
naire | -0.010 |
orsche | -0.010 |
Token | story |
Token ID | 1621 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
ibaba | +0.123 |
naires | +0.117 |
unin | +0.115 |
ivo | +0.113 |
naire | +0.113 |
Neg logit contributions | |
Line | -0.088 |
Tig | -0.083 |
Beet | -0.081 |
metaphor | -0.072 |
Vide | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Line | +3.469 |
Tig | +3.249 |
Beet | +3.121 |
Vide | +2.803 |
Passive | +2.777 |
Neg logit contributions | |
ibaba | -4.842 |
unin | -4.427 |
orsche | -4.417 |
naires | -4.343 |
ivo | -4.327 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Line | +0.778 |
Tig | +0.734 |
Beet | +0.714 |
Vide | +0.630 |
Passive | +0.630 |
Neg logit contributions | |
ibaba | -0.977 |
unin | -0.894 |
naires | -0.887 |
orsche | -0.884 |
ivo | -0.876 |
Token | Some |
Token ID | 4366 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Line | +0.719 |
Tig | +0.685 |
Beet | +0.678 |
metaphor | +0.598 |
Vide | +0.594 |
Neg logit contributions | |
ibaba | -0.853 |
naires | -0.793 |
unin | -0.785 |
ivo | -0.768 |
orsche | -0.765 |
Token | teenagers |
Token ID | 17366 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
Line | +0.755 |
Tig | +0.719 |
Beet | +0.715 |
metaphor | +0.627 |
Vide | +0.616 |
Neg logit contributions | |
ibaba | -0.940 |
naires | -0.882 |
unin | -0.874 |
ivo | -0.856 |
naire | -0.851 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Line | +0.473 |
Tig | +0.447 |
Beet | +0.444 |
metaphor | +0.385 |
Vide | +0.377 |
Neg logit contributions | |
ibaba | -0.697 |
naires | -0.659 |
unin | -0.652 |
ivo | -0.640 |
naire | -0.636 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ibaba | +0.524 |
naires | +0.496 |
unin | +0.489 |
ivo | +0.480 |
naire | +0.476 |
Neg logit contributions | |
Line | -0.442 |
Tig | -0.421 |
Beet | -0.420 |
metaphor | -0.369 |
Vide | -0.363 |
Token | Continue |
Token ID | 10054 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ibaba | +0.416 |
naires | +0.389 |
unin | +0.381 |
ivo | +0.371 |
naire | +0.371 |
Neg logit contributions | |
Line | -0.465 |
Tig | -0.446 |
Beet | -0.442 |
metaphor | -0.396 |
Vide | -0.395 |
Token | reading |
Token ID | 3555 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Line | +0.161 |
Tig | +0.150 |
Beet | +0.147 |
metaphor | +0.121 |
Vide | +0.119 |
Neg logit contributions | |
ibaba | -0.363 |
naires | -0.346 |
unin | -0.343 |
ivo | -0.338 |
orsche | -0.337 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Line | +0.640 |
Tig | +0.609 |
Beet | +0.594 |
metaphor | +0.529 |
Vide | +0.525 |
Neg logit contributions | |
ibaba | -0.744 |
naires | -0.693 |
unin | -0.685 |
ivo | -0.673 |
orsche | -0.671 |
Token | main |
Token ID | 1388 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Line | +0.148 |
Tig | +0.142 |
Beet | +0.138 |
metaphor | +0.127 |
Passive | +0.124 |
Neg logit contributions | |
ibaba | -0.128 |
naires | -0.119 |
unin | -0.116 |
naire | -0.114 |
orsche | -0.114 |
Token | story |
Token ID | 1621 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
ibaba | +0.096 |
naires | +0.090 |
unin | +0.089 |
ivo | +0.088 |
orsche | +0.087 |
Neg logit contributions | |
Line | -0.067 |
Tig | -0.063 |
Beet | -0.061 |
metaphor | -0.055 |
Vide | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Line | +3.418 |
Tig | +3.192 |
Beet | +3.054 |
Vide | +2.764 |
Passive | +2.736 |
Neg logit contributions | |
ibaba | -4.890 |
orsche | -4.451 |
unin | -4.449 |
naires | -4.366 |
ivo | -4.359 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Line | +0.395 |
Tig | +0.374 |
Beet | +0.365 |
Vide | +0.322 |
metaphor | +0.322 |
Neg logit contributions | |
ibaba | -0.483 |
unin | -0.443 |
naires | -0.442 |
orsche | -0.437 |
ivo | -0.434 |
Token | When |
Token ID | 2215 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Line | +0.158 |
Tig | +0.151 |
Beet | +0.150 |
metaphor | +0.133 |
Vide | +0.131 |
Neg logit contributions | |
ibaba | -0.173 |
naires | -0.162 |
unin | -0.160 |
ivo | -0.157 |
naire | -0.155 |
Token | it |
Token ID | 340 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ibaba | +0.184 |
naires | +0.174 |
unin | +0.170 |
ivo | +0.167 |
naire | +0.166 |
Neg logit contributions | |
Line | -0.167 |
Tig | -0.159 |
Beet | -0.158 |
metaphor | -0.140 |
Vide | -0.138 |
Token | is |
Token ID | 318 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
ibaba | +0.591 |
naires | +0.560 |
unin | +0.551 |
ivo | +0.542 |
naire | +0.539 |
Neg logit contributions | |
Line | -0.450 |
Tig | -0.427 |
Beet | -0.427 |
metaphor | -0.369 |
Vide | -0.367 |
Token | Arrow |
Token ID | 19408 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ibaba | +2.023 |
naires | +1.904 |
unin | +1.876 |
ivo | +1.844 |
orsche | +1.829 |
Neg logit contributions | |
Line | -1.597 |
Tig | -1.519 |
Beet | -1.518 |
metaphor | -1.323 |
Vide | -1.308 |
Token | � |
Token ID | 447 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Line | +0.923 |
Tig | +0.873 |
Beet | +0.866 |
metaphor | +0.755 |
Vide | +0.742 |
Neg logit contributions | |
ibaba | -1.254 |
naires | -1.182 |
unin | -1.172 |
ivo | -1.148 |
orsche | -1.140 |
Token | � |
Token ID | 247 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Line | +1.196 |
Tig | +1.144 |
Beet | +1.139 |
metaphor | +1.034 |
Vide | +1.019 |
Neg logit contributions | |
ibaba | -0.914 |
naires | -0.845 |
unin | -0.835 |
ivo | -0.819 |
orsche | -0.802 |
Token | s |
Token ID | 82 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Line | +0.537 |
Tig | +0.507 |
Beet | +0.504 |
metaphor | +0.440 |
Vide | +0.434 |
Neg logit contributions | |
ibaba | -0.704 |
naires | -0.663 |
unin | -0.658 |
ivo | -0.645 |
orsche | -0.639 |
Token | O |
Token ID | 440 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Line | +0.294 |
Tig | +0.279 |
Beet | +0.278 |
metaphor | +0.242 |
Vide | +0.239 |
Neg logit contributions | |
ibaba | -0.376 |
naires | -0.356 |
unin | -0.351 |
ivo | -0.345 |
naire | -0.342 |
Token | lic |
Token ID | 677 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
ibaba | +0.262 |
naires | +0.247 |
unin | +0.243 |
ivo | +0.238 |
naire | +0.236 |
Neg logit contributions | |
Line | -0.243 |
Tig | -0.232 |
Beet | -0.231 |
metaphor | -0.205 |
Vide | -0.202 |
Token | ity |
Token ID | 414 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Line | +3.700 |
Tig | +3.549 |
Beet | +3.467 |
Vide | +3.068 |
metaphor | +3.054 |
Neg logit contributions | |
ibaba | -4.350 |
naires | -4.070 |
unin | -4.017 |
orsche | -3.913 |
ivo | -3.904 |
Token | . |
Token ID | 13 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Line | +1.467 |
Tig | +1.380 |
Beet | +1.365 |
metaphor | +1.197 |
Vide | +1.175 |
Neg logit contributions | |
ibaba | -2.009 |
naires | -1.893 |
unin | -1.881 |
ivo | -1.837 |
orsche | -1.826 |
Token | Oliver |
Token ID | 15416 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Line | +0.068 |
Tig | +0.064 |
Beet | +0.064 |
metaphor | +0.056 |
Vide | +0.055 |
Neg logit contributions | |
ibaba | -0.082 |
naires | -0.077 |
unin | -0.076 |
ivo | -0.075 |
naire | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Line | +1.444 |
Tig | +1.370 |
Beet | +1.347 |
metaphor | +1.184 |
Vide | +1.157 |
Neg logit contributions | |
ibaba | -1.989 |
naires | -1.874 |
unin | -1.857 |
ivo | -1.811 |
naire | -1.801 |
Token | Fel |
Token ID | 13937 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Line | +1.423 |
Tig | +1.355 |
Beet | +1.336 |
metaphor | +1.161 |
Vide | +1.143 |
Neg logit contributions | |
ibaba | -1.975 |
naires | -1.858 |
unin | -1.837 |
ivo | -1.801 |
naire | -1.789 |
Token | said |
Token ID | 531 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
Line | +0.090 |
Tig | +0.085 |
Beet | +0.085 |
metaphor | +0.070 |
Vide | +0.069 |
Neg logit contributions | |
ibaba | -0.176 |
naires | -0.168 |
unin | -0.166 |
ivo | -0.164 |
naire | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ibaba | +0.048 |
naires | +0.045 |
unin | +0.045 |
ivo | +0.044 |
naire | +0.044 |
Neg logit contributions | |
Line | -0.036 |
Tig | -0.034 |
Beet | -0.034 |
metaphor | -0.030 |
Vide | -0.029 |
Token | � |
Token ID | 564 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Line | +0.185 |
Tig | +0.174 |
Beet | +0.174 |
metaphor | +0.146 |
Vide | +0.143 |
Neg logit contributions | |
ibaba | -0.334 |
naires | -0.318 |
unin | -0.314 |
ivo | -0.310 |
naire | -0.308 |
Token | � |
Token ID | 250 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
Line | +1.007 |
Tig | +0.975 |
Beet | +0.973 |
metaphor | +0.896 |
Vide | +0.889 |
Neg logit contributions | |
ibaba | -0.447 |
naires | -0.402 |
unin | -0.392 |
ivo | -0.379 |
naire | -0.373 |
Token | T |
Token ID | 51 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Line | +0.667 |
Tig | +0.635 |
Beet | +0.629 |
metaphor | +0.559 |
Vide | +0.552 |
Neg logit contributions | |
ibaba | -0.749 |
naires | -0.700 |
unin | -0.688 |
ivo | -0.676 |
naire | -0.671 |
Token | oss |
Token ID | 793 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Line | +0.418 |
Tig | +0.398 |
Beet | +0.394 |
metaphor | +0.352 |
Vide | +0.346 |
Neg logit contributions | |
ibaba | -0.443 |
naires | -0.416 |
unin | -0.406 |
naire | -0.400 |
ivo | -0.396 |
Token | out |
Token ID | 503 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Line | +3.607 |
Tig | +3.420 |
Beet | +3.382 |
metaphor | +3.038 |
Vide | +2.945 |
Neg logit contributions | |
ibaba | -4.370 |
naires | -4.071 |
unin | -4.037 |
ivo | -3.945 |
humane | -3.932 |
Token | everything |
Token ID | 2279 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Line | +0.112 |
Tig | +0.107 |
Beet | +0.106 |
metaphor | +0.094 |
Vide | +0.093 |
Neg logit contributions | |
ibaba | -0.127 |
naires | -0.120 |
unin | -0.118 |
ivo | -0.116 |
naire | -0.115 |
Token | you |
Token ID | 345 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ibaba | +0.381 |
naires | +0.361 |
unin | +0.356 |
ivo | +0.351 |
naire | +0.348 |
Neg logit contributions | |
Line | -0.305 |
Tig | -0.290 |
Beet | -0.290 |
metaphor | -0.252 |
Vide | -0.250 |
Token | can |
Token ID | 460 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Line | +0.987 |
Tig | +0.928 |
Beet | +0.921 |
metaphor | +0.796 |
Vide | +0.782 |
Neg logit contributions | |
ibaba | -1.499 |
naires | -1.419 |
unin | -1.404 |
ivo | -1.376 |
naire | -1.367 |
Token | imagine |
Token ID | 5967 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Line | +1.160 |
Tig | +1.079 |
Beet | +1.071 |
metaphor | +0.924 |
Vide | +0.887 |
Neg logit contributions | |
ibaba | -2.002 |
naires | -1.911 |
unin | -1.897 |
ivo | -1.848 |
orsche | -1.846 |
Token | let |
Token ID | 1309 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ibaba | +0.693 |
naires | +0.655 |
unin | +0.646 |
ivo | +0.636 |
naire | +0.631 |
Neg logit contributions | |
Line | -0.546 |
Tig | -0.518 |
Beet | -0.517 |
metaphor | -0.449 |
Vide | -0.445 |
Token | the |
Token ID | 262 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Line | +0.802 |
Tig | +0.764 |
Beet | +0.758 |
metaphor | +0.671 |
Vide | +0.659 |
Neg logit contributions | |
ibaba | -0.945 |
naires | -0.895 |
unin | -0.879 |
ivo | -0.865 |
naire | -0.860 |
Token | future |
Token ID | 2003 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Line | +0.222 |
Tig | +0.210 |
Beet | +0.209 |
metaphor | +0.182 |
Vide | +0.179 |
Neg logit contributions | |
ibaba | -0.294 |
naires | -0.278 |
unin | -0.274 |
ivo | -0.269 |
naire | -0.267 |
Token | be |
Token ID | 307 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
ibaba | +0.566 |
naires | +0.534 |
unin | +0.527 |
ivo | +0.518 |
naire | +0.513 |
Neg logit contributions | |
Line | -0.463 |
Tig | -0.440 |
Beet | -0.439 |
metaphor | -0.384 |
Vide | -0.379 |
Token | held |
Token ID | 2714 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Line | +0.014 |
Tig | +0.013 |
Beet | +0.013 |
metaphor | +0.012 |
Vide | +0.011 |
Neg logit contributions | |
ibaba | -0.019 |
naires | -0.017 |
unin | -0.017 |
ivo | -0.017 |
naire | -0.017 |
Token | hostage |
Token ID | 23229 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
ibaba | +0.344 |
naires | +0.325 |
unin | +0.322 |
ivo | +0.316 |
naire | +0.313 |
Neg logit contributions | |
Line | -0.266 |
Tig | -0.252 |
Beet | -0.252 |
metaphor | -0.218 |
Vide | -0.216 |
Token | by |
Token ID | 416 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Line | +3.253 |
Tig | +3.099 |
Beet | +3.008 |
metaphor | +2.797 |
rooted | +2.649 |
Neg logit contributions | |
ibaba | -4.563 |
naires | -4.294 |
unin | -4.193 |
ivo | -4.173 |
orsche | -4.157 |
Token | the |
Token ID | 262 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ibaba | +0.288 |
naires | +0.271 |
unin | +0.268 |
ivo | +0.263 |
naire | +0.261 |
Neg logit contributions | |
Line | -0.245 |
Tig | -0.234 |
Beet | -0.233 |
metaphor | -0.205 |
Vide | -0.202 |
Token | failures |
Token ID | 15536 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
Line | +0.435 |
Tig | +0.413 |
Beet | +0.409 |
metaphor | +0.360 |
Vide | +0.352 |
Neg logit contributions | |
ibaba | -0.568 |
naires | -0.535 |
unin | -0.528 |
ivo | -0.520 |
orsche | -0.516 |
Token | of |
Token ID | 286 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Line | +0.539 |
Tig | +0.513 |
Beet | +0.509 |
metaphor | +0.451 |
Vide | +0.443 |
Neg logit contributions | |
ibaba | -0.635 |
naires | -0.597 |
unin | -0.591 |
ivo | -0.578 |
naire | -0.574 |
Token | the |
Token ID | 262 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Line | +0.411 |
Tig | +0.390 |
Beet | +0.387 |
metaphor | +0.342 |
Vide | +0.336 |
Neg logit contributions | |
ibaba | -0.507 |
naires | -0.479 |
unin | -0.471 |
ivo | -0.464 |
naire | -0.461 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ibaba | +0.533 |
naires | +0.505 |
unin | +0.498 |
ivo | +0.489 |
naire | +0.485 |
Neg logit contributions | |
Line | -0.430 |
Tig | -0.409 |
Beet | -0.408 |
metaphor | -0.357 |
Vide | -0.352 |
Token | Continue |
Token ID | 10054 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ibaba | +0.224 |
naires | +0.210 |
unin | +0.206 |
ivo | +0.200 |
naire | +0.200 |
Neg logit contributions | |
Line | -0.249 |
Tig | -0.239 |
Beet | -0.237 |
metaphor | -0.213 |
Vide | -0.212 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Line | +0.074 |
Tig | +0.069 |
Beet | +0.067 |
metaphor | +0.056 |
Vide | +0.054 |
Neg logit contributions | |
ibaba | -0.164 |
naires | -0.156 |
unin | -0.155 |
ivo | -0.153 |
orsche | -0.152 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Line | +0.160 |
Tig | +0.152 |
Beet | +0.149 |
metaphor | +0.133 |
Vide | +0.132 |
Neg logit contributions | |
ibaba | -0.182 |
naires | -0.170 |
unin | -0.168 |
ivo | -0.165 |
orsche | -0.165 |
Token | main |
Token ID | 1388 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Line | +0.092 |
Tig | +0.088 |
Beet | +0.086 |
metaphor | +0.079 |
Passive | +0.077 |
Neg logit contributions | |
ibaba | -0.078 |
naires | -0.073 |
unin | -0.071 |
orsche | -0.070 |
naire | -0.070 |
Token | story |
Token ID | 1621 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
ibaba | +0.191 |
naires | +0.181 |
unin | +0.178 |
ivo | +0.175 |
naire | +0.175 |
Neg logit contributions | |
Line | -0.135 |
Tig | -0.128 |
Beet | -0.125 |
metaphor | -0.111 |
Vide | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
Line | +3.316 |
Tig | +3.092 |
Beet | +2.965 |
Vide | +2.680 |
Passive | +2.660 |
Neg logit contributions | |
ibaba | -4.733 |
orsche | -4.331 |
unin | -4.331 |
naires | -4.239 |
ivo | -4.235 |
Token |
|
Token ID | 198 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Line | +0.602 |
Tig | +0.569 |
Beet | +0.555 |
Vide | +0.490 |
Passive | +0.489 |
Neg logit contributions | |
ibaba | -0.744 |
unin | -0.682 |
naires | -0.678 |
orsche | -0.673 |
ivo | -0.668 |
Token | Thus |
Token ID | 19093 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Line | +0.383 |
Tig | +0.364 |
Beet | +0.361 |
metaphor | +0.318 |
Vide | +0.317 |
Neg logit contributions | |
ibaba | -0.438 |
naires | -0.407 |
unin | -0.403 |
ivo | -0.395 |
orsche | -0.392 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ibaba | +1.237 |
naires | +1.172 |
unin | +1.150 |
ivo | +1.130 |
naire | +1.122 |
Neg logit contributions | |
Line | -1.023 |
Beet | -0.979 |
Tig | -0.979 |
metaphor | -0.852 |
Vide | -0.844 |
Token | is |
Token ID | 318 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
Line | +0.189 |
Tig | +0.179 |
Beet | +0.178 |
metaphor | +0.153 |
Vide | +0.151 |
Neg logit contributions | |
ibaba | -0.276 |
naires | -0.261 |
unin | -0.258 |
ivo | -0.254 |
naire | -0.252 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
ibaba | +0.625 |
naires | +0.589 |
unin | +0.581 |
ivo | +0.570 |
naire | +0.565 |
Neg logit contributions | |
Line | -0.533 |
Tig | -0.508 |
Beet | -0.505 |
metaphor | -0.444 |
Vide | -0.439 |
Token | Continue |
Token ID | 10054 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ibaba | +0.589 |
naires | +0.551 |
unin | +0.540 |
naire | +0.527 |
ivo | +0.526 |
Neg logit contributions | |
Line | -0.634 |
Tig | -0.609 |
Beet | -0.602 |
Vide | -0.539 |
metaphor | -0.538 |
Token | reading |
Token ID | 3555 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Line | +0.075 |
Tig | +0.070 |
Beet | +0.069 |
metaphor | +0.057 |
Vide | +0.056 |
Neg logit contributions | |
ibaba | -0.170 |
naires | -0.161 |
unin | -0.160 |
ivo | -0.158 |
orsche | -0.157 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Line | +0.197 |
Tig | +0.188 |
Beet | +0.183 |
metaphor | +0.163 |
Vide | +0.162 |
Neg logit contributions | |
ibaba | -0.229 |
naires | -0.212 |
unin | -0.210 |
orsche | -0.207 |
ivo | -0.206 |
Token | main |
Token ID | 1388 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Line | +0.032 |
Tig | +0.030 |
Beet | +0.029 |
metaphor | +0.027 |
Passive | +0.026 |
Neg logit contributions | |
ibaba | -0.027 |
naires | -0.026 |
unin | -0.025 |
orsche | -0.025 |
naire | -0.025 |
Token | story |
Token ID | 1621 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
Line | +0.148 |
Tig | +0.140 |
Beet | +0.134 |
metaphor | +0.121 |
Vide | +0.116 |
Neg logit contributions | |
ibaba | -0.219 |
naires | -0.207 |
unin | -0.203 |
orsche | -0.201 |
ivo | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Line | +3.274 |
Tig | +3.050 |
Beet | +2.911 |
Vide | +2.632 |
Passive | +2.624 |
Neg logit contributions | |
ibaba | -4.764 |
orsche | -4.359 |
unin | -4.344 |
naires | -4.258 |
ivo | -4.242 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Line | +0.371 |
Tig | +0.351 |
Beet | +0.343 |
Vide | +0.302 |
Passive | +0.302 |
Neg logit contributions | |
ibaba | -0.450 |
unin | -0.414 |
naires | -0.412 |
orsche | -0.407 |
ivo | -0.405 |
Token | In |
Token ID | 818 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Line | +0.013 |
Tig | +0.012 |
Beet | +0.012 |
metaphor | +0.011 |
Vide | +0.011 |
Neg logit contributions | |
ibaba | -0.015 |
naires | -0.014 |
unin | -0.014 |
ivo | -0.014 |
naire | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ibaba | +0.119 |
naires | +0.112 |
unin | +0.111 |
ivo | +0.109 |
naire | +0.108 |
Neg logit contributions | |
Line | -0.091 |
Tig | -0.086 |
Beet | -0.086 |
metaphor | -0.075 |
Vide | -0.074 |
Token | capital |
Token ID | 3139 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ibaba | +0.561 |
naires | +0.531 |
unin | +0.524 |
ivo | +0.515 |
naire | +0.510 |
Neg logit contributions | |
Line | -0.419 |
Beet | -0.397 |
Tig | -0.397 |
metaphor | -0.345 |
Vide | -0.340 |
Token | available |
Token ID | 1695 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Line | +0.181 |
Tig | +0.172 |
Beet | +0.172 |
metaphor | +0.150 |
Vide | +0.148 |
Neg logit contributions | |
ibaba | -0.228 |
naires | -0.215 |
unin | -0.212 |
ivo | -0.208 |
naire | -0.207 |
Token | on |
Token ID | 319 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Line | +1.413 |
Tig | +1.341 |
Beet | +1.336 |
metaphor | +1.182 |
Vide | +1.162 |
Neg logit contributions | |
ibaba | -1.703 |
naires | -1.603 |
unin | -1.583 |
ivo | -1.550 |
naire | -1.546 |
Token | the |
Token ID | 262 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Line | +0.471 |
Tig | +0.448 |
Beet | +0.446 |
metaphor | +0.392 |
Vide | +0.388 |
Neg logit contributions | |
ibaba | -0.562 |
naires | -0.530 |
unin | -0.523 |
ivo | -0.512 |
naire | -0.511 |
Token | BBC |
Token ID | 7823 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Line | +0.369 |
Beet | +0.348 |
Tig | +0.347 |
metaphor | +0.298 |
Vide | +0.297 |
Neg logit contributions | |
ibaba | -0.509 |
naires | -0.485 |
unin | -0.479 |
naire | -0.471 |
ivo | -0.470 |
Token | i |
Token ID | 1312 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Line | +0.356 |
Tig | +0.340 |
Beet | +0.339 |
metaphor | +0.301 |
Vide | +0.297 |
Neg logit contributions | |
ibaba | -0.367 |
naires | -0.345 |
unin | -0.340 |
ivo | -0.334 |
naire | -0.330 |
Token | Player |
Token ID | 14140 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
Line | +1.703 |
Tig | +1.606 |
Beet | +1.605 |
metaphor | +1.380 |
Vide | +1.380 |
Neg logit contributions | |
ibaba | -2.260 |
naires | -2.118 |
unin | -2.090 |
naire | -2.056 |
orsche | -2.040 |
Token | afterwards |
Token ID | 12979 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Line | +3.154 |
Beet | +2.918 |
Tig | +2.918 |
metaphor | +2.524 |
Vide | +2.510 |
Neg logit contributions | |
ibaba | -4.521 |
naires | -4.325 |
unin | -4.235 |
naire | -4.209 |
orsche | -4.191 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Line | +0.616 |
Tig | +0.582 |
Beet | +0.580 |
metaphor | +0.503 |
Vide | +0.497 |
Neg logit contributions | |
ibaba | -0.841 |
naires | -0.795 |
unin | -0.785 |
ivo | -0.770 |
naire | -0.766 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
Line | +0.986 |
Tig | +0.934 |
Beet | +0.932 |
metaphor | +0.816 |
Vide | +0.810 |
Neg logit contributions | |
ibaba | -1.142 |
naires | -1.076 |
unin | -1.061 |
ivo | -1.040 |
naire | -1.035 |
Token | Develop |
Token ID | 19246 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Line | +0.045 |
Tig | +0.043 |
Beet | +0.042 |
metaphor | +0.038 |
Vide | +0.037 |
Neg logit contributions | |
ibaba | -0.050 |
naires | -0.047 |
unin | -0.046 |
ivo | -0.045 |
naire | -0.045 |
Token | ers |
Token ID | 364 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
ibaba | +0.167 |
naires | +0.157 |
unin | +0.155 |
ivo | +0.151 |
naire | +0.150 |
Neg logit contributions | |
Line | -0.163 |
Tig | -0.155 |
Beet | -0.155 |
metaphor | -0.137 |
Vide | -0.136 |
Token | They |
Token ID | 1119 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
Line | +0.338 |
Tig | +0.318 |
Beet | +0.316 |
Vide | +0.268 |
metaphor | +0.268 |
Neg logit contributions | |
ibaba | -0.518 |
naires | -0.489 |
unin | -0.485 |
ivo | -0.476 |
orsche | -0.472 |
Token | also |
Token ID | 635 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Line | +0.545 |
Tig | +0.513 |
Beet | +0.509 |
metaphor | +0.441 |
Vide | +0.432 |
Neg logit contributions | |
ibaba | -0.815 |
naires | -0.771 |
unin | -0.762 |
ivo | -0.749 |
naire | -0.743 |
Token | had |
Token ID | 550 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
ibaba | +0.489 |
naires | +0.463 |
unin | +0.458 |
ivo | +0.450 |
naire | +0.447 |
Neg logit contributions | |
Line | -0.341 |
Tig | -0.323 |
Beet | -0.322 |
metaphor | -0.277 |
Vide | -0.274 |
Token | to |
Token ID | 284 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Line | +0.404 |
Tig | +0.384 |
Beet | +0.382 |
metaphor | +0.334 |
Vide | +0.331 |
Neg logit contributions | |
ibaba | -0.491 |
naires | -0.463 |
unin | -0.457 |
ivo | -0.449 |
naire | -0.445 |
Token | give |
Token ID | 1577 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
ibaba | +0.338 |
naires | +0.318 |
unin | +0.313 |
ivo | +0.306 |
orsche | +0.304 |
Neg logit contributions | |
Line | -0.280 |
Tig | -0.265 |
Beet | -0.263 |
metaphor | -0.233 |
Vide | -0.228 |
Token | up |
Token ID | 510 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
Line | +0.384 |
Tig | +0.363 |
Beet | +0.360 |
metaphor | +0.310 |
Vide | +0.307 |
Neg logit contributions | |
ibaba | -0.571 |
naires | -0.541 |
unin | -0.534 |
ivo | -0.525 |
naire | -0.522 |
Token | their |
Token ID | 511 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Line | +3.427 |
Tig | +3.265 |
Beet | +3.175 |
Vide | +2.811 |
metaphor | +2.773 |
Neg logit contributions | |
ibaba | -4.252 |
naires | -4.015 |
unin | -3.958 |
orsche | -3.842 |
ivo | -3.834 |
Token | top |
Token ID | 1353 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Line | +1.255 |
Tig | +1.188 |
Beet | +1.174 |
metaphor | +1.038 |
Vide | +1.022 |
Neg logit contributions | |
ibaba | -1.513 |
naires | -1.418 |
unin | -1.394 |
ivo | -1.371 |
orsche | -1.353 |
Token | pitching |
Token ID | 21088 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ibaba | +0.356 |
naires | +0.336 |
unin | +0.332 |
ivo | +0.326 |
naire | +0.323 |
Neg logit contributions | |
Line | -0.286 |
Tig | -0.271 |
Beet | -0.269 |
metaphor | -0.236 |
Vide | -0.233 |
Token | prospect |
Token ID | 6034 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Line | +0.146 |
Tig | +0.138 |
Beet | +0.136 |
metaphor | +0.120 |
Vide | +0.118 |
Neg logit contributions | |
ibaba | -0.181 |
naires | -0.171 |
unin | -0.167 |
ivo | -0.166 |
orsche | -0.164 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ibaba | +1.145 |
naires | +1.081 |
unin | +1.068 |
ivo | +1.048 |
naire | +1.041 |
Neg logit contributions | |
Line | -0.907 |
Tig | -0.862 |
Beet | -0.861 |
metaphor | -0.752 |
Vide | -0.741 |
Token | or |
Token ID | 393 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Line | +0.178 |
Tig | +0.169 |
Beet | +0.168 |
metaphor | +0.147 |
Vide | +0.145 |
Neg logit contributions | |
ibaba | -0.235 |
naires | -0.222 |
unin | -0.219 |
ivo | -0.215 |
naire | -0.213 |
Token | ed |
Token ID | 1225 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Line | +1.799 |
Tig | +1.722 |
Beet | +1.716 |
metaphor | +1.531 |
Vide | +1.505 |
Neg logit contributions | |
ibaba | -1.935 |
naires | -1.819 |
unin | -1.815 |
ivo | -1.770 |
orsche | -1.759 |
Token | raper |
Token ID | 38545 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Line | +1.758 |
Tig | +1.648 |
Beet | +1.607 |
wart | +1.581 |
xt | +1.561 |
Neg logit contributions | |
ibaba | -1.238 |
naires | -1.236 |
naire | -1.198 |
orsche | -1.186 |
unin | -1.159 |
Token | @ |
Token ID | 31 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
Line | +1.046 |
Tig | +0.993 |
Beet | +0.977 |
metaphor | +0.886 |
Vide | +0.881 |
Neg logit contributions | |
ibaba | -0.896 |
naires | -0.831 |
unin | -0.820 |
ivo | -0.792 |
naire | -0.787 |
Token | den |
Token ID | 6559 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Line | +0.625 |
Tig | +0.589 |
Beet | +0.579 |
Vide | +0.511 |
metaphor | +0.510 |
Neg logit contributions | |
ibaba | -0.850 |
naires | -0.805 |
unin | -0.787 |
naire | -0.779 |
ivo | -0.770 |
Token | ver |
Token ID | 332 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
ibaba | +1.452 |
naires | +1.368 |
unin | +1.351 |
ivo | +1.338 |
naire | +1.321 |
Neg logit contributions | |
Line | -1.039 |
Beet | -1.000 |
Tig | -0.994 |
metaphor | -0.852 |
Passive | -0.849 |
Token | post |
Token ID | 7353 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Line | +3.301 |
Tig | +3.069 |
Beet | +2.897 |
Vide | +2.715 |
wart | +2.657 |
Neg logit contributions | |
ibaba | -4.244 |
naires | -4.045 |
orsche | -3.937 |
ivo | -3.877 |
unin | -3.848 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Line | +1.076 |
Tig | +1.002 |
Beet | +0.979 |
metaphor | +0.840 |
Vide | +0.836 |
Neg logit contributions | |
ibaba | -1.756 |
naires | -1.648 |
unin | -1.639 |
orsche | -1.613 |
ivo | -1.605 |
Token | com |
Token ID | 785 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Line | +0.160 |
Tig | +0.154 |
Beet | +0.154 |
metaphor | +0.141 |
Vide | +0.140 |
Neg logit contributions | |
ibaba | -0.088 |
naires | -0.080 |
unin | -0.078 |
ivo | -0.076 |
naire | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Line | +0.482 |
Tig | +0.461 |
Beet | +0.460 |
metaphor | +0.406 |
Vide | +0.400 |
Neg logit contributions | |
ibaba | -0.527 |
naires | -0.494 |
unin | -0.488 |
ivo | -0.479 |
naire | -0.475 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Line | +1.111 |
Tig | +1.048 |
Beet | +1.025 |
metaphor | +0.905 |
Vide | +0.903 |
Neg logit contributions | |
ibaba | -1.366 |
unin | -1.252 |
naires | -1.251 |
orsche | -1.234 |
ivo | -1.228 |
Token | disp |
Token ID | 4596 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ibaba | +0.166 |
naires | +0.156 |
unin | +0.154 |
ivo | +0.151 |
naire | +0.149 |
Neg logit contributions | |
Line | -0.157 |
Tig | -0.149 |
Beet | -0.149 |
metaphor | -0.132 |
Vide | -0.130 |
Token | ersion |
Token ID | 6900 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
ibaba | +0.171 |
naires | +0.161 |
unin | +0.158 |
ivo | +0.155 |
naire | +0.154 |
Neg logit contributions | |
Line | -0.170 |
Tig | -0.162 |
Beet | -0.162 |
metaphor | -0.144 |
Vide | -0.142 |
Token | as |
Token ID | 355 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ibaba | +0.024 |
naires | +0.023 |
unin | +0.022 |
ivo | +0.022 |
naire | +0.022 |
Neg logit contributions | |
Line | -0.024 |
Tig | -0.023 |
Beet | -0.022 |
metaphor | -0.020 |
Vide | -0.020 |
Token | such |
Token ID | 884 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Line | +0.089 |
Tig | +0.085 |
Beet | +0.084 |
metaphor | +0.074 |
Vide | +0.073 |
Neg logit contributions | |
ibaba | -0.105 |
naires | -0.099 |
unin | -0.097 |
ivo | -0.095 |
naire | -0.095 |
Token | ! |
Token ID | 0 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ibaba | +0.145 |
naires | +0.137 |
unin | +0.135 |
ivo | +0.132 |
naire | +0.131 |
Neg logit contributions | |
Line | -0.135 |
Tig | -0.129 |
Beet | -0.128 |
metaphor | -0.113 |
Vide | -0.112 |
Token | Ont |
Token ID | 45984 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Line | +0.211 |
Tig | +0.200 |
Beet | +0.199 |
metaphor | +0.174 |
Vide | +0.172 |
Neg logit contributions | |
ibaba | -0.262 |
naires | -0.247 |
unin | -0.244 |
ivo | -0.240 |
naire | -0.238 |
Token | ology |
Token ID | 1435 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Line | +3.421 |
Tig | +3.228 |
Beet | +3.160 |
metaphor | +2.851 |
Vide | +2.769 |
Neg logit contributions | |
ibaba | -4.031 |
naires | -3.775 |
unin | -3.744 |
ivo | -3.668 |
orsche | -3.650 |
Token | returned |
Token ID | 4504 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Line | +0.422 |
Tig | +0.401 |
Beet | +0.399 |
metaphor | +0.350 |
Vide | +0.344 |
Neg logit contributions | |
ibaba | -0.529 |
naires | -0.499 |
unin | -0.493 |
ivo | -0.484 |
naire | -0.480 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ibaba | +0.562 |
naires | +0.530 |
unin | +0.523 |
ivo | +0.514 |
naire | +0.509 |
Neg logit contributions | |
Line | -0.477 |
Tig | -0.454 |
Beet | -0.453 |
metaphor | -0.397 |
Vide | -0.393 |
Token | the |
Token ID | 262 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Line | +0.111 |
Tig | +0.106 |
Beet | +0.106 |
metaphor | +0.093 |
Vide | +0.092 |
Neg logit contributions | |
ibaba | -0.129 |
naires | -0.121 |
unin | -0.120 |
ivo | -0.117 |
naire | -0.116 |
Token | Meg |
Token ID | 8336 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Line | +0.505 |
Tig | +0.480 |
Beet | +0.477 |
metaphor | +0.418 |
Passive | +0.410 |
Neg logit contributions | |
ibaba | -0.636 |
naires | -0.600 |
unin | -0.592 |
ivo | -0.583 |
naire | -0.578 |
Token | olla |
Token ID | 33011 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
Line | +0.671 |
Tig | +0.623 |
Beet | +0.609 |
metaphor | +0.518 |
wart | +0.504 |
Neg logit contributions | |
ibaba | -1.289 |
naires | -1.230 |
unin | -1.205 |
naire | -1.193 |
humane | -1.184 |
Token | shared |
Token ID | 4888 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Line | +0.575 |
Tig | +0.540 |
Beet | +0.535 |
metaphor | +0.464 |
Vide | +0.457 |
Neg logit contributions | |
ibaba | -0.849 |
naires | -0.803 |
unin | -0.794 |
ivo | -0.780 |
naire | -0.774 |
Token | this |
Token ID | 428 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Line | +0.412 |
Tig | +0.392 |
Beet | +0.389 |
metaphor | +0.344 |
Vide | +0.340 |
Neg logit contributions | |
ibaba | -0.494 |
naires | -0.465 |
unin | -0.460 |
ivo | -0.451 |
orsche | -0.447 |
Token | afterwards |
Token ID | 12979 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Line | +0.740 |
Tig | +0.700 |
Beet | +0.693 |
metaphor | +0.615 |
Vide | +0.603 |
Neg logit contributions | |
ibaba | -0.941 |
naires | -0.890 |
unin | -0.878 |
ivo | -0.863 |
orsche | -0.856 |
Token | ]: |
Token ID | 5974 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
Line | +0.131 |
Tig | +0.124 |
Beet | +0.123 |
metaphor | +0.107 |
Vide | +0.106 |
Neg logit contributions | |
ibaba | -0.176 |
naires | -0.166 |
unin | -0.164 |
ivo | -0.161 |
naire | -0.160 |
Token | J |
Token ID | 41 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Line | +0.562 |
Tig | +0.530 |
Beet | +0.526 |
metaphor | +0.464 |
Vide | +0.458 |
Neg logit contributions | |
ibaba | -0.696 |
naires | -0.658 |
unin | -0.649 |
ivo | -0.635 |
naire | -0.632 |
Token | olla |
Token ID | 33011 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Line | +2.356 |
Tig | +2.110 |
Beet | +1.984 |
metaphor | +1.753 |
wart | +1.733 |
Neg logit contributions | |
ibaba | -5.021 |
naires | -4.856 |
naire | -4.736 |
humane | -4.688 |
unin | -4.651 |
Token | phone |
Token ID | 3072 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Line | +1.479 |
Tig | +1.377 |
Beet | +1.355 |
metaphor | +1.182 |
Vide | +1.173 |
Neg logit contributions | |
ibaba | -2.171 |
naires | -2.057 |
unin | -2.033 |
ivo | -1.989 |
humane | -1.982 |
Token | 's |
Token ID | 338 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Line | +1.015 |
Tig | +0.951 |
Beet | +0.939 |
metaphor | +0.828 |
Vide | +0.815 |
Neg logit contributions | |
ibaba | -1.335 |
naires | -1.265 |
unin | -1.248 |
ivo | -1.219 |
naire | -1.218 |
Token | back |
Token ID | 736 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Line | +1.147 |
Tig | +1.082 |
Beet | +1.067 |
metaphor | +0.949 |
Vide | +0.936 |
Neg logit contributions | |
ibaba | -1.341 |
naires | -1.280 |
unin | -1.252 |
naire | -1.226 |
ivo | -1.224 |
Token | cover |
Token ID | 3002 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ibaba | +0.515 |
naires | +0.486 |
unin | +0.479 |
ivo | +0.471 |
naire | +0.467 |
Neg logit contributions | |
Line | -0.429 |
Tig | -0.409 |
Beet | -0.407 |
metaphor | -0.357 |
Vide | -0.353 |
Token | hard |
Token ID | 10424 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
Line | +0.097 |
Tig | +0.092 |
Beet | +0.091 |
metaphor | +0.079 |
Vide | +0.078 |
Neg logit contributions | |
ibaba | -0.133 |
naires | -0.125 |
unin | -0.124 |
ivo | -0.122 |
naire | -0.121 |
Token | attitude |
Token ID | 9408 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Line | +2.099 |
Tig | +1.960 |
Beet | +1.957 |
metaphor | +1.686 |
Vide | +1.645 |
Neg logit contributions | |
ibaba | -3.336 |
unin | -3.128 |
naires | -3.124 |
ivo | -3.039 |
orsche | -3.021 |
Token | to |
Token ID | 284 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
Line | +0.850 |
Tig | +0.806 |
Beet | +0.799 |
metaphor | +0.698 |
Vide | +0.684 |
Neg logit contributions | |
ibaba | -1.131 |
naires | -1.064 |
unin | -1.056 |
ivo | -1.033 |
orsche | -1.026 |
Token | never |
Token ID | 1239 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
Line | +0.018 |
Tig | +0.018 |
Beet | +0.017 |
metaphor | +0.015 |
Vide | +0.015 |
Neg logit contributions | |
ibaba | -0.022 |
naires | -0.021 |
unin | -0.021 |
ivo | -0.021 |
naire | -0.020 |
Token | give |
Token ID | 1577 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ibaba | +0.001 |
naires | +0.001 |
unin | +0.001 |
ivo | +0.001 |
naire | +0.001 |
Neg logit contributions | |
Line | -0.001 |
Tig | -0.001 |
Beet | -0.001 |
metaphor | -0.001 |
Vide | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ibaba | +0.325 |
naires | +0.308 |
unin | +0.304 |
ivo | +0.299 |
naire | +0.297 |
Neg logit contributions | |
Line | -0.220 |
Tig | -0.208 |
Beet | -0.207 |
metaphor | -0.179 |
Vide | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Line | +2.958 |
Tig | +2.782 |
Beet | +2.723 |
metaphor | +2.403 |
Vide | +2.326 |
Neg logit contributions | |
ibaba | -4.413 |
naires | -4.196 |
unin | -4.168 |
orsche | -4.071 |
ivo | -4.055 |
Token | If |
Token ID | 1002 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Line | +0.432 |
Tig | +0.408 |
Beet | +0.406 |
metaphor | +0.347 |
Vide | +0.340 |
Neg logit contributions | |
ibaba | -0.699 |
naires | -0.664 |
unin | -0.656 |
ivo | -0.646 |
naire | -0.641 |
Token | I |
Token ID | 314 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ibaba | +0.089 |
naires | +0.084 |
unin | +0.082 |
ivo | +0.081 |
naire | +0.080 |
Neg logit contributions | |
Line | -0.093 |
Tig | -0.089 |
Beet | -0.089 |
metaphor | -0.079 |
Vide | -0.078 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ibaba | +0.517 |
naires | +0.493 |
unin | +0.485 |
ivo | +0.477 |
naire | +0.475 |
Neg logit contributions | |
Line | -0.390 |
Beet | -0.371 |
Tig | -0.371 |
metaphor | -0.319 |
Vide | -0.317 |
Token | up |
Token ID | 510 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
ibaba | +0.012 |
naires | +0.011 |
unin | +0.011 |
ivo | +0.011 |
naire | +0.011 |
Neg logit contributions | |
Line | -0.008 |
Tig | -0.008 |
Beet | -0.008 |
metaphor | -0.007 |
Vide | -0.006 |
Token | conserv |
Token ID | 4055 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
ibaba | +0.838 |
naires | +0.789 |
unin | +0.780 |
ivo | +0.765 |
naire | +0.758 |
Neg logit contributions | |
Line | -0.709 |
Tig | -0.675 |
Beet | -0.671 |
metaphor | -0.590 |
Vide | -0.583 |
Token | ator |
Token ID | 1352 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
ibaba | +0.741 |
naires | +0.704 |
unin | +0.696 |
ivo | +0.683 |
naire | +0.679 |
Neg logit contributions | |
Line | -0.453 |
Tig | -0.427 |
Beet | -0.424 |
metaphor | -0.362 |
Vide | -0.356 |
Token | of |
Token ID | 286 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ibaba | +2.534 |
naires | +2.408 |
unin | +2.354 |
ivo | +2.338 |
naire | +2.321 |
Neg logit contributions | |
Line | -2.371 |
Beet | -2.270 |
Tig | -2.242 |
metaphor | -1.984 |
Passive | -1.980 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
ibaba | +1.285 |
naires | +1.208 |
unin | +1.191 |
ivo | +1.168 |
naire | +1.158 |
Neg logit contributions | |
Line | -1.182 |
Tig | -1.127 |
Beet | -1.123 |
metaphor | -0.993 |
Vide | -0.981 |
Token | Mur |
Token ID | 5921 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ibaba | +0.799 |
naires | +0.749 |
unin | +0.742 |
ivo | +0.726 |
naire | +0.719 |
Neg logit contributions | |
Line | -0.717 |
Tig | -0.683 |
Beet | -0.680 |
metaphor | -0.601 |
Vide | -0.594 |
Token | to |
Token ID | 1462 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
Line | +0.776 |
Tig | +0.734 |
Beet | +0.730 |
metaphor | +0.643 |
Vide | +0.636 |
Neg logit contributions | |
ibaba | -0.868 |
naires | -0.823 |
unin | -0.807 |
naire | -0.787 |
ivo | -0.787 |
Token | gh |
Token ID | 456 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Line | +3.625 |
Tig | +3.456 |
Beet | +3.430 |
Vide | +3.028 |
metaphor | +2.986 |
Neg logit contributions | |
ibaba | -3.703 |
naires | -3.493 |
unin | -3.467 |
naire | -3.335 |
ivo | -3.332 |
Token | D |
Token ID | 360 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ibaba | +0.311 |
naires | +0.293 |
unin | +0.289 |
ivo | +0.283 |
naire | +0.281 |
Neg logit contributions | |
Line | -0.285 |
Tig | -0.272 |
Beet | -0.271 |
metaphor | -0.240 |
Vide | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Line | +0.082 |
Tig | +0.078 |
Beet | +0.078 |
metaphor | +0.069 |
Vide | +0.068 |
Neg logit contributions | |
ibaba | -0.077 |
naires | -0.072 |
unin | -0.071 |
ivo | -0.070 |
naire | -0.069 |
Token | Guinness |
Token ID | 41559 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ibaba | +2.138 |
naires | +2.015 |
unin | +1.979 |
ivo | +1.964 |
orsche | +1.943 |
Neg logit contributions | |
Line | -1.682 |
Tig | -1.600 |
Beet | -1.599 |
metaphor | -1.415 |
polarized | -1.387 |
Token | Collection |
Token ID | 12251 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Line | +0.705 |
Tig | +0.672 |
Beet | +0.671 |
metaphor | +0.595 |
Vide | +0.591 |
Neg logit contributions | |
ibaba | -0.687 |
naires | -0.642 |
unin | -0.637 |
ivo | -0.619 |
naire | -0.614 |
Token | That |
Token ID | 1320 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
Line | +0.159 |
Tig | +0.150 |
Beet | +0.149 |
metaphor | +0.128 |
polarized | +0.125 |
Neg logit contributions | |
ibaba | -0.260 |
naires | -0.247 |
unin | -0.244 |
ivo | -0.240 |
naire | -0.239 |
Token | was |
Token ID | 373 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Line | +0.378 |
Tig | +0.357 |
Beet | +0.356 |
metaphor | +0.307 |
Vide | +0.302 |
Neg logit contributions | |
ibaba | -0.554 |
naires | -0.525 |
unin | -0.519 |
ivo | -0.511 |
naire | -0.507 |
Token | just |
Token ID | 655 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Line | +0.123 |
Tig | +0.117 |
Beet | +0.116 |
metaphor | +0.102 |
Vide | +0.100 |
Neg logit contributions | |
ibaba | -0.157 |
naires | -0.148 |
unin | -0.147 |
ivo | -0.144 |
naire | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +6.39e-03 |
Pos logit contributions | |
ibaba | +0.393 |
naires | +0.371 |
unin | +0.367 |
ivo | +0.361 |
naire | +0.357 |
Neg logit contributions | |
Line | -0.327 |
Tig | -0.311 |
Beet | -0.309 |
metaphor | -0.272 |
Vide | -0.267 |
Token | second |
Token ID | 1218 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ibaba | +0.005 |
naires | +0.005 |
unin | +0.005 |
ivo | +0.005 |
orsche | +0.005 |
Neg logit contributions | |
Line | -0.005 |
Tig | -0.004 |
Beet | -0.004 |
metaphor | -0.004 |
Passive | -0.004 |
Token | time |
Token ID | 640 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
ibaba | +0.619 |
naires | +0.590 |
unin | +0.583 |
ivo | +0.575 |
naire | +0.571 |
Neg logit contributions | |
Line | -0.317 |
Tig | -0.297 |
Beet | -0.295 |
metaphor | -0.246 |
Vide | -0.241 |
Token | Manning |
Token ID | 15281 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Line | +3.008 |
Tig | +2.855 |
Beet | +2.752 |
metaphor | +2.410 |
Vide | +2.377 |
Neg logit contributions | |
ibaba | -4.370 |
unin | -4.128 |
naires | -4.126 |
orsche | -4.009 |
naire | -3.987 |
Token | has |
Token ID | 468 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Line | +0.714 |
Tig | +0.670 |
Beet | +0.658 |
metaphor | +0.560 |
polarized | +0.550 |
Neg logit contributions | |
ibaba | -1.241 |
naires | -1.171 |
unin | -1.164 |
ivo | -1.140 |
orsche | -1.137 |
Token | scored |
Token ID | 7781 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Line | +1.072 |
Tig | +1.008 |
Beet | +0.993 |
metaphor | +0.859 |
polarized | +0.844 |
Neg logit contributions | |
ibaba | -1.635 |
naires | -1.538 |
unin | -1.525 |
ivo | -1.494 |
naire | -1.487 |
Token | more |
Token ID | 517 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Line | +1.828 |
Tig | +1.731 |
Beet | +1.688 |
metaphor | +1.510 |
Passive | +1.478 |
Neg logit contributions | |
ibaba | -2.140 |
unin | -2.026 |
naires | -2.022 |
ivo | -1.959 |
orsche | -1.951 |
Token | than |
Token ID | 621 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Line | +1.228 |
Tig | +1.146 |
Beet | +1.129 |
metaphor | +0.961 |
Passive | +0.941 |
Neg logit contributions | |
ibaba | -2.124 |
naires | -2.021 |
unin | -2.017 |
ivo | -1.963 |
orsche | -1.957 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ibaba | +0.532 |
naires | +0.503 |
unin | +0.496 |
ivo | +0.487 |
naire | +0.483 |
Neg logit contributions | |
Line | -0.444 |
Tig | -0.422 |
Beet | -0.422 |
metaphor | -0.370 |
Vide | -0.364 |
Token | Continue |
Token ID | 10054 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ibaba | +0.615 |
naires | +0.571 |
unin | +0.564 |
ivo | +0.548 |
naire | +0.544 |
Neg logit contributions | |
Line | -0.696 |
Tig | -0.667 |
Beet | -0.661 |
metaphor | -0.594 |
Vide | -0.592 |
Token | reading |
Token ID | 3555 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ibaba | +0.115 |
naires | +0.109 |
unin | +0.108 |
ivo | +0.107 |
orsche | +0.106 |
Neg logit contributions | |
Line | -0.052 |
Tig | -0.048 |
Beet | -0.047 |
metaphor | -0.039 |
Vide | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ibaba | +0.082 |
naires | +0.076 |
unin | +0.075 |
orsche | +0.074 |
ivo | +0.074 |
Neg logit contributions | |
Line | -0.072 |
Tig | -0.069 |
Beet | -0.067 |
metaphor | -0.060 |
Vide | -0.060 |
Token | main |
Token ID | 1388 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Line | +0.197 |
Tig | +0.189 |
Beet | +0.182 |
metaphor | +0.169 |
polarized | +0.165 |
Neg logit contributions | |
ibaba | -0.175 |
naires | -0.162 |
unin | -0.161 |
orsche | -0.158 |
ivo | -0.157 |
Token | story |
Token ID | 1621 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
Line | +0.084 |
Tig | +0.080 |
Beet | +0.077 |
metaphor | +0.070 |
Vide | +0.067 |
Neg logit contributions | |
ibaba | -0.119 |
naires | -0.112 |
unin | -0.110 |
ivo | -0.109 |
orsche | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Line | +3.120 |
Tig | +2.917 |
Beet | +2.765 |
Vide | +2.489 |
Passive | +2.489 |
Neg logit contributions | |
ibaba | -4.475 |
orsche | -4.073 |
unin | -4.051 |
naires | -3.968 |
ivo | -3.953 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Line | +0.675 |
Tig | +0.638 |
Beet | +0.621 |
Vide | +0.548 |
metaphor | +0.548 |
Neg logit contributions | |
ibaba | -0.843 |
unin | -0.773 |
naires | -0.769 |
orsche | -0.764 |
ivo | -0.758 |
Token | Although |
Token ID | 7003 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Line | +0.274 |
Tig | +0.261 |
Beet | +0.259 |
metaphor | +0.228 |
Vide | +0.226 |
Neg logit contributions | |
ibaba | -0.316 |
naires | -0.296 |
unin | -0.293 |
ivo | -0.287 |
naire | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
ibaba | +1.300 |
naires | +1.239 |
unin | +1.212 |
ivo | +1.193 |
naire | +1.185 |
Neg logit contributions | |
Line | -1.041 |
Beet | -0.997 |
Tig | -0.988 |
metaphor | -0.866 |
Passive | -0.855 |
Token | mar |
Token ID | 1667 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ibaba | +0.638 |
naires | +0.609 |
unin | +0.600 |
ivo | +0.591 |
naire | +0.586 |
Neg logit contributions | |
Line | -0.385 |
Beet | -0.365 |
Tig | -0.361 |
metaphor | -0.307 |
Vide | -0.302 |
Token | no |
Token ID | 645 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Line | +0.096 |
Tig | +0.091 |
Beet | +0.090 |
metaphor | +0.080 |
polarized | +0.079 |
Neg logit contributions | |
ibaba | -0.109 |
naires | -0.103 |
unin | -0.101 |
ivo | -0.099 |
orsche | -0.099 |
Token | one |
Token ID | 530 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Line | +0.967 |
Tig | +0.919 |
Beet | +0.905 |
metaphor | +0.805 |
polarized | +0.784 |
Neg logit contributions | |
ibaba | -1.279 |
naires | -1.203 |
unin | -1.189 |
ivo | -1.169 |
naire | -1.159 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ibaba | +0.483 |
naires | +0.461 |
unin | +0.456 |
ivo | +0.448 |
naire | +0.446 |
Neg logit contributions | |
Line | -0.278 |
Beet | -0.264 |
Tig | -0.263 |
Vide | -0.219 |
metaphor | -0.217 |
Token | wiser |
Token ID | 47897 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Line | +0.636 |
Tig | +0.593 |
Beet | +0.589 |
metaphor | +0.501 |
polarized | +0.486 |
Neg logit contributions | |
ibaba | -1.200 |
naires | -1.143 |
unin | -1.124 |
ivo | -1.110 |
naire | -1.099 |
Token | . |
Token ID | 13 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Line | +0.440 |
Tig | +0.418 |
Beet | +0.417 |
metaphor | +0.362 |
Vide | +0.358 |
Neg logit contributions | |
ibaba | -0.570 |
naires | -0.540 |
unin | -0.532 |
ivo | -0.523 |
naire | -0.519 |
Token | Furthermore |
Token ID | 24951 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
Line | +0.415 |
Tig | +0.393 |
Beet | +0.390 |
metaphor | +0.337 |
Vide | +0.336 |
Neg logit contributions | |
ibaba | -0.559 |
naires | -0.526 |
unin | -0.521 |
ivo | -0.511 |
orsche | -0.507 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Line | +2.915 |
Tig | +2.731 |
Beet | +2.683 |
metaphor | +2.358 |
polarized | +2.308 |
Neg logit contributions | |
ibaba | -4.341 |
naires | -4.115 |
unin | -4.047 |
ivo | -4.011 |
naire | -3.980 |
Token | what |
Token ID | 644 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Line | +1.082 |
Tig | +1.029 |
Beet | +1.013 |
metaphor | +0.901 |
polarized | +0.884 |
Neg logit contributions | |
ibaba | -1.315 |
naires | -1.241 |
unin | -1.221 |
ivo | -1.208 |
naire | -1.197 |
Token | these |
Token ID | 777 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Line | +0.439 |
Tig | +0.418 |
Beet | +0.413 |
metaphor | +0.363 |
polarized | +0.355 |
Neg logit contributions | |
ibaba | -0.588 |
naires | -0.552 |
unin | -0.547 |
ivo | -0.540 |
orsche | -0.533 |
Token | theorists |
Token ID | 33142 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Line | +1.784 |
Tig | +1.694 |
Beet | +1.673 |
metaphor | +1.494 |
polarized | +1.474 |
Neg logit contributions | |
ibaba | -2.174 |
naires | -2.011 |
unin | -2.002 |
ivo | -1.976 |
orsche | -1.963 |
Token | ignore |
Token ID | 8856 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Line | +0.396 |
Tig | +0.372 |
Beet | +0.369 |
metaphor | +0.317 |
Vide | +0.309 |
Neg logit contributions | |
ibaba | -0.661 |
naires | -0.626 |
unin | -0.620 |
ivo | -0.610 |
naire | -0.605 |
Token | < |
Token ID | 1279 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ibaba | +0.627 |
naires | +0.573 |
unin | +0.560 |
ivo | +0.545 |
naire | +0.538 |
Neg logit contributions | |
Line | -1.109 |
Tig | -1.072 |
Beet | -1.069 |
metaphor | -0.976 |
Vide | -0.969 |
Token | m |
Token ID | 76 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ibaba | +1.402 |
naires | +1.316 |
unin | +1.303 |
ivo | +1.274 |
naire | +1.262 |
Neg logit contributions | |
Line | -1.361 |
Tig | -1.299 |
Beet | -1.296 |
metaphor | -1.148 |
Vide | -1.136 |
Token | ik |
Token ID | 1134 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ibaba | +1.230 |
naires | +1.154 |
unin | +1.141 |
ivo | +1.119 |
naire | +1.108 |
Neg logit contributions | |
Line | -1.149 |
Tig | -1.097 |
Beet | -1.094 |
metaphor | -0.969 |
Vide | -0.957 |
Token | et |
Token ID | 316 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ibaba | +0.435 |
naires | +0.409 |
unin | +0.401 |
ivo | +0.393 |
naire | +0.390 |
Neg logit contributions | |
Line | -0.441 |
Tig | -0.421 |
Beet | -0.419 |
metaphor | -0.374 |
Vide | -0.369 |
Token | hem |
Token ID | 4411 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Line | +0.406 |
Tig | +0.388 |
Beet | +0.386 |
metaphor | +0.344 |
wart | +0.340 |
Neg logit contributions | |
ibaba | -0.418 |
naires | -0.396 |
unin | -0.386 |
naire | -0.378 |
ivo | -0.377 |
Token | ad |
Token ID | 324 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ibaba | +0.141 |
naires | +0.132 |
unin | +0.130 |
ivo | +0.128 |
naire | +0.127 |
Neg logit contributions | |
Line | -0.132 |
Tig | -0.126 |
Beet | -0.126 |
metaphor | -0.111 |
Vide | -0.110 |
Token | man |
Token ID | 805 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ibaba | +2.676 |
naires | +2.481 |
unin | +2.462 |
ivo | +2.430 |
naire | +2.391 |
Neg logit contributions | |
Line | -2.457 |
Tig | -2.360 |
Beet | -2.353 |
metaphor | -2.063 |
Vide | -2.054 |
Token | 1 |
Token ID | 16 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ibaba | +1.340 |
naires | +1.259 |
unin | +1.232 |
ivo | +1.218 |
naire | +1.207 |
Neg logit contributions | |
Line | -1.447 |
Tig | -1.396 |
Beet | -1.396 |
metaphor | -1.245 |
Vide | -1.232 |
Token | > |
Token ID | 29 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ibaba | +0.415 |
naires | +0.389 |
unin | +0.383 |
ivo | +0.376 |
naire | +0.372 |
Neg logit contributions | |
Line | -0.439 |
Tig | -0.422 |
Beet | -0.420 |
metaphor | -0.376 |
Vide | -0.371 |
Token | lol |
Token ID | 19462 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ibaba | +2.075 |
naires | +1.953 |
unin | +1.921 |
ivo | +1.884 |
naire | +1.874 |
Neg logit contributions | |
Line | -1.842 |
Tig | -1.757 |
Beet | -1.756 |
metaphor | -1.542 |
Vide | -1.526 |
Token | y |
Token ID | 331 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ibaba | +1.213 |
naires | +1.136 |
unin | +1.117 |
ivo | +1.094 |
naire | +1.088 |
Neg logit contributions | |
Line | -1.264 |
Tig | -1.207 |
Beet | -1.207 |
metaphor | -1.071 |
Vide | -1.063 |
Token | 4 |
Token ID | 19 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ibaba | +0.334 |
naires | +0.315 |
unin | +0.310 |
naire | +0.303 |
ivo | +0.302 |
Neg logit contributions | |
Line | -0.279 |
Tig | -0.265 |
Beet | -0.262 |
metaphor | -0.230 |
Vide | -0.229 |
Token | { |
Token ID | 1391 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ibaba | +1.657 |
naires | +1.551 |
unin | +1.526 |
ivo | +1.500 |
naire | +1.482 |
Neg logit contributions | |
Line | -1.742 |
Tig | -1.671 |
Beet | -1.664 |
metaphor | -1.489 |
Vide | -1.467 |
Token | ( |
Token ID | 7 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ibaba | +0.154 |
naires | +0.140 |
unin | +0.139 |
orsche | +0.136 |
ivo | +0.135 |
Neg logit contributions | |
Line | -0.203 |
Tig | -0.194 |
Beet | -0.192 |
metaphor | -0.174 |
Passive | -0.173 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ibaba | +0.348 |
naires | +0.326 |
unin | +0.322 |
ivo | +0.316 |
naire | +0.313 |
Neg logit contributions | |
Line | -0.324 |
Tig | -0.309 |
Beet | -0.307 |
metaphor | -0.272 |
Vide | -0.269 |
Token | s |
Token ID | 82 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ibaba | +0.892 |
naires | +0.836 |
unin | +0.823 |
ivo | +0.807 |
naire | +0.799 |
Neg logit contributions | |
Line | -0.935 |
Tig | -0.896 |
Beet | -0.893 |
metaphor | -0.797 |
Vide | -0.788 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Line | +0.608 |
Tig | +0.552 |
Beet | +0.544 |
metaphor | +0.447 |
Passive | +0.441 |
Neg logit contributions | |
ibaba | -1.368 |
naires | -1.298 |
unin | -1.288 |
orsche | -1.271 |
ivo | -1.270 |
Token | Ng |
Token ID | 34786 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ibaba | +2.430 |
naires | +2.293 |
unin | +2.250 |
ivo | +2.218 |
naire | +2.202 |
Neg logit contributions | |
Line | -2.088 |
Tig | -1.990 |
Beet | -1.984 |
metaphor | -1.755 |
Vide | -1.722 |
Token | 6 |
Token ID | 21 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ibaba | +1.360 |
naires | +1.279 |
unin | +1.262 |
ivo | +1.238 |
naire | +1.227 |
Neg logit contributions | |
Line | -1.233 |
Tig | -1.176 |
Beet | -1.171 |
metaphor | -1.035 |
Vide | -1.022 |
Token | { |
Token ID | 1391 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ibaba | +0.705 |
naires | +0.657 |
unin | +0.651 |
ivo | +0.637 |
orsche | +0.631 |
Neg logit contributions | |
Line | -0.686 |
Tig | -0.654 |
Beet | -0.649 |
metaphor | -0.575 |
Passive | -0.572 |
Token | ( |
Token ID | 7 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ibaba | +0.191 |
naires | +0.173 |
unin | +0.172 |
orsche | +0.168 |
ivo | +0.167 |
Neg logit contributions | |
Line | -0.251 |
Tig | -0.240 |
Beet | -0.237 |
metaphor | -0.215 |
Passive | -0.214 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ibaba | +0.148 |
naires | +0.138 |
unin | +0.137 |
ivo | +0.134 |
naire | +0.133 |
Neg logit contributions | |
Line | -0.141 |
Tig | -0.134 |
Beet | -0.134 |
metaphor | -0.118 |
Vide | -0.117 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ibaba | +0.747 |
naires | +0.706 |
unin | +0.697 |
ivo | +0.684 |
naire | +0.679 |
Neg logit contributions | |
Line | -0.579 |
Tig | -0.550 |
Beet | -0.547 |
metaphor | -0.477 |
Vide | -0.471 |
Token | { |
Token ID | 1391 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
ibaba | +1.100 |
naires | +1.028 |
unin | +1.005 |
ivo | +0.992 |
naire | +0.981 |
Neg logit contributions | |
Line | -1.226 |
Tig | -1.189 |
Beet | -1.180 |
metaphor | -1.062 |
polarized | -1.045 |
Token | ( |
Token ID | 7 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ibaba | +0.522 |
naires | +0.477 |
unin | +0.472 |
ivo | +0.458 |
orsche | +0.457 |
Neg logit contributions | |
Line | -0.714 |
Tig | -0.685 |
Beet | -0.679 |
metaphor | -0.616 |
Vide | -0.611 |
Token | 4 |
Token ID | 19 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ibaba | +0.590 |
naires | +0.554 |
unin | +0.546 |
ivo | +0.535 |
naire | +0.530 |
Neg logit contributions | |
Line | -0.570 |
Tig | -0.544 |
Beet | -0.542 |
metaphor | -0.481 |
Vide | -0.475 |
Token | s |
Token ID | 82 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ibaba | +0.617 |
naires | +0.583 |
unin | +0.575 |
ivo | +0.565 |
naire | +0.559 |
Neg logit contributions | |
Line | -0.510 |
Tig | -0.487 |
Beet | -0.485 |
metaphor | -0.427 |
Vide | -0.421 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Line | +0.738 |
Tig | +0.672 |
Beet | +0.662 |
metaphor | +0.542 |
Passive | +0.535 |
Neg logit contributions | |
ibaba | -1.677 |
naires | -1.588 |
unin | -1.576 |
orsche | -1.554 |
ivo | -1.552 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ibaba | +3.048 |
naires | +2.877 |
unin | +2.811 |
ivo | +2.795 |
naire | +2.777 |
Neg logit contributions | |
Line | -1.910 |
Tig | -1.825 |
Beet | -1.823 |
polarized | -1.560 |
metaphor | -1.551 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ibaba | +2.027 |
naires | +1.940 |
unin | +1.904 |
ivo | +1.875 |
naire | +1.867 |
Neg logit contributions | |
Line | -1.464 |
Beet | -1.396 |
Tig | -1.391 |
metaphor | -1.209 |
polarized | -1.191 |
Token | N |
Token ID | 399 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
ibaba | +0.216 |
naires | +0.203 |
unin | +0.203 |
ivo | +0.197 |
orsche | +0.195 |
Neg logit contributions | |
Line | -0.176 |
Tig | -0.167 |
Beet | -0.166 |
Passive | -0.144 |
Vide | -0.144 |
Token | b |
Token ID | 65 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ibaba | +0.512 |
naires | +0.478 |
unin | +0.469 |
ivo | +0.458 |
naire | +0.456 |
Neg logit contributions | |
Line | -0.573 |
Tig | -0.550 |
Beet | -0.546 |
metaphor | -0.488 |
Vide | -0.485 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
ibaba | +1.336 |
naires | +1.247 |
unin | +1.229 |
naire | +1.201 |
ivo | +1.197 |
Neg logit contributions | |
Line | -1.116 |
Tig | -1.067 |
Beet | -1.054 |
metaphor | -0.923 |
Passive | -0.919 |
Token | Write |
Token ID | 19430 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ibaba | +0.664 |
naires | +0.632 |
unin | +0.622 |
ivo | +0.616 |
orsche | +0.609 |
Neg logit contributions | |
Line | -0.452 |
Tig | -0.434 |
Beet | -0.432 |
metaphor | -0.373 |
Vide | -0.367 |
Token | - |
Token ID | 12 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ibaba | +0.096 |
naires | +0.090 |
unin | +0.089 |
ivo | +0.087 |
orsche | +0.087 |
Neg logit contributions | |
Line | -0.073 |
Tig | -0.069 |
Beet | -0.068 |
metaphor | -0.059 |
Vide | -0.059 |
Token | Warning |
Token ID | 20361 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ibaba | +2.191 |
naires | +2.100 |
unin | +2.064 |
ivo | +2.049 |
humane | +2.016 |
Neg logit contributions | |
Line | -2.105 |
Beet | -2.059 |
Tig | -2.042 |
polarized | -1.807 |
metaphor | -1.804 |
Token | - |
Token ID | 532 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ibaba | +1.856 |
naires | +1.806 |
unin | +1.757 |
ivo | +1.747 |
naire | +1.739 |
Neg logit contributions | |
Line | -1.434 |
Beet | -1.408 |
Tig | -1.384 |
metaphor | -1.229 |
polarized | -1.215 |
Token | Message |
Token ID | 12837 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ibaba | +2.090 |
naires | +1.998 |
unin | +1.950 |
ivo | +1.934 |
naire | +1.917 |
Neg logit contributions | |
Line | -2.054 |
Beet | -2.002 |
Tig | -1.990 |
metaphor | -1.767 |
polarized | -1.758 |
Token | " |
Token ID | 366 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ibaba | +0.620 |
naires | +0.595 |
unin | +0.586 |
ivo | +0.579 |
naire | +0.575 |
Neg logit contributions | |
Line | -0.300 |
Beet | -0.286 |
Tig | -0.285 |
metaphor | -0.236 |
Vide | -0.230 |
Token | F |
Token ID | 37 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ibaba | +2.168 |
naires | +2.059 |
unin | +2.045 |
ivo | +1.983 |
naire | +1.941 |
Neg logit contributions | |
Line | -3.110 |
Beet | -3.053 |
Tig | -3.017 |
metaphor | -2.755 |
Vide | -2.717 |
Token | ailed |
Token ID | 6255 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ibaba | +0.157 |
naires | +0.145 |
unin | +0.141 |
ivo | +0.138 |
naire | +0.138 |
Neg logit contributions | |
Line | -0.246 |
Tig | -0.236 |
Beet | -0.233 |
metaphor | -0.214 |
wart | -0.212 |
Token | to |
Token ID | 284 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ibaba | +0.839 |
naires | +0.793 |
unin | +0.782 |
ivo | +0.766 |
naire | +0.760 |
Neg logit contributions | |
Line | -0.731 |
Beet | -0.699 |
Tig | -0.699 |
metaphor | -0.614 |
Vide | -0.607 |
Token | $ |
Token ID | 720 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ibaba | +0.584 |
naires | +0.551 |
unin | +0.544 |
ivo | +0.534 |
naire | +0.529 |
Neg logit contributions | |
Line | -0.475 |
Tig | -0.452 |
Beet | -0.451 |
metaphor | -0.395 |
Vide | -0.390 |
Token | ($ |
Token ID | 16763 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Line | +0.165 |
Tig | +0.157 |
Beet | +0.157 |
metaphor | +0.142 |
Vide | +0.140 |
Neg logit contributions | |
ibaba | -0.129 |
naires | -0.120 |
unin | -0.118 |
ivo | -0.115 |
naire | -0.114 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ibaba | +0.459 |
naires | +0.431 |
unin | +0.424 |
ivo | +0.417 |
naire | +0.413 |
Neg logit contributions | |
Line | -0.429 |
Tig | -0.411 |
Beet | -0.409 |
metaphor | -0.363 |
Vide | -0.357 |
Token | Donald |
Token ID | 7371 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
Line | +0.130 |
Tig | +0.123 |
Beet | +0.122 |
metaphor | +0.109 |
Vide | +0.107 |
Neg logit contributions | |
ibaba | -0.144 |
naires | -0.135 |
unin | -0.133 |
ivo | -0.130 |
naire | -0.130 |
Token | Mir |
Token ID | 7381 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Line | +0.049 |
Tig | +0.046 |
Beet | +0.046 |
metaphor | +0.039 |
Passive | +0.038 |
Neg logit contributions | |
ibaba | -0.082 |
naires | -0.078 |
unin | -0.077 |
ivo | -0.076 |
naire | -0.075 |
Token | alle |
Token ID | 6765 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Line | +0.280 |
Tig | +0.267 |
Beet | +0.266 |
metaphor | +0.235 |
Vide | +0.232 |
Neg logit contributions | |
ibaba | -0.309 |
naires | -0.291 |
unin | -0.287 |
ivo | -0.281 |
naire | -0.279 |
Token | / |
Token ID | 14 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Line | +1.365 |
Tig | +1.290 |
Beet | +1.278 |
metaphor | +1.115 |
Vide | +1.104 |
Neg logit contributions | |
ibaba | -1.789 |
naires | -1.679 |
unin | -1.663 |
naire | -1.616 |
ivo | -1.615 |
Token | Getty |
Token ID | 6633 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ibaba | +0.934 |
naires | +0.880 |
unin | +0.867 |
ivo | +0.851 |
naire | +0.844 |
Neg logit contributions | |
Line | -0.805 |
Tig | -0.766 |
Beet | -0.762 |
metaphor | -0.672 |
Vide | -0.664 |
Token | Images |
Token ID | 5382 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ibaba | +2.709 |
naires | +2.576 |
unin | +2.535 |
ivo | +2.492 |
orsche | +2.488 |
Neg logit contributions | |
Line | -1.950 |
Tig | -1.860 |
Beet | -1.856 |
metaphor | -1.623 |
polarized | -1.593 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ibaba | +0.314 |
naires | +0.296 |
unin | +0.291 |
ivo | +0.286 |
naire | +0.284 |
Neg logit contributions | |
Line | -0.277 |
Tig | -0.264 |
Beet | -0.264 |
metaphor | -0.234 |
polarized | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ibaba | +0.366 |
naires | +0.340 |
unin | +0.338 |
ivo | +0.331 |
orsche | +0.330 |
Neg logit contributions | |
Line | -0.321 |
Tig | -0.306 |
Beet | -0.301 |
metaphor | -0.267 |
Vide | -0.264 |
Token | The |
Token ID | 464 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
ibaba | +0.247 |
naires | +0.232 |
unin | +0.229 |
ivo | +0.225 |
naire | +0.223 |
Neg logit contributions | |
Line | -0.214 |
Tig | -0.203 |
Beet | -0.202 |
metaphor | -0.178 |
Vide | -0.176 |
Token | latest |
Token ID | 3452 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Line | +0.055 |
Tig | +0.053 |
Beet | +0.052 |
metaphor | +0.045 |
Vide | +0.045 |
Neg logit contributions | |
ibaba | -0.075 |
naires | -0.071 |
unin | -0.070 |
ivo | -0.069 |
naire | -0.069 |
Token | possible |
Token ID | 1744 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ibaba | +0.985 |
naires | +0.933 |
unin | +0.925 |
ivo | +0.904 |
naire | +0.900 |
Neg logit contributions | |
Line | -0.752 |
Beet | -0.721 |
Tig | -0.717 |
Vide | -0.622 |
metaphor | -0.615 |
Token | component |
Token ID | 7515 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ibaba | +0.763 |
naires | +0.724 |
unin | +0.720 |
ivo | +0.708 |
naire | +0.701 |
Neg logit contributions | |
Line | -0.533 |
Beet | -0.509 |
Tig | -0.508 |
Vide | -0.434 |
metaphor | -0.429 |
Token | of |
Token ID | 286 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ibaba | +0.556 |
naires | +0.525 |
unin | +0.518 |
ivo | +0.508 |
naire | +0.504 |
Neg logit contributions | |
Line | -0.495 |
Tig | -0.473 |
Beet | -0.472 |
metaphor | -0.413 |
Vide | -0.411 |
Token | dark |
Token ID | 3223 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ibaba | +1.149 |
naires | +1.082 |
unin | +1.068 |
ivo | +1.047 |
naire | +1.034 |
Neg logit contributions | |
Line | -1.072 |
Tig | -1.030 |
Beet | -1.028 |
metaphor | -0.905 |
Vide | -0.898 |
Token | matter |
Token ID | 2300 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Line | +0.381 |
Tig | +0.359 |
Beet | +0.357 |
metaphor | +0.307 |
polarized | +0.301 |
Neg logit contributions | |
ibaba | -0.591 |
naires | -0.558 |
unin | -0.553 |
ivo | -0.544 |
naire | -0.540 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Line | +0.209 |
Tig | +0.197 |
Beet | +0.196 |
metaphor | +0.170 |
Vide | +0.167 |
Neg logit contributions | |
ibaba | -0.305 |
naires | -0.288 |
unin | -0.285 |
ivo | -0.280 |
naire | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
ibaba | +0.981 |
naires | +0.939 |
unin | +0.915 |
ivo | +0.904 |
naire | +0.900 |
Neg logit contributions | |
Line | -0.844 |
Tig | -0.806 |
Beet | -0.803 |
metaphor | -0.720 |
polarized | -0.705 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ibaba | +0.595 |
naires | +0.554 |
unin | +0.549 |
ivo | +0.539 |
orsche | +0.536 |
Neg logit contributions | |
Line | -0.530 |
Tig | -0.504 |
Beet | -0.498 |
metaphor | -0.442 |
Vide | -0.437 |
Token | If |
Token ID | 1532 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
ibaba | +0.426 |
naires | +0.405 |
unin | +0.399 |
ivo | +0.392 |
naire | +0.388 |
Neg logit contributions | |
Line | -0.355 |
Tig | -0.339 |
Beet | -0.338 |
metaphor | -0.296 |
Vide | -0.292 |
Token | it |
Token ID | 340 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ibaba | +0.780 |
naires | +0.740 |
unin | +0.726 |
ivo | +0.712 |
naire | +0.706 |
Neg logit contributions | |
Line | -0.683 |
Tig | -0.653 |
Beet | -0.650 |
metaphor | -0.571 |
Vide | -0.568 |
Token | succeeds |
Token ID | 31137 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ibaba | +1.729 |
naires | +1.659 |
unin | +1.625 |
ivo | +1.590 |
naire | +1.583 |
Neg logit contributions | |
Line | -1.400 |
Tig | -1.335 |
Beet | -1.331 |
Vide | -1.153 |
Passive | -1.150 |
Token | look |
Token ID | 804 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
Line | +0.449 |
Tig | +0.426 |
Beet | +0.424 |
metaphor | +0.372 |
Vide | +0.365 |
Neg logit contributions | |
ibaba | -0.574 |
naires | -0.541 |
unin | -0.535 |
ivo | -0.525 |
naire | -0.521 |
Token | like |
Token ID | 588 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Line | +0.575 |
Tig | +0.545 |
Beet | +0.539 |
metaphor | +0.470 |
Vide | +0.456 |
Neg logit contributions | |
ibaba | -0.850 |
naires | -0.807 |
unin | -0.795 |
ivo | -0.781 |
naire | -0.779 |
Token | with |
Token ID | 351 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ibaba | +1.384 |
naires | +1.311 |
unin | +1.290 |
ivo | +1.272 |
naire | +1.259 |
Neg logit contributions | |
Line | -1.171 |
Beet | -1.113 |
Tig | -1.110 |
metaphor | -0.966 |
Vide | -0.963 |
Token | your |
Token ID | 534 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ibaba | +1.302 |
naires | +1.225 |
unin | +1.200 |
ivo | +1.174 |
naire | +1.167 |
Neg logit contributions | |
Line | -1.505 |
Beet | -1.443 |
Tig | -1.442 |
metaphor | -1.288 |
Vide | -1.278 |
Token | shirt |
Token ID | 10147 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Line | +0.341 |
Tig | +0.326 |
Beet | +0.324 |
metaphor | +0.289 |
Vide | +0.284 |
Neg logit contributions | |
ibaba | -0.354 |
naires | -0.331 |
unin | -0.327 |
ivo | -0.320 |
naire | -0.317 |
Token | off |
Token ID | 572 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
Line | +0.292 |
Tig | +0.277 |
Beet | +0.276 |
metaphor | +0.242 |
Vide | +0.238 |
Neg logit contributions | |
ibaba | -0.368 |
naires | -0.347 |
unin | -0.342 |
ivo | -0.336 |
naire | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
ibaba | +0.058 |
naires | +0.055 |
unin | +0.054 |
ivo | +0.053 |
naire | +0.053 |
Neg logit contributions | |
Line | -0.043 |
Tig | -0.041 |
Beet | -0.041 |
metaphor | -0.035 |
Vide | -0.035 |
Token | We |
Token ID | 775 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Line | +0.595 |
Tig | +0.567 |
Beet | +0.564 |
metaphor | +0.498 |
Vide | +0.493 |
Neg logit contributions | |
ibaba | -0.660 |
naires | -0.620 |
unin | -0.613 |
ivo | -0.600 |
naire | -0.594 |
Token | get |
Token ID | 651 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Line | +0.293 |
Tig | +0.276 |
Beet | +0.275 |
metaphor | +0.235 |
Vide | +0.231 |
Neg logit contributions | |
ibaba | -0.466 |
naires | -0.442 |
unin | -0.437 |
ivo | -0.430 |
naire | -0.427 |
Token | it |
Token ID | 340 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ibaba | +0.095 |
naires | +0.090 |
unin | +0.089 |
ivo | +0.087 |
naire | +0.086 |
Neg logit contributions | |
Line | -0.078 |
Tig | -0.074 |
Beet | -0.074 |
metaphor | -0.065 |
Vide | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ibaba | +0.028 |
naires | +0.027 |
unin | +0.027 |
ivo | +0.026 |
naire | +0.026 |
Neg logit contributions | |
Line | -0.021 |
Tig | -0.020 |
Beet | -0.020 |
metaphor | -0.017 |
Vide | -0.017 |
Token | went |
Token ID | 1816 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ibaba | +0.233 |
naires | +0.220 |
unin | +0.218 |
ivo | +0.214 |
naire | +0.212 |
Neg logit contributions | |
Line | -0.162 |
Tig | -0.153 |
Beet | -0.153 |
metaphor | -0.132 |
Vide | -0.130 |
Token | so |
Token ID | 523 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
Line | +0.543 |
Tig | +0.517 |
Beet | +0.513 |
metaphor | +0.453 |
polarized | +0.443 |
Neg logit contributions | |
ibaba | -0.686 |
naires | -0.645 |
unin | -0.636 |
ivo | -0.626 |
orsche | -0.623 |
Token | late |
Token ID | 2739 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ibaba | +0.739 |
naires | +0.695 |
unin | +0.686 |
ivo | +0.673 |
naire | +0.666 |
Neg logit contributions | |
Line | -0.680 |
Tig | -0.649 |
Beet | -0.647 |
metaphor | -0.571 |
Vide | -0.566 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ibaba | +1.877 |
naires | +1.777 |
unin | +1.741 |
ivo | +1.717 |
naire | +1.699 |
Neg logit contributions | |
Line | -1.572 |
Tig | -1.486 |
Beet | -1.480 |
metaphor | -1.298 |
Vide | -1.294 |
Token | bird |
Token ID | 6512 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
ibaba | +0.670 |
naires | +0.637 |
unin | +0.630 |
ivo | +0.620 |
naire | +0.616 |
Neg logit contributions | |
Line | -0.373 |
Tig | -0.349 |
Beet | -0.347 |
metaphor | -0.293 |
Vide | -0.288 |
Token | migration |
Token ID | 13472 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
Line | +0.546 |
Tig | +0.519 |
Beet | +0.517 |
metaphor | +0.451 |
Vide | +0.443 |
Neg logit contributions | |
ibaba | -0.704 |
naires | -0.662 |
unin | -0.656 |
ivo | -0.644 |
naire | -0.639 |
Token | was |
Token ID | 373 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ibaba | +0.773 |
naires | +0.732 |
unin | +0.723 |
ivo | +0.710 |
naire | +0.705 |
Neg logit contributions | |
Line | -0.553 |
Tig | -0.524 |
Beet | -0.521 |
metaphor | -0.451 |
Vide | -0.446 |
Token | in |
Token ID | 287 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Line | +0.139 |
Tig | +0.133 |
Beet | +0.132 |
metaphor | +0.117 |
polarized | +0.114 |
Neg logit contributions | |
ibaba | -0.164 |
naires | -0.155 |
unin | -0.152 |
ivo | -0.150 |
naire | -0.149 |
Token | full |
Token ID | 1336 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
ibaba | +0.275 |
naires | +0.259 |
unin | +0.253 |
ivo | +0.250 |
naire | +0.248 |
Neg logit contributions | |
Line | -0.229 |
Tig | -0.218 |
Beet | -0.216 |
metaphor | -0.191 |
Passive | -0.187 |
Token | swing |
Token ID | 9628 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
ibaba | +0.056 |
naires | +0.053 |
unin | +0.052 |
ivo | +0.051 |
orsche | +0.050 |
Neg logit contributions | |
Line | -0.054 |
Tig | -0.052 |
Beet | -0.051 |
metaphor | -0.046 |
Vide | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Line | +0.531 |
Tig | +0.504 |
Beet | +0.501 |
metaphor | +0.438 |
Vide | +0.428 |
Neg logit contributions | |
ibaba | -0.714 |
naires | -0.674 |
unin | -0.665 |
ivo | -0.654 |
orsche | -0.649 |
Token | distribution |
Token ID | 6082 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Line | +0.527 |
Tig | +0.502 |
Beet | +0.498 |
metaphor | +0.451 |
Vide | +0.445 |
Neg logit contributions | |
ibaba | -0.464 |
naires | -0.431 |
unin | -0.424 |
orsche | -0.411 |
ivo | -0.411 |
Token | with |
Token ID | 351 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Line | +0.934 |
Tig | +0.881 |
Beet | +0.872 |
metaphor | +0.771 |
Vide | +0.751 |
Neg logit contributions | |
ibaba | -1.254 |
naires | -1.175 |
unin | -1.163 |
ivo | -1.145 |
orsche | -1.135 |
Token | the |
Token ID | 262 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Line | +0.630 |
Tig | +0.594 |
Beet | +0.590 |
metaphor | +0.522 |
Vide | +0.515 |
Neg logit contributions | |
ibaba | -0.761 |
naires | -0.712 |
unin | -0.703 |
ivo | -0.687 |
naire | -0.684 |
Token | Flat |
Token ID | 21939 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Line | +0.175 |
Tig | +0.166 |
Beet | +0.165 |
metaphor | +0.144 |
Vide | +0.142 |
Neg logit contributions | |
ibaba | -0.224 |
naires | -0.211 |
unin | -0.209 |
ivo | -0.205 |
naire | -0.203 |
Token | pak |
Token ID | 41091 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Line | +1.200 |
Tig | +1.120 |
Beet | +1.111 |
metaphor | +0.932 |
Vide | +0.911 |
Neg logit contributions | |
ibaba | -2.315 |
naires | -2.208 |
unin | -2.179 |
ivo | -2.149 |
naire | -2.136 |
Token | software |
Token ID | 3788 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Line | +1.682 |
Tig | +1.588 |
Beet | +1.571 |
metaphor | +1.439 |
Vide | +1.399 |
Neg logit contributions | |
ibaba | -1.708 |
naires | -1.596 |
unin | -1.563 |
ivo | -1.527 |
humane | -1.519 |
Token | installed |
Token ID | 6589 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ibaba | +0.741 |
naires | +0.699 |
unin | +0.690 |
ivo | +0.678 |
naire | +0.672 |
Neg logit contributions | |
Line | -0.587 |
Tig | -0.558 |
Beet | -0.555 |
metaphor | -0.486 |
Vide | -0.479 |
Token | should |
Token ID | 815 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
Line | +1.243 |
Tig | +1.178 |
Beet | +1.161 |
metaphor | +1.031 |
Vide | +0.995 |
Neg logit contributions | |
ibaba | -1.692 |
naires | -1.578 |
unin | -1.563 |
ivo | -1.541 |
orsche | -1.535 |
Token | be |
Token ID | 307 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Line | +0.030 |
Tig | +0.029 |
Beet | +0.029 |
metaphor | +0.025 |
Vide | +0.025 |
Neg logit contributions | |
ibaba | -0.040 |
naires | -0.038 |
unin | -0.038 |
ivo | -0.037 |
orsche | -0.036 |
Token | able |
Token ID | 1498 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Line | +0.855 |
Tig | +0.808 |
Beet | +0.804 |
metaphor | +0.707 |
Vide | +0.691 |
Neg logit contributions | |
ibaba | -1.103 |
naires | -1.040 |
unin | -1.026 |
ivo | -1.006 |
naire | -0.999 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Line | +1.192 |
Tig | +1.119 |
Beet | +1.107 |
metaphor | +0.983 |
Vide | +0.955 |
Neg logit contributions | |
ibaba | -1.567 |
naires | -1.475 |
unin | -1.468 |
ivo | -1.437 |
orsche | -1.433 |
Token | ining |
Token ID | 3191 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Line | +0.921 |
Tig | +0.883 |
Beet | +0.880 |
metaphor | +0.795 |
Vide | +0.787 |
Neg logit contributions | |
ibaba | -0.699 |
naires | -0.649 |
unin | -0.639 |
ivo | -0.623 |
naire | -0.616 |
Token | each |
Token ID | 1123 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Line | +0.179 |
Tig | +0.169 |
Beet | +0.168 |
metaphor | +0.148 |
Passive | +0.146 |
Neg logit contributions | |
ibaba | -0.213 |
naires | -0.200 |
unin | -0.198 |
ivo | -0.194 |
naire | -0.192 |
Token | one |
Token ID | 530 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ibaba | +0.244 |
naires | +0.230 |
unin | +0.227 |
ivo | +0.223 |
naire | +0.221 |
Neg logit contributions | |
Line | -0.201 |
Tig | -0.192 |
Beet | -0.191 |
metaphor | -0.167 |
Vide | -0.165 |
Token | of |
Token ID | 286 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ibaba | +1.451 |
naires | +1.373 |
unin | +1.348 |
ivo | +1.327 |
naire | +1.315 |
Neg logit contributions | |
Line | -1.254 |
Beet | -1.195 |
Tig | -1.195 |
metaphor | -1.042 |
Vide | -1.039 |
Token | those |
Token ID | 883 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ibaba | +0.543 |
naires | +0.510 |
unin | +0.503 |
ivo | +0.493 |
naire | +0.489 |
Neg logit contributions | |
Line | -0.529 |
Tig | -0.505 |
Beet | -0.502 |
metaphor | -0.447 |
Vide | -0.441 |
Token | in |
Token ID | 287 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
Line | +0.723 |
Tig | +0.685 |
Beet | +0.676 |
metaphor | +0.602 |
Passive | +0.586 |
Neg logit contributions | |
ibaba | -0.913 |
naires | -0.854 |
unin | -0.848 |
ivo | -0.835 |
orsche | -0.829 |
Token | turn |
Token ID | 1210 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ibaba | +0.528 |
naires | +0.499 |
unin | +0.493 |
ivo | +0.484 |
naire | +0.480 |
Neg logit contributions | |
Line | -0.412 |
Tig | -0.390 |
Beet | -0.388 |
metaphor | -0.340 |
Vide | -0.334 |
Token | can |
Token ID | 460 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Line | +0.140 |
Tig | +0.133 |
Beet | +0.132 |
metaphor | +0.115 |
Vide | +0.112 |
Neg logit contributions | |
ibaba | -0.198 |
naires | -0.187 |
unin | -0.186 |
ivo | -0.182 |
naire | -0.181 |
Token | give |
Token ID | 1577 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Line | +0.204 |
Tig | +0.193 |
Beet | +0.192 |
metaphor | +0.167 |
Vide | +0.164 |
Neg logit contributions | |
ibaba | -0.282 |
naires | -0.267 |
unin | -0.264 |
ivo | -0.259 |
naire | -0.257 |
Token | one |
Token ID | 530 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
ibaba | +0.180 |
naires | +0.168 |
unin | +0.166 |
ivo | +0.162 |
naire | +0.161 |
Neg logit contributions | |
Line | -0.188 |
Tig | -0.180 |
Beet | -0.179 |
metaphor | -0.160 |
Vide | -0.158 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ibaba | +0.294 |
naires | +0.277 |
unin | +0.273 |
ivo | +0.268 |
naire | +0.266 |
Neg logit contributions | |
Line | -0.259 |
Tig | -0.246 |
Beet | -0.245 |
metaphor | -0.217 |
Vide | -0.213 |
Token | report |
Token ID | 989 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ibaba | +1.255 |
naires | +1.186 |
unin | +1.172 |
ivo | +1.151 |
naire | +1.141 |
Neg logit contributions | |
Line | -0.950 |
Tig | -0.901 |
Beet | -0.895 |
metaphor | -0.781 |
Vide | -0.770 |
Token | says |
Token ID | 1139 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Line | +0.093 |
Tig | +0.087 |
Beet | +0.087 |
metaphor | +0.073 |
Vide | +0.072 |
Neg logit contributions | |
ibaba | -0.172 |
naires | -0.163 |
unin | -0.161 |
ivo | -0.159 |
naire | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ibaba | +1.264 |
naires | +1.211 |
unin | +1.178 |
ivo | +1.163 |
humane | +1.161 |
Neg logit contributions | |
Line | -0.990 |
Beet | -0.952 |
Tig | -0.948 |
Passive | -0.823 |
Vide | -0.820 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ibaba | +0.215 |
naires | +0.201 |
unin | +0.199 |
ivo | +0.195 |
orsche | +0.194 |
Neg logit contributions | |
Line | -0.195 |
Tig | -0.186 |
Beet | -0.184 |
Vide | -0.162 |
metaphor | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ibaba | +1.487 |
naires | +1.394 |
unin | +1.376 |
ivo | +1.349 |
naire | +1.337 |
Neg logit contributions | |
Line | -1.386 |
Tig | -1.322 |
Beet | -1.316 |
metaphor | -1.165 |
Vide | -1.152 |
Token | An |
Token ID | 2025 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ibaba | +1.109 |
naires | +1.039 |
unin | +1.025 |
ivo | +1.006 |
naire | +0.998 |
Neg logit contributions | |
Line | -1.003 |
Tig | -0.956 |
Beet | -0.950 |
metaphor | -0.840 |
Vide | -0.832 |
Token | unprecedented |
Token ID | 13029 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Line | +0.395 |
Tig | +0.376 |
Beet | +0.370 |
metaphor | +0.327 |
Vide | +0.324 |
Neg logit contributions | |
ibaba | -0.462 |
naires | -0.440 |
unin | -0.429 |
ivo | -0.423 |
naire | -0.421 |
Token | number |
Token ID | 1271 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Line | +0.289 |
Tig | +0.273 |
Beet | +0.269 |
metaphor | +0.238 |
Vide | +0.233 |
Neg logit contributions | |
ibaba | -0.383 |
naires | -0.362 |
unin | -0.358 |
ivo | -0.353 |
orsche | -0.350 |
Token | of |
Token ID | 286 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ibaba | +0.968 |
naires | +0.923 |
unin | +0.894 |
ivo | +0.885 |
naire | +0.884 |
Neg logit contributions | |
Line | -0.861 |
Beet | -0.825 |
Tig | -0.822 |
Vide | -0.719 |
metaphor | -0.718 |
Token | children |
Token ID | 1751 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Line | +0.438 |
Tig | +0.420 |
Beet | +0.415 |
metaphor | +0.371 |
Vide | +0.366 |
Neg logit contributions | |
ibaba | -0.428 |
naires | -0.397 |
unin | -0.391 |
ivo | -0.386 |
orsche | -0.383 |
Token | has |
Token ID | 468 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Line | +1.125 |
Tig | +1.064 |
Beet | +1.046 |
metaphor | +0.921 |
polarized | +0.895 |
Neg logit contributions | |
ibaba | -1.656 |
unin | -1.550 |
naires | -1.548 |
ivo | -1.515 |
orsche | -1.511 |
Token | . |
Token ID | 13 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Line | +0.478 |
Tig | +0.453 |
Beet | +0.450 |
metaphor | +0.392 |
Vide | +0.386 |
Neg logit contributions | |
ibaba | -0.663 |
naires | -0.626 |
unin | -0.618 |
ivo | -0.608 |
naire | -0.604 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Line | +0.457 |
Tig | +0.434 |
Beet | +0.431 |
Vide | +0.378 |
metaphor | +0.377 |
Neg logit contributions | |
ibaba | -0.534 |
naires | -0.501 |
unin | -0.497 |
ivo | -0.485 |
naire | -0.482 |
Token | The |
Token ID | 464 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
Line | +0.449 |
Tig | +0.427 |
Beet | +0.424 |
metaphor | +0.376 |
Vide | +0.372 |
Neg logit contributions | |
ibaba | -0.497 |
naires | -0.465 |
unin | -0.458 |
ivo | -0.449 |
naire | -0.446 |
Token | thorn |
Token ID | 38999 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ibaba | +0.080 |
naires | +0.075 |
unin | +0.074 |
ivo | +0.073 |
naire | +0.073 |
Neg logit contributions | |
Line | -0.060 |
Tig | -0.057 |
Beet | -0.057 |
metaphor | -0.049 |
Vide | -0.049 |
Token | y |
Token ID | 88 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
ibaba | +0.972 |
naires | +0.918 |
unin | +0.906 |
ivo | +0.893 |
naire | +0.882 |
Neg logit contributions | |
Line | -0.748 |
Tig | -0.710 |
Beet | -0.707 |
metaphor | -0.613 |
Vide | -0.610 |
Token | debates |
Token ID | 15389 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
Line | +0.052 |
Tig | +0.049 |
Beet | +0.049 |
metaphor | +0.041 |
Vide | +0.041 |
Neg logit contributions | |
ibaba | -0.081 |
naires | -0.077 |
unin | -0.076 |
ivo | -0.075 |
naire | -0.075 |
Token | around |
Token ID | 1088 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Line | +0.634 |
Tig | +0.604 |
Beet | +0.600 |
metaphor | +0.530 |
Vide | +0.522 |
Neg logit contributions | |
ibaba | -0.735 |
naires | -0.690 |
unin | -0.683 |
ivo | -0.669 |
naire | -0.663 |
Token | encryption |
Token ID | 15835 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
Line | +0.866 |
Tig | +0.821 |
Beet | +0.814 |
metaphor | +0.718 |
Vide | +0.708 |
Neg logit contributions | |
ibaba | -1.065 |
naires | -1.002 |
unin | -0.991 |
ivo | -0.976 |
naire | -0.966 |
Token | , |
Token ID | 11 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Line | +0.423 |
Tig | +0.402 |
Beet | +0.400 |
metaphor | +0.349 |
Vide | +0.344 |
Neg logit contributions | |
ibaba | -0.542 |
naires | -0.512 |
unin | -0.505 |
ivo | -0.496 |
naire | -0.492 |
Token | national |
Token ID | 2260 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Line | +0.272 |
Tig | +0.258 |
Beet | +0.256 |
metaphor | +0.225 |
Vide | +0.222 |
Neg logit contributions | |
ibaba | -0.346 |
naires | -0.327 |
unin | -0.323 |
ivo | -0.317 |
naire | -0.314 |
Token | security |
Token ID | 2324 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
ibaba | +1.511 |
naires | +1.434 |
unin | +1.416 |
ivo | +1.393 |
naire | +1.384 |
Neg logit contributions | |
Line | -0.938 |
Beet | -0.885 |
Tig | -0.885 |
metaphor | -0.750 |
Vide | -0.739 |
Token | laid |
Token ID | 8104 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ibaba | +0.322 |
naires | +0.305 |
unin | +0.301 |
ivo | +0.295 |
naire | +0.293 |
Neg logit contributions | |
Line | -0.254 |
Tig | -0.241 |
Beet | -0.240 |
metaphor | -0.210 |
Vide | -0.207 |
Token | during |
Token ID | 1141 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ibaba | +1.641 |
naires | +1.554 |
unin | +1.536 |
ivo | +1.491 |
naire | +1.488 |
Neg logit contributions | |
Line | -1.540 |
Tig | -1.473 |
Beet | -1.472 |
Vide | -1.286 |
metaphor | -1.284 |
Token | the |
Token ID | 262 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ibaba | +0.167 |
naires | +0.157 |
unin | +0.155 |
ivo | +0.152 |
naire | +0.151 |
Neg logit contributions | |
Line | -0.145 |
Tig | -0.138 |
Beet | -0.138 |
metaphor | -0.121 |
Vide | -0.120 |
Token | past |
Token ID | 1613 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
Line | +0.160 |
Tig | +0.150 |
Beet | +0.149 |
metaphor | +0.128 |
Vide | +0.125 |
Neg logit contributions | |
ibaba | -0.267 |
naires | -0.253 |
unin | -0.250 |
ivo | -0.246 |
naire | -0.244 |
Token | month |
Token ID | 1227 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ibaba | +0.056 |
naires | +0.053 |
unin | +0.052 |
ivo | +0.051 |
naire | +0.051 |
Neg logit contributions | |
Line | -0.036 |
Tig | -0.034 |
Beet | -0.034 |
metaphor | -0.029 |
Vide | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ibaba | +0.385 |
naires | +0.365 |
unin | +0.359 |
ivo | +0.353 |
naire | +0.351 |
Neg logit contributions | |
Line | -0.299 |
Tig | -0.285 |
Beet | -0.285 |
metaphor | -0.247 |
Vide | -0.245 |
Token | conditioning |
Token ID | 21143 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Line | +0.845 |
Tig | +0.806 |
Beet | +0.800 |
metaphor | +0.716 |
Vide | +0.706 |
Neg logit contributions | |
ibaba | -0.823 |
naires | -0.764 |
unin | -0.752 |
ivo | -0.743 |
orsche | -0.734 |
Token | sessions |
Token ID | 10991 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Line | +0.101 |
Tig | +0.096 |
Beet | +0.096 |
metaphor | +0.084 |
Vide | +0.083 |
Neg logit contributions | |
ibaba | -0.119 |
naires | -0.112 |
unin | -0.110 |
ivo | -0.108 |
naire | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Line | +1.180 |
Tig | +1.118 |
Beet | +1.105 |
metaphor | +0.962 |
Vide | +0.946 |
Neg logit contributions | |
ibaba | -1.637 |
naires | -1.542 |
unin | -1.529 |
ivo | -1.498 |
naire | -1.487 |
Token | position |
Token ID | 2292 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Line | +0.097 |
Tig | +0.092 |
Beet | +0.091 |
metaphor | +0.080 |
Vide | +0.079 |
Neg logit contributions | |
ibaba | -0.119 |
naires | -0.112 |
unin | -0.111 |
ivo | -0.109 |
naire | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Line | +0.494 |
Tig | +0.471 |
Beet | +0.468 |
metaphor | +0.422 |
Vide | +0.416 |
Neg logit contributions | |
ibaba | -0.440 |
naires | -0.407 |
unin | -0.403 |
ivo | -0.394 |
orsche | -0.390 |
Token | ata |
Token ID | 1045 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ibaba | +2.005 |
naires | +1.920 |
unin | +1.902 |
ivo | +1.876 |
naire | +1.865 |
Neg logit contributions | |
Line | -0.716 |
Tig | -0.657 |
Beet | -0.650 |
metaphor | -0.507 |
Vide | -0.494 |
Token | : |
Token ID | 25 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ibaba | +1.037 |
naires | +0.980 |
unin | +0.963 |
ivo | +0.947 |
naire | +0.938 |
Neg logit contributions | |
Line | -0.930 |
Tig | -0.889 |
Beet | -0.887 |
metaphor | -0.781 |
Vide | -0.771 |
Token | During |
Token ID | 5856 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ibaba | +1.740 |
naires | +1.668 |
unin | +1.633 |
ivo | +1.614 |
naire | +1.607 |
Neg logit contributions | |
Line | -1.191 |
Tig | -1.132 |
Beet | -1.130 |
metaphor | -0.989 |
polarized | -0.973 |
Token | development |
Token ID | 2478 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Line | +0.022 |
Tig | +0.021 |
Beet | +0.021 |
metaphor | +0.018 |
Vide | +0.018 |
Neg logit contributions | |
ibaba | -0.024 |
naires | -0.023 |
unin | -0.023 |
ivo | -0.022 |
orsche | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Line | +0.498 |
Tig | +0.471 |
Beet | +0.466 |
metaphor | +0.408 |
Vide | +0.404 |
Neg logit contributions | |
ibaba | -0.641 |
naires | -0.598 |
unin | -0.594 |
ivo | -0.582 |
orsche | -0.580 |
Token | we |
Token ID | 356 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Line | +0.531 |
Tig | +0.500 |
Beet | +0.493 |
metaphor | +0.437 |
Vide | +0.432 |
Neg logit contributions | |
ibaba | -0.651 |
naires | -0.608 |
unin | -0.605 |
ivo | -0.597 |
orsche | -0.590 |
Token | were |
Token ID | 547 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Line | +0.449 |
Tig | +0.424 |
Beet | +0.419 |
metaphor | +0.366 |
Vide | +0.358 |
Neg logit contributions | |
ibaba | -0.657 |
naires | -0.618 |
unin | -0.613 |
ivo | -0.602 |
orsche | -0.597 |
Token | working |
Token ID | 1762 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Line | +0.476 |
Tig | +0.452 |
Beet | +0.447 |
metaphor | +0.396 |
Vide | +0.387 |
Neg logit contributions | |
ibaba | -0.603 |
naires | -0.565 |
unin | -0.561 |
ivo | -0.550 |
orsche | -0.545 |
Token | around |
Token ID | 1088 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Line | +0.316 |
Tig | +0.301 |
Beet | +0.299 |
metaphor | +0.265 |
Vide | +0.260 |
Neg logit contributions | |
ibaba | -0.377 |
naires | -0.354 |
unin | -0.349 |
ivo | -0.343 |
naire | -0.341 |
Token | the |
Token ID | 262 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
Line | +0.760 |
Tig | +0.723 |
Beet | +0.716 |
metaphor | +0.637 |
Vide | +0.629 |
Neg logit contributions | |
ibaba | -0.840 |
naires | -0.785 |
unin | -0.775 |
ivo | -0.764 |
naire | -0.756 |
Token | clock |
Token ID | 8801 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Line | +0.299 |
Tig | +0.279 |
Beet | +0.277 |
metaphor | +0.228 |
Vide | +0.224 |
Neg logit contributions | |
ibaba | -0.628 |
naires | -0.599 |
unin | -0.593 |
ivo | -0.584 |
naire | -0.581 |
Token | Under |
Token ID | 9203 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Line | +0.018 |
Tig | +0.017 |
Beet | +0.017 |
metaphor | +0.015 |
Vide | +0.015 |
Neg logit contributions | |
ibaba | -0.020 |
naires | -0.019 |
unin | -0.019 |
ivo | -0.018 |
orsche | -0.018 |
Token | ground |
Token ID | 2833 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ibaba | +1.397 |
naires | +1.310 |
unin | +1.293 |
ivo | +1.268 |
naire | +1.255 |
Neg logit contributions | |
Line | -1.196 |
Tig | -1.137 |
Beet | -1.135 |
metaphor | -0.997 |
Vide | -0.990 |
Token | … |
Token ID | 1399 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Line | +0.165 |
Tig | +0.155 |
Beet | +0.154 |
metaphor | +0.132 |
Vide | +0.130 |
Neg logit contributions | |
ibaba | -0.267 |
naires | -0.254 |
unin | -0.251 |
ivo | -0.247 |
naire | -0.245 |
Token | is |
Token ID | 318 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ibaba | +1.521 |
naires | +1.442 |
unin | +1.423 |
ivo | +1.398 |
naire | +1.386 |
Neg logit contributions | |
Line | -1.039 |
Tig | -0.984 |
Beet | -0.978 |
metaphor | -0.847 |
Vide | -0.835 |
Token | it |
Token ID | 340 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ibaba | +0.356 |
naires | +0.336 |
unin | +0.331 |
ivo | +0.325 |
naire | +0.322 |
Neg logit contributions | |
Line | -0.291 |
Tig | -0.277 |
Beet | -0.276 |
metaphor | -0.242 |
Vide | -0.240 |
Token | ? |
Token ID | 30 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Line | +1.338 |
Tig | +1.272 |
Beet | +1.266 |
metaphor | +1.102 |
Passive | +1.073 |
Neg logit contributions | |
ibaba | -1.843 |
naires | -1.739 |
unin | -1.714 |
ivo | -1.696 |
orsche | -1.681 |
Token | We |
Token ID | 775 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
Line | +0.319 |
Tig | +0.301 |
Beet | +0.299 |
metaphor | +0.255 |
Vide | +0.251 |
Neg logit contributions | |
ibaba | -0.509 |
naires | -0.482 |
unin | -0.477 |
ivo | -0.469 |
naire | -0.465 |
Token | 're |
Token ID | 821 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
Line | +0.046 |
Tig | +0.044 |
Beet | +0.044 |
metaphor | +0.038 |
Vide | +0.037 |
Neg logit contributions | |
ibaba | -0.066 |
naires | -0.062 |
unin | -0.061 |
ivo | -0.060 |
naire | -0.060 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ibaba | +0.632 |
naires | +0.595 |
unin | +0.588 |
ivo | +0.577 |
naire | +0.572 |
Neg logit contributions | |
Line | -0.536 |
Tig | -0.510 |
Beet | -0.507 |
metaphor | -0.447 |
Vide | -0.439 |
Token | talking |
Token ID | 3375 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
Line | +0.802 |
Tig | +0.763 |
Beet | +0.753 |
metaphor | +0.665 |
polarized | +0.655 |
Neg logit contributions | |
ibaba | -1.078 |
naires | -1.014 |
unin | -1.001 |
orsche | -0.988 |
ivo | -0.986 |
Token | about |
Token ID | 546 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Line | +0.023 |
Tig | +0.022 |
Beet | +0.022 |
metaphor | +0.019 |
Vide | +0.019 |
Neg logit contributions | |
ibaba | -0.025 |
naires | -0.023 |
unin | -0.023 |
ivo | -0.022 |
orsche | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Line | +0.660 |
Tig | +0.624 |
Beet | +0.621 |
metaphor | +0.535 |
Vide | +0.531 |
Neg logit contributions | |
ibaba | -0.897 |
naires | -0.850 |
unin | -0.840 |
ivo | -0.824 |
naire | -0.819 |
Token | Som |
Token ID | 9995 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Line | +1.906 |
Tig | +1.801 |
Beet | +1.782 |
Vide | +1.545 |
metaphor | +1.529 |
Neg logit contributions | |
ibaba | -2.485 |
naires | -2.367 |
unin | -2.328 |
ivo | -2.284 |
naire | -2.270 |
Token | n |
Token ID | 77 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Line | +1.654 |
Tig | +1.558 |
Beet | +1.545 |
Vide | +1.363 |
metaphor | +1.354 |
Neg logit contributions | |
ibaba | -1.920 |
naires | -1.840 |
unin | -1.800 |
ivo | -1.764 |
naire | -1.755 |
Token | ath |
Token ID | 776 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Line | +0.232 |
Tig | +0.196 |
Beet | +0.189 |
metaphor | +0.101 |
Vide | +0.096 |
Neg logit contributions | |
ibaba | -1.379 |
naires | -1.337 |
unin | -1.324 |
naire | -1.307 |
ivo | -1.305 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Line | +0.884 |
Tig | +0.837 |
Beet | +0.833 |
metaphor | +0.720 |
Vide | +0.712 |
Neg logit contributions | |
ibaba | -1.136 |
naires | -1.082 |
unin | -1.064 |
ivo | -1.042 |
naire | -1.041 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Line | +1.093 |
Tig | +1.033 |
Beet | +1.026 |
metaphor | +0.881 |
Vide | +0.878 |
Neg logit contributions | |
ibaba | -1.560 |
naires | -1.481 |
unin | -1.462 |
ivo | -1.435 |
naire | -1.426 |
Token | 36 |
Token ID | 4570 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Line | +2.032 |
Tig | +1.918 |
Beet | +1.908 |
metaphor | +1.662 |
Vide | +1.662 |
Neg logit contributions | |
ibaba | -2.406 |
naires | -2.269 |
unin | -2.246 |
ivo | -2.200 |
orsche | -2.182 |
Token | 22 |
Token ID | 1828 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Line | +2.453 |
Tig | +2.329 |
Beet | +2.303 |
Vide | +2.035 |
metaphor | +2.027 |
Neg logit contributions | |
ibaba | -2.515 |
naires | -2.351 |
unin | -2.325 |
ivo | -2.273 |
orsche | -2.254 |
Token | 65 |
Token ID | 2996 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Line | +1.235 |
Tig | +1.172 |
Beet | +1.165 |
metaphor | +1.022 |
Vide | +1.019 |
Neg logit contributions | |
ibaba | -1.387 |
naires | -1.302 |
unin | -1.290 |
ivo | -1.262 |
orsche | -1.250 |
Token | , |
Token ID | 11 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ibaba | +0.014 |
naires | +0.013 |
unin | +0.013 |
ivo | +0.012 |
naire | +0.012 |
Neg logit contributions | |
Line | -0.012 |
Tig | -0.012 |
Beet | -0.012 |
metaphor | -0.010 |
Vide | -0.010 |
Token | India |
Token ID | 3794 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Line | +0.424 |
Tig | +0.400 |
Beet | +0.398 |
metaphor | +0.340 |
Vide | +0.334 |
Neg logit contributions | |
ibaba | -0.685 |
naires | -0.650 |
unin | -0.642 |
ivo | -0.632 |
naire | -0.628 |
Token | without |
Token ID | 1231 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ibaba | +1.229 |
naires | +1.169 |
unin | +1.145 |
ivo | +1.132 |
naire | +1.120 |
Neg logit contributions | |
Line | -1.031 |
Beet | -0.982 |
Tig | -0.981 |
Vide | -0.855 |
metaphor | -0.848 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Line | +1.122 |
Tig | +1.070 |
Beet | +1.056 |
metaphor | +0.932 |
polarized | +0.904 |
Neg logit contributions | |
ibaba | -1.545 |
naires | -1.457 |
unin | -1.439 |
ivo | -1.418 |
naire | -1.409 |
Token | bitterness |
Token ID | 35987 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Line | +0.912 |
Tig | +0.867 |
Beet | +0.862 |
metaphor | +0.755 |
polarized | +0.735 |
Neg logit contributions | |
ibaba | -1.211 |
naires | -1.141 |
unin | -1.126 |
ivo | -1.110 |
naire | -1.100 |
Token | of |
Token ID | 286 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ibaba | +0.991 |
naires | +0.937 |
unin | +0.920 |
ivo | +0.907 |
naire | +0.899 |
Neg logit contributions | |
Line | -0.804 |
Beet | -0.763 |
Tig | -0.763 |
metaphor | -0.663 |
Vide | -0.662 |
Token | p |
Token ID | 279 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
ibaba | +0.015 |
naires | +0.014 |
unin | +0.014 |
ivo | +0.014 |
naire | +0.014 |
Neg logit contributions | |
Line | -0.013 |
Tig | -0.012 |
Beet | -0.012 |
metaphor | -0.011 |
Vide | -0.010 |
Token | ith |
Token ID | 342 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
ibaba | +0.634 |
naires | +0.594 |
unin | +0.586 |
ivo | +0.575 |
naire | +0.569 |
Neg logit contributions | |
Line | -0.617 |
Tig | -0.589 |
Beet | -0.587 |
metaphor | -0.521 |
Vide | -0.515 |
Token | and |
Token ID | 290 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
Line | +2.288 |
Beet | +2.174 |
Tig | +2.160 |
metaphor | +1.887 |
wart | +1.822 |
Neg logit contributions | |
ibaba | -3.375 |
naires | -3.188 |
unin | -3.134 |
orsche | -3.083 |
naire | -3.070 |
Token | peel |
Token ID | 31738 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
Line | +0.655 |
Tig | +0.624 |
Beet | +0.621 |
metaphor | +0.547 |
Vide | +0.535 |
Neg logit contributions | |
ibaba | -0.781 |
naires | -0.736 |
unin | -0.725 |
ivo | -0.714 |
naire | -0.707 |
Token | or |
Token ID | 393 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ibaba | +0.059 |
naires | +0.055 |
unin | +0.055 |
ivo | +0.054 |
naire | +0.053 |
Neg logit contributions | |
Line | -0.043 |
Tig | -0.041 |
Beet | -0.041 |
metaphor | -0.035 |
Vide | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Line | +1.117 |
Tig | +1.064 |
Beet | +1.059 |
metaphor | +0.934 |
Vide | +0.911 |
Neg logit contributions | |
ibaba | -1.328 |
naires | -1.259 |
unin | -1.237 |
ivo | -1.216 |
naire | -1.209 |
Token | acid |
Token ID | 7408 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Line | +0.131 |
Tig | +0.124 |
Beet | +0.123 |
metaphor | +0.107 |
Vide | +0.106 |
Neg logit contributions | |
ibaba | -0.175 |
naires | -0.166 |
unin | -0.164 |
ivo | -0.161 |
naire | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
ibaba | +0.167 |
naires | +0.157 |
unin | +0.155 |
ivo | +0.153 |
naire | +0.151 |
Neg logit contributions | |
Line | -0.136 |
Tig | -0.129 |
Beet | -0.129 |
metaphor | -0.113 |
Vide | -0.111 |
Token | it |
Token ID | 340 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
ibaba | +0.080 |
naires | +0.075 |
unin | +0.075 |
ivo | +0.073 |
naire | +0.073 |
Neg logit contributions | |
Line | -0.065 |
Tig | -0.062 |
Beet | -0.062 |
metaphor | -0.054 |
Vide | -0.053 |
Token | had |
Token ID | 550 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
ibaba | +0.626 |
naires | +0.594 |
unin | +0.587 |
ivo | +0.576 |
naire | +0.572 |
Neg logit contributions | |
Line | -0.442 |
Tig | -0.418 |
Beet | -0.417 |
metaphor | -0.359 |
Vide | -0.355 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ibaba | +0.412 |
naires | +0.389 |
unin | +0.384 |
ivo | +0.377 |
naire | +0.374 |
Neg logit contributions | |
Line | -0.331 |
Tig | -0.315 |
Beet | -0.314 |
metaphor | -0.274 |
Vide | -0.271 |
Token | become |
Token ID | 1716 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
Line | +1.028 |
Tig | +0.982 |
Beet | +0.972 |
metaphor | +0.867 |
polarized | +0.855 |
Neg logit contributions | |
ibaba | -1.264 |
naires | -1.189 |
unin | -1.175 |
ivo | -1.155 |
naire | -1.145 |
Token | painfully |
Token ID | 32258 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Line | +0.572 |
Tig | +0.542 |
Beet | +0.538 |
metaphor | +0.468 |
Vide | +0.459 |
Neg logit contributions | |
ibaba | -0.807 |
naires | -0.765 |
unin | -0.755 |
ivo | -0.743 |
naire | -0.737 |
Token | apparent |
Token ID | 4156 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Line | +1.835 |
Tig | +1.749 |
Beet | +1.718 |
metaphor | +1.530 |
polarized | +1.510 |
Neg logit contributions | |
ibaba | -2.424 |
naires | -2.286 |
unin | -2.245 |
orsche | -2.215 |
ivo | -2.211 |
Token | that |
Token ID | 326 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ibaba | +0.427 |
naires | +0.404 |
unin | +0.399 |
ivo | +0.392 |
naire | +0.389 |
Neg logit contributions | |
Line | -0.326 |
Tig | -0.309 |
Beet | -0.309 |
metaphor | -0.268 |
Vide | -0.265 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Line | +0.334 |
Tig | +0.318 |
Beet | +0.316 |
metaphor | +0.278 |
Vide | +0.274 |
Neg logit contributions | |
ibaba | -0.408 |
naires | -0.384 |
unin | -0.380 |
ivo | -0.373 |
naire | -0.369 |
Token | stories |
Token ID | 3923 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ibaba | +0.156 |
naires | +0.148 |
unin | +0.145 |
ivo | +0.143 |
naire | +0.142 |
Neg logit contributions | |
Line | -0.116 |
Tig | -0.110 |
Beet | -0.110 |
metaphor | -0.095 |
Vide | -0.094 |
Token | of |
Token ID | 286 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Line | +0.264 |
Tig | +0.251 |
Beet | +0.250 |
metaphor | +0.220 |
Vide | +0.216 |
Neg logit contributions | |
ibaba | -0.333 |
naires | -0.312 |
unin | -0.309 |
ivo | -0.303 |
naire | -0.300 |
Token | from |
Token ID | 422 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Line | +0.063 |
Tig | +0.060 |
Beet | +0.059 |
metaphor | +0.052 |
Vide | +0.051 |
Neg logit contributions | |
ibaba | -0.078 |
naires | -0.073 |
unin | -0.073 |
ivo | -0.071 |
naire | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
Line | +0.150 |
Tig | +0.143 |
Beet | +0.142 |
metaphor | +0.124 |
Vide | +0.122 |
Neg logit contributions | |
ibaba | -0.192 |
naires | -0.181 |
unin | -0.178 |
ivo | -0.175 |
naire | -0.174 |
Token | rather |
Token ID | 2138 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
Line | +0.054 |
Tig | +0.052 |
Beet | +0.052 |
metaphor | +0.045 |
Vide | +0.045 |
Neg logit contributions | |
ibaba | -0.064 |
naires | -0.061 |
unin | -0.060 |
ivo | -0.059 |
naire | -0.058 |
Token | strange |
Token ID | 6283 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Line | +0.375 |
Tig | +0.357 |
Beet | +0.356 |
metaphor | +0.313 |
Vide | +0.309 |
Neg logit contributions | |
ibaba | -0.435 |
naires | -0.410 |
unin | -0.404 |
ivo | -0.397 |
naire | -0.393 |
Token | mother |
Token ID | 2802 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Line | +1.515 |
Tig | +1.441 |
Beet | +1.426 |
metaphor | +1.266 |
Passive | +1.237 |
Neg logit contributions | |
ibaba | -1.923 |
naires | -1.813 |
unin | -1.790 |
ivo | -1.747 |
naire | -1.741 |
Token | fixation |
Token ID | 48785 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
Line | +0.550 |
Tig | +0.524 |
Beet | +0.520 |
metaphor | +0.457 |
Vide | +0.447 |
Neg logit contributions | |
ibaba | -0.698 |
naires | -0.659 |
unin | -0.651 |
ivo | -0.639 |
naire | -0.633 |
Token | . |
Token ID | 13 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
Line | +1.767 |
Tig | +1.675 |
Beet | +1.650 |
metaphor | +1.449 |
wart | +1.413 |
Neg logit contributions | |
ibaba | -2.515 |
naires | -2.353 |
unin | -2.340 |
ivo | -2.295 |
orsche | -2.278 |
Token | And |
Token ID | 843 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
ibaba | +0.573 |
naires | +0.540 |
unin | +0.535 |
ivo | +0.526 |
orsche | +0.521 |
Neg logit contributions | |
Line | -0.382 |
Tig | -0.360 |
Beet | -0.360 |
metaphor | -0.307 |
Vide | -0.305 |
Token | he |
Token ID | 339 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
ibaba | +0.795 |
naires | +0.746 |
unin | +0.737 |
ivo | +0.726 |
naire | +0.718 |
Neg logit contributions | |
Line | -0.630 |
Tig | -0.598 |
Beet | -0.597 |
metaphor | -0.523 |
Vide | -0.514 |
Token | owns |
Token ID | 12216 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ibaba | +0.592 |
naires | +0.559 |
unin | +0.553 |
ivo | +0.544 |
naire | +0.539 |
Neg logit contributions | |
Line | -0.408 |
Tig | -0.386 |
Beet | -0.384 |
metaphor | -0.333 |
Vide | -0.326 |
Token | a |
Token ID | 257 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Line | +0.292 |
Beet | +0.278 |
Tig | +0.278 |
metaphor | +0.244 |
Vide | +0.241 |
Neg logit contributions | |
ibaba | -0.344 |
naires | -0.322 |
unin | -0.316 |
ivo | -0.312 |
naire | -0.310 |
Token | we |
Token ID | 356 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Line | +0.649 |
Tig | +0.618 |
Beet | +0.612 |
metaphor | +0.539 |
Vide | +0.533 |
Neg logit contributions | |
ibaba | -0.771 |
naires | -0.724 |
unin | -0.719 |
ivo | -0.706 |
naire | -0.698 |
Token | couldn |
Token ID | 3521 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
Line | +0.543 |
Tig | +0.513 |
Beet | +0.510 |
metaphor | +0.441 |
Vide | +0.433 |
Neg logit contributions | |
ibaba | -0.806 |
naires | -0.763 |
unin | -0.755 |
ivo | -0.742 |
naire | -0.736 |
Token | 't |
Token ID | 470 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Line | +0.485 |
Tig | +0.461 |
Beet | +0.457 |
metaphor | +0.405 |
Vide | +0.400 |
Neg logit contributions | |
ibaba | -0.544 |
naires | -0.507 |
unin | -0.502 |
ivo | -0.491 |
orsche | -0.489 |
Token | resist |
Token ID | 4180 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ibaba | +1.149 |
naires | +1.096 |
unin | +1.082 |
ivo | +1.067 |
naire | +1.058 |
Neg logit contributions | |
Line | -0.829 |
Beet | -0.790 |
Tig | -0.788 |
Vide | -0.672 |
Passive | -0.669 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Line | +1.269 |
Tig | +1.202 |
Beet | +1.192 |
metaphor | +1.044 |
Vide | +1.025 |
Neg logit contributions | |
ibaba | -1.727 |
naires | -1.627 |
unin | -1.618 |
ivo | -1.584 |
naire | -1.571 |
Token | temptation |
Token ID | 29062 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Line | +0.861 |
Tig | +0.814 |
Beet | +0.809 |
metaphor | +0.700 |
Vide | +0.685 |
Neg logit contributions | |
ibaba | -1.292 |
naires | -1.224 |
unin | -1.210 |
ivo | -1.190 |
naire | -1.180 |
Token | to |
Token ID | 284 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Line | +2.111 |
Tig | +1.997 |
Beet | +1.973 |
metaphor | +1.760 |
Vide | +1.717 |
Neg logit contributions | |
ibaba | -2.656 |
naires | -2.489 |
unin | -2.481 |
ivo | -2.428 |
orsche | -2.405 |
Token | recall |
Token ID | 10014 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Line | +0.186 |
Tig | +0.177 |
Beet | +0.176 |
metaphor | +0.153 |
Vide | +0.151 |
Neg logit contributions | |
ibaba | -0.247 |
naires | -0.233 |
unin | -0.230 |
ivo | -0.226 |
naire | -0.225 |
Token | 1974 |
Token ID | 16489 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
ibaba | +0.041 |
naires | +0.038 |
unin | +0.038 |
ivo | +0.037 |
naire | +0.037 |
Neg logit contributions | |
Line | -0.036 |
Tig | -0.034 |
Beet | -0.034 |
metaphor | -0.030 |
Vide | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ibaba | +0.801 |
naires | +0.760 |
unin | +0.750 |
ivo | +0.738 |
naire | +0.732 |
Neg logit contributions | |
Line | -0.577 |
Tig | -0.550 |
Beet | -0.547 |
metaphor | -0.473 |
Passive | -0.466 |
Token | masterpiece |
Token ID | 30669 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Line | +0.188 |
Tig | +0.177 |
Beet | +0.176 |
metaphor | +0.151 |
Vide | +0.149 |
Neg logit contributions | |
ibaba | -0.286 |
naires | -0.271 |
unin | -0.268 |
ivo | -0.264 |
naire | -0.262 |