Token | Washington |
Token ID | 2669 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
helium | +0.429 |
apo | +0.416 |
Amen | +0.415 |
Cassidy | +0.411 |
Hert | +0.398 |
Neg logit contributions | |
cli | -0.517 |
�� | -0.514 |
ette | -0.461 |
� | -0.457 |
� | -0.448 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
cli | +0.488 |
�� | +0.478 |
� | +0.430 |
ette | +0.428 |
� | +0.418 |
Neg logit contributions | |
helium | -0.523 |
apo | -0.515 |
Amen | -0.500 |
Cassidy | -0.500 |
Hert | -0.480 |
Token | D |
Token ID | 360 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
helium | +0.396 |
apo | +0.386 |
Cassidy | +0.379 |
Amen | +0.378 |
Hert | +0.363 |
Neg logit contributions | |
cli | -0.414 |
�� | -0.407 |
ette | -0.366 |
� | -0.364 |
� | -0.355 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
cli | +0.446 |
�� | +0.441 |
� | +0.394 |
ette | +0.392 |
� | +0.380 |
Neg logit contributions | |
helium | -0.489 |
apo | -0.482 |
Amen | -0.469 |
Cassidy | -0.467 |
Hert | -0.450 |
Token | C |
Token ID | 34 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
helium | +0.085 |
apo | +0.083 |
Amen | +0.081 |
Cassidy | +0.081 |
Hert | +0.078 |
Neg logit contributions | |
cli | -0.081 |
�� | -0.080 |
ette | -0.071 |
� | -0.071 |
ngth | -0.069 |
Token | .) |
Token ID | 2014 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
cli | +1.618 |
�� | +1.591 |
� | +1.473 |
ette | +1.458 |
� | +1.441 |
Neg logit contributions | |
helium | -1.533 |
apo | -1.505 |
Amen | -1.470 |
Cassidy | -1.462 |
Hert | -1.399 |
Token | What |
Token ID | 1867 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
helium | +2.356 |
Amen | +2.270 |
apo | +2.250 |
Cassidy | +2.212 |
Hert | +2.128 |
Neg logit contributions | |
�� | -3.899 |
cli | -3.884 |
ette | -3.514 |
� | -3.440 |
ngth | -3.409 |
Token | is |
Token ID | 318 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
cli | +0.533 |
�� | +0.530 |
ette | +0.475 |
� | +0.471 |
� | +0.453 |
Neg logit contributions | |
helium | -0.543 |
apo | -0.531 |
Amen | -0.518 |
Cassidy | -0.514 |
Hert | -0.499 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
helium | +0.187 |
apo | +0.181 |
Amen | +0.176 |
Cassidy | +0.175 |
Hert | +0.169 |
Neg logit contributions | |
cli | -0.242 |
�� | -0.237 |
ette | -0.217 |
� | -0.214 |
� | -0.209 |
Token | cart |
Token ID | 6383 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
cli | +0.276 |
�� | +0.271 |
ette | +0.248 |
� | +0.247 |
� | +0.242 |
Neg logit contributions | |
helium | -0.212 |
apo | -0.207 |
Amen | -0.200 |
Cassidy | -0.199 |
Hert | -0.192 |
Token | ographer |
Token ID | 18539 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
cli | +0.014 |
�� | +0.014 |
� | +0.013 |
ette | +0.013 |
� | +0.013 |
Neg logit contributions | |
helium | -0.005 |
apo | -0.005 |
Cassidy | -0.005 |
Amen | -0.005 |
Hert | -0.004 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
cli | +0.832 |
�� | +0.818 |
� | +0.747 |
ette | +0.739 |
� | +0.723 |
Neg logit contributions | |
helium | -0.909 |
apo | -0.899 |
Amen | -0.873 |
Cassidy | -0.870 |
Hert | -0.838 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
cli | +1.120 |
�� | +1.100 |
� | +1.013 |
ette | +1.004 |
� | +0.984 |
Neg logit contributions | |
helium | -0.995 |
apo | -0.984 |
Amen | -0.955 |
Cassidy | -0.953 |
Hert | -0.915 |
Token | 7 |
Token ID | 767 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
cli | +0.504 |
�� | +0.496 |
� | +0.456 |
ette | +0.452 |
� | +0.444 |
Neg logit contributions | |
helium | -0.451 |
apo | -0.446 |
Cassidy | -0.431 |
Amen | -0.430 |
Hert | -0.413 |
Token | 8 |
Token ID | 807 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
cli | +0.261 |
�� | +0.256 |
� | +0.230 |
ette | +0.228 |
� | +0.223 |
Neg logit contributions | |
helium | -0.303 |
apo | -0.297 |
Amen | -0.290 |
Cassidy | -0.289 |
Hert | -0.278 |
Token | void |
Token ID | 7951 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
cli | +0.631 |
�� | +0.617 |
� | +0.574 |
ette | +0.570 |
� | +0.557 |
Neg logit contributions | |
helium | -0.577 |
apo | -0.570 |
Cassidy | -0.551 |
Amen | -0.550 |
Hert | -0.526 |
Token | vert |
Token ID | 9421 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
helium | +0.300 |
apo | +0.275 |
Cassidy | +0.267 |
Amen | +0.264 |
Hert | +0.255 |
Neg logit contributions | |
cli | -0.623 |
�� | -0.622 |
ette | -0.564 |
ngth | -0.560 |
� | -0.558 |
Token | ( |
Token ID | 357 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
helium | +2.819 |
Cassidy | +2.746 |
Amen | +2.733 |
apo | +2.724 |
Hert | +2.635 |
Neg logit contributions | |
�� | -3.529 |
cli | -3.337 |
ngth | -3.061 |
ette | -2.833 |
ettings | -2.819 |
Token | in |
Token ID | 287 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
helium | +0.411 |
apo | +0.402 |
Amen | +0.389 |
Cassidy | +0.388 |
Hert | +0.372 |
Neg logit contributions | |
cli | -0.497 |
�� | -0.492 |
� | -0.447 |
ette | -0.447 |
� | -0.437 |
Token | out |
Token ID | 448 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
helium | +0.538 |
apo | +0.536 |
Amen | +0.517 |
Cassidy | +0.509 |
Hert | +0.488 |
Neg logit contributions | |
�� | -0.716 |
cli | -0.704 |
� | -0.630 |
ette | -0.625 |
� | -0.613 |
Token | app |
Token ID | 598 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
helium | +0.190 |
apo | +0.183 |
Amen | +0.180 |
Cassidy | +0.179 |
Hert | +0.172 |
Neg logit contributions | |
�� | -0.203 |
cli | -0.200 |
ette | -0.177 |
ngth | -0.177 |
� | -0.174 |
Token | data |
Token ID | 7890 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
�� | +0.038 |
cli | +0.035 |
� | +0.030 |
ngth | +0.029 |
ette | +0.029 |
Neg logit contributions | |
apo | -0.072 |
helium | -0.071 |
Cassidy | -0.069 |
Amen | -0.069 |
Hert | -0.066 |
Token | ak |
Token ID | 461 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
cli | +0.348 |
�� | +0.344 |
� | +0.304 |
ette | +0.302 |
� | +0.291 |
Neg logit contributions | |
helium | -0.448 |
apo | -0.448 |
Amen | -0.437 |
Cassidy | -0.434 |
Hert | -0.419 |
Token | at |
Token ID | 265 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
cli | +0.317 |
�� | +0.312 |
� | +0.277 |
ette | +0.274 |
� | +0.267 |
Neg logit contributions | |
helium | -0.410 |
apo | -0.404 |
Amen | -0.395 |
Cassidy | -0.394 |
Hert | -0.380 |
Token | al |
Token ID | 435 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
cli | +0.177 |
�� | +0.176 |
ette | +0.159 |
� | +0.158 |
� | +0.154 |
Neg logit contributions | |
helium | -0.143 |
apo | -0.141 |
Amen | -0.138 |
Cassidy | -0.137 |
Hert | -0.131 |
Token | - |
Token ID | 12 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
cli | +0.199 |
�� | +0.194 |
ette | +0.173 |
� | +0.172 |
� | +0.166 |
Neg logit contributions | |
helium | -0.261 |
apo | -0.257 |
Amen | -0.253 |
Cassidy | -0.252 |
Hert | -0.243 |
Token | N |
Token ID | 45 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
helium | +0.765 |
apo | +0.755 |
Amen | +0.742 |
Cassidy | +0.734 |
Hert | +0.701 |
Neg logit contributions | |
cli | -0.912 |
�� | -0.902 |
ette | -0.819 |
� | -0.816 |
� | -0.785 |
Token | uj |
Token ID | 23577 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
apo | +0.125 |
helium | +0.125 |
Amen | +0.120 |
Cassidy | +0.119 |
Hert | +0.114 |
Neg logit contributions | |
�� | -0.128 |
cli | -0.127 |
� | -0.114 |
ette | -0.112 |
� | -0.109 |
Token | aba |
Token ID | 15498 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
apo | +2.631 |
helium | +2.555 |
Amen | +2.456 |
Cassidy | +2.453 |
Hert | +2.340 |
Neg logit contributions | |
�� | -3.068 |
cli | -2.972 |
� | -2.694 |
ette | -2.599 |
ngth | -2.562 |
Token | , |
Token ID | 11 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
helium | +0.571 |
apo | +0.570 |
Amen | +0.554 |
Cassidy | +0.551 |
Hert | +0.534 |
Neg logit contributions | |
cli | -0.423 |
�� | -0.419 |
ette | -0.361 |
� | -0.357 |
ngth | -0.348 |
Token | said |
Token ID | 531 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
helium | +0.263 |
apo | +0.258 |
Amen | +0.252 |
Cassidy | +0.252 |
Hert | +0.240 |
Neg logit contributions | |
cli | -0.352 |
�� | -0.349 |
ette | -0.316 |
� | -0.313 |
� | -0.306 |
Token | it |
Token ID | 340 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
helium | +0.397 |
apo | +0.387 |
Cassidy | +0.381 |
Amen | +0.381 |
Hert | +0.364 |
Neg logit contributions | |
cli | -0.478 |
�� | -0.476 |
ette | -0.425 |
� | -0.422 |
� | -0.412 |
Token | had |
Token ID | 550 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
cli | +0.356 |
�� | +0.353 |
ette | +0.315 |
� | +0.311 |
� | +0.301 |
Neg logit contributions | |
helium | -0.346 |
apo | -0.343 |
Cassidy | -0.334 |
Amen | -0.332 |
Hert | -0.319 |
Token | origin |
Token ID | 8159 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
helium | +0.468 |
apo | +0.458 |
Amen | +0.451 |
Cassidy | +0.447 |
Hert | +0.428 |
Neg logit contributions | |
cli | -0.432 |
�� | -0.427 |
� | -0.378 |
ette | -0.378 |
� | -0.367 |
Token | el |
Token ID | 417 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
helium | +1.370 |
apo | +1.355 |
Amen | +1.310 |
Cassidy | +1.306 |
Hert | +1.255 |
Neg logit contributions | |
�� | -1.130 |
cli | -1.120 |
� | -0.985 |
ette | -0.957 |
� | -0.936 |
Token | des |
Token ID | 748 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
cli | +0.269 |
�� | +0.266 |
� | +0.238 |
ette | +0.237 |
� | +0.231 |
Neg logit contributions | |
helium | -0.268 |
apo | -0.262 |
Amen | -0.257 |
Cassidy | -0.255 |
Hert | -0.244 |
Token | Cors |
Token ID | 26978 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
helium | +0.517 |
apo | +0.497 |
Amen | +0.492 |
Cassidy | +0.488 |
Hert | +0.467 |
Neg logit contributions | |
cli | -0.544 |
�� | -0.541 |
ette | -0.483 |
� | -0.479 |
� | -0.467 |
Token | aires |
Token ID | 17693 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
helium | +0.504 |
apo | +0.499 |
Amen | +0.488 |
Cassidy | +0.484 |
Hert | +0.468 |
Neg logit contributions | |
cli | -0.350 |
�� | -0.345 |
� | -0.303 |
ette | -0.299 |
� | -0.290 |
Token | [...] |
Token ID | 26894 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
helium | +0.247 |
apo | +0.239 |
Amen | +0.237 |
Cassidy | +0.234 |
Hert | +0.226 |
Neg logit contributions | |
cli | -0.249 |
�� | -0.247 |
ette | -0.219 |
� | -0.218 |
� | -0.212 |
Token | En |
Token ID | 2039 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
helium | +2.772 |
Amen | +2.710 |
apo | +2.656 |
Cassidy | +2.639 |
Hert | +2.548 |
Neg logit contributions | |
cli | -2.869 |
�� | -2.860 |
ette | -2.522 |
� | -2.474 |
ngth | -2.456 |
Token | cas |
Token ID | 6124 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
helium | +0.335 |
apo | +0.326 |
Amen | +0.320 |
Cassidy | +0.318 |
Hert | +0.305 |
Neg logit contributions | |
cli | -0.359 |
�� | -0.358 |
ette | -0.321 |
� | -0.321 |
� | -0.313 |
Token | de |
Token ID | 390 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
helium | +0.455 |
apo | +0.446 |
Amen | +0.437 |
Cassidy | +0.432 |
Hert | +0.415 |
Neg logit contributions | |
cli | -0.456 |
�� | -0.455 |
� | -0.403 |
ette | -0.399 |
� | -0.392 |
Token | d |
Token ID | 288 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
cli | +0.985 |
�� | +0.973 |
� | +0.881 |
ette | +0.880 |
� | +0.859 |
Neg logit contributions | |
helium | -0.931 |
apo | -0.909 |
Amen | -0.888 |
Cassidy | -0.885 |
Hert | -0.850 |
Token | és |
Token ID | 20954 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
helium | +0.062 |
apo | +0.061 |
Amen | +0.060 |
Cassidy | +0.059 |
Hert | +0.057 |
Neg logit contributions | |
cli | -0.054 |
�� | -0.053 |
� | -0.048 |
ette | -0.047 |
� | -0.045 |
Token | up |
Token ID | 510 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
cli | +0.239 |
�� | +0.234 |
ette | +0.211 |
� | +0.211 |
� | +0.205 |
Neg logit contributions | |
helium | -0.232 |
apo | -0.225 |
Amen | -0.222 |
Cassidy | -0.221 |
Hert | -0.212 |
Token | short |
Token ID | 1790 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
cli | +0.819 |
�� | +0.807 |
� | +0.739 |
ette | +0.737 |
� | +0.721 |
Neg logit contributions | |
helium | -0.643 |
apo | -0.627 |
Amen | -0.609 |
Cassidy | -0.608 |
Hert | -0.581 |
Token | . |
Token ID | 13 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
helium | +0.269 |
apo | +0.262 |
Amen | +0.257 |
Cassidy | +0.257 |
Hert | +0.246 |
Neg logit contributions | |
cli | -0.268 |
�� | -0.265 |
ette | -0.236 |
� | -0.234 |
� | -0.227 |
Token | Does |
Token ID | 8314 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
cli | +0.075 |
�� | +0.075 |
ette | +0.067 |
� | +0.067 |
� | +0.065 |
Neg logit contributions | |
helium | -0.050 |
apo | -0.049 |
Amen | -0.049 |
Cassidy | -0.049 |
Hert | -0.046 |
Token | that |
Token ID | 326 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
cli | +0.802 |
�� | +0.790 |
� | +0.714 |
ette | +0.714 |
� | +0.695 |
Neg logit contributions | |
helium | -0.740 |
apo | -0.725 |
Amen | -0.707 |
Cassidy | -0.705 |
Hert | -0.677 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
helium | +0.407 |
apo | +0.393 |
Amen | +0.387 |
Cassidy | +0.385 |
Hert | +0.370 |
Neg logit contributions | |
cli | -0.420 |
�� | -0.417 |
ette | -0.373 |
� | -0.366 |
ngth | -0.355 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
helium | +2.456 |
Amen | +2.393 |
apo | +2.378 |
Cassidy | +2.360 |
Hert | +2.254 |
Neg logit contributions | |
cli | -3.010 |
�� | -2.963 |
ette | -2.639 |
ngth | -2.607 |
� | -2.597 |
Token | can |
Token ID | 460 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
cli | +0.912 |
�� | +0.897 |
ette | +0.803 |
� | +0.802 |
� | +0.776 |
Neg logit contributions | |
helium | -1.002 |
apo | -0.981 |
Cassidy | -0.957 |
Amen | -0.957 |
Hert | -0.920 |
Token | get |
Token ID | 651 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
cli | +0.237 |
�� | +0.233 |
ette | +0.211 |
� | +0.209 |
� | +0.202 |
Neg logit contributions | |
helium | -0.222 |
apo | -0.215 |
Amen | -0.211 |
Cassidy | -0.210 |
Hert | -0.202 |
Token | back |
Token ID | 736 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
helium | +0.117 |
apo | +0.114 |
Amen | +0.112 |
Cassidy | +0.112 |
Hert | +0.107 |
Neg logit contributions | |
cli | -0.126 |
�� | -0.123 |
ette | -0.111 |
� | -0.111 |
� | -0.108 |
Token | ? |
Token ID | 30 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
helium | +1.524 |
apo | +1.467 |
Amen | +1.458 |
Cassidy | +1.456 |
Hert | +1.383 |
Neg logit contributions | |
cli | -1.595 |
�� | -1.553 |
ette | -1.393 |
� | -1.365 |
� | -1.320 |
Token | into |
Token ID | 656 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
cli | +0.507 |
�� | +0.502 |
ette | +0.447 |
� | +0.444 |
� | +0.432 |
Neg logit contributions | |
helium | -0.450 |
apo | -0.430 |
Amen | -0.427 |
Cassidy | -0.426 |
Hert | -0.405 |
Token | them |
Token ID | 606 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
cli | +0.528 |
�� | +0.518 |
ette | +0.466 |
� | +0.465 |
� | +0.452 |
Neg logit contributions | |
helium | -0.520 |
apo | -0.504 |
Amen | -0.498 |
Cassidy | -0.495 |
Hert | -0.477 |
Token | ". |
Token ID | 1911 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
helium | +0.003 |
apo | +0.003 |
Amen | +0.003 |
Cassidy | +0.003 |
Hert | +0.003 |
Neg logit contributions | |
cli | -0.003 |
�� | -0.003 |
ette | -0.003 |
� | -0.003 |
� | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
�� | +0.078 |
cli | +0.078 |
� | +0.071 |
ette | +0.071 |
� | +0.070 |
Neg logit contributions | |
helium | -0.036 |
apo | -0.036 |
Amen | -0.034 |
Cassidy | -0.034 |
Hert | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
helium | +0.046 |
apo | +0.045 |
Amen | +0.043 |
Cassidy | +0.043 |
Hert | +0.041 |
Neg logit contributions | |
�� | -0.101 |
cli | -0.100 |
ette | -0.091 |
� | -0.091 |
ngth | -0.090 |
Token | Topics |
Token ID | 25902 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
apo | +0.213 |
helium | +0.213 |
Amen | +0.204 |
Cassidy | +0.203 |
Hert | +0.195 |
Neg logit contributions | |
�� | -0.240 |
cli | -0.239 |
� | -0.217 |
ette | -0.213 |
ngth | -0.208 |
Token | : |
Token ID | 25 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
helium | +2.311 |
apo | +2.230 |
Amen | +2.227 |
Cassidy | +2.217 |
Hert | +2.121 |
Neg logit contributions | |
�� | -3.165 |
cli | -3.027 |
ette | -2.722 |
� | -2.702 |
ngth | -2.699 |
Token | marine |
Token ID | 16050 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
cli | +0.100 |
�� | +0.099 |
ette | +0.090 |
� | +0.089 |
� | +0.087 |
Neg logit contributions | |
helium | -0.087 |
apo | -0.083 |
Cassidy | -0.082 |
Amen | -0.081 |
Hert | -0.078 |
Token | - |
Token ID | 12 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
cli | +0.631 |
�� | +0.617 |
� | +0.540 |
ette | +0.537 |
� | +0.521 |
Neg logit contributions | |
helium | -1.014 |
apo | -0.996 |
Amen | -0.974 |
Cassidy | -0.973 |
Hert | -0.944 |
Token | biology |
Token ID | 43592 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
cli | +1.304 |
�� | +1.267 |
ette | +1.174 |
� | +1.172 |
� | +1.150 |
Neg logit contributions | |
helium | -1.051 |
apo | -1.023 |
Amen | -0.999 |
Cassidy | -0.996 |
Hert | -0.951 |
Token | , |
Token ID | 11 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
�� | +0.265 |
cli | +0.252 |
ngth | +0.218 |
ette | +0.213 |
� | +0.210 |
Neg logit contributions | |
helium | -0.370 |
apo | -0.360 |
Amen | -0.355 |
Cassidy | -0.354 |
Hert | -0.346 |
Token |
|
Token ID | 198 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
helium | +0.140 |
apo | +0.136 |
Amen | +0.133 |
Cassidy | +0.131 |
Hert | +0.123 |
Neg logit contributions | |
�� | -0.312 |
cli | -0.308 |
� | -0.281 |
ette | -0.281 |
ngth | -0.278 |
Token | " |
Token ID | 1 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
helium | +0.187 |
apo | +0.186 |
Amen | +0.180 |
Cassidy | +0.178 |
Hert | +0.173 |
Neg logit contributions | |
cli | -0.189 |
�� | -0.189 |
� | -0.169 |
ette | -0.168 |
ngth | -0.163 |
Token | What |
Token ID | 2061 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
cli | +0.259 |
�� | +0.257 |
� | +0.232 |
ette | +0.231 |
� | +0.225 |
Neg logit contributions | |
helium | -0.222 |
apo | -0.219 |
Amen | -0.213 |
Cassidy | -0.211 |
Hert | -0.204 |
Token | does |
Token ID | 857 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
cli | +0.069 |
�� | +0.068 |
� | +0.060 |
ette | +0.060 |
� | +0.058 |
Neg logit contributions | |
helium | -0.076 |
apo | -0.075 |
Amen | -0.074 |
Cassidy | -0.073 |
Hert | -0.071 |
Token | it |
Token ID | 340 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
cli | +0.325 |
�� | +0.318 |
� | +0.289 |
ette | +0.289 |
� | +0.282 |
Neg logit contributions | |
helium | -0.291 |
apo | -0.283 |
Amen | -0.277 |
Cassidy | -0.276 |
Hert | -0.266 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
helium | +0.686 |
apo | +0.669 |
Amen | +0.653 |
Cassidy | +0.652 |
Hert | +0.636 |
Neg logit contributions | |
�� | -0.614 |
cli | -0.613 |
ette | -0.535 |
� | -0.534 |
� | -0.513 |
Token | to |
Token ID | 284 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
helium | +2.698 |
apo | +2.637 |
Amen | +2.597 |
Cassidy | +2.544 |
Hert | +2.505 |
Neg logit contributions | |
cli | -2.713 |
�� | -2.688 |
ette | -2.341 |
� | -2.336 |
ngth | -2.268 |
Token | an |
Token ID | 281 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
helium | +0.424 |
apo | +0.411 |
Amen | +0.405 |
Cassidy | +0.401 |
Hert | +0.391 |
Neg logit contributions | |
cli | -0.426 |
�� | -0.419 |
ette | -0.376 |
� | -0.372 |
� | -0.363 |
Token | intro |
Token ID | 18951 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
cli | +0.265 |
�� | +0.257 |
� | +0.234 |
ette | +0.234 |
� | +0.229 |
Neg logit contributions | |
helium | -0.229 |
apo | -0.226 |
Amen | -0.220 |
Cassidy | -0.217 |
Hert | -0.209 |
Token | vert |
Token ID | 1851 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
helium | +0.779 |
apo | +0.774 |
Amen | +0.754 |
Cassidy | +0.747 |
Hert | +0.734 |
Neg logit contributions | |
cli | -0.460 |
�� | -0.447 |
� | -0.387 |
ette | -0.383 |
� | -0.366 |
Token | online |
Token ID | 2691 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
helium | +0.044 |
apo | +0.043 |
Amen | +0.042 |
Cassidy | +0.041 |
Hert | +0.040 |
Neg logit contributions | |
cli | -0.042 |
�� | -0.041 |
ette | -0.037 |
� | -0.037 |
� | -0.035 |
Token | ready |
Token ID | 3492 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
helium | +0.308 |
apo | +0.300 |
Amen | +0.292 |
Cassidy | +0.292 |
Hert | +0.278 |
Neg logit contributions | |
cli | -0.342 |
�� | -0.337 |
ette | -0.304 |
� | -0.302 |
� | -0.294 |
Token | made |
Token ID | 925 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
helium | +0.038 |
apo | +0.037 |
Amen | +0.036 |
Cassidy | +0.036 |
Hert | +0.035 |
Neg logit contributions | |
cli | -0.033 |
�� | -0.032 |
� | -0.029 |
ette | -0.029 |
� | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
cli | +0.254 |
�� | +0.250 |
ette | +0.224 |
� | +0.223 |
� | +0.218 |
Neg logit contributions | |
helium | -0.253 |
apo | -0.247 |
Amen | -0.242 |
Cassidy | -0.241 |
Hert | -0.231 |
Token | have |
Token ID | 423 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
cli | +0.151 |
�� | +0.149 |
ette | +0.134 |
� | +0.134 |
� | +0.131 |
Neg logit contributions | |
helium | -0.141 |
apo | -0.137 |
Amen | -0.134 |
Cassidy | -0.133 |
Hert | -0.128 |
Token | somebody |
Token ID | 8276 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
cli | +0.402 |
�� | +0.394 |
ette | +0.358 |
� | +0.358 |
� | +0.349 |
Neg logit contributions | |
helium | -0.366 |
apo | -0.358 |
Amen | -0.349 |
Cassidy | -0.349 |
Hert | -0.334 |
Token | add |
Token ID | 751 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
helium | +0.418 |
apo | +0.402 |
Cassidy | +0.397 |
Amen | +0.397 |
Hert | +0.377 |
Neg logit contributions | |
cli | -0.467 |
�� | -0.463 |
� | -0.410 |
ette | -0.409 |
� | -0.398 |
Token | in |
Token ID | 287 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
helium | +2.571 |
apo | +2.436 |
Amen | +2.429 |
Cassidy | +2.421 |
Hert | +2.314 |
Neg logit contributions | |
cli | -2.867 |
�� | -2.805 |
ette | -2.536 |
� | -2.472 |
� | -2.458 |
Token | sn |
Token ID | 3013 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
helium | +0.489 |
apo | +0.476 |
Amen | +0.466 |
Cassidy | +0.464 |
Hert | +0.445 |
Neg logit contributions | |
cli | -0.527 |
�� | -0.518 |
ette | -0.464 |
� | -0.461 |
� | -0.454 |
Token | ark |
Token ID | 668 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
apo | +1.165 |
helium | +1.154 |
Amen | +1.114 |
Cassidy | +1.104 |
Hert | +1.069 |
Neg logit contributions | |
cli | -0.992 |
�� | -0.992 |
� | -0.881 |
ette | -0.859 |
� | -0.835 |
Token | y |
Token ID | 88 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
cli | +1.467 |
�� | +1.435 |
� | +1.309 |
ette | +1.300 |
� | +1.271 |
Neg logit contributions | |
helium | -1.623 |
apo | -1.595 |
Amen | -1.554 |
Cassidy | -1.551 |
Hert | -1.496 |
Token | commentary |
Token ID | 14604 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
helium | +0.739 |
apo | +0.712 |
Amen | +0.704 |
Cassidy | +0.700 |
Hert | +0.673 |
Neg logit contributions | |
cli | -0.772 |
�� | -0.761 |
ette | -0.679 |
� | -0.673 |
� | -0.662 |
Token | let |
Token ID | 1309 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
helium | +0.409 |
apo | +0.398 |
Cassidy | +0.390 |
Amen | +0.390 |
Hert | +0.371 |
Neg logit contributions | |
cli | -0.464 |
�� | -0.456 |
ette | -0.412 |
� | -0.410 |
� | -0.397 |
Token | � |
Token ID | 447 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
helium | +0.167 |
apo | +0.164 |
Amen | +0.158 |
Cassidy | +0.158 |
Hert | +0.151 |
Neg logit contributions | |
cli | -0.219 |
�� | -0.216 |
ette | -0.198 |
� | -0.197 |
� | -0.191 |
Token | � |
Token ID | 247 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
helium | +0.402 |
apo | +0.392 |
Amen | +0.380 |
Cassidy | +0.378 |
Hert | +0.360 |
Neg logit contributions | |
cli | -0.646 |
�� | -0.621 |
ette | -0.589 |
� | -0.585 |
� | -0.573 |
Token | s |
Token ID | 82 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
helium | +0.224 |
apo | +0.223 |
Amen | +0.216 |
Cassidy | +0.213 |
Hert | +0.206 |
Neg logit contributions | |
�� | -0.231 |
cli | -0.229 |
� | -0.206 |
ette | -0.203 |
� | -0.198 |
Token | look |
Token ID | 804 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
helium | +0.193 |
apo | +0.189 |
Amen | +0.183 |
Cassidy | +0.181 |
Hert | +0.175 |
Neg logit contributions | |
cli | -0.231 |
�� | -0.229 |
ette | -0.206 |
� | -0.204 |
� | -0.198 |
Token | back |
Token ID | 736 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
helium | +0.581 |
apo | +0.566 |
Amen | +0.549 |
Cassidy | +0.547 |
Hert | +0.518 |
Neg logit contributions | |
cli | -0.893 |
�� | -0.883 |
ette | -0.812 |
� | -0.807 |
� | -0.787 |
Token | on |
Token ID | 319 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
helium | +2.129 |
apo | +2.017 |
Cassidy | +1.995 |
Amen | +1.984 |
Hert | +1.881 |
Neg logit contributions | |
cli | -3.196 |
�� | -3.181 |
ette | -2.892 |
� | -2.833 |
ngth | -2.771 |
Token | recent |
Token ID | 2274 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
helium | +0.795 |
apo | +0.769 |
Cassidy | +0.762 |
Amen | +0.761 |
Hert | +0.732 |
Neg logit contributions | |
cli | -0.849 |
�� | -0.836 |
ette | -0.757 |
� | -0.741 |
ngth | -0.726 |
Token | history |
Token ID | 2106 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
cli | +0.418 |
�� | +0.409 |
ette | +0.370 |
� | +0.366 |
� | +0.360 |
Neg logit contributions | |
helium | -0.370 |
apo | -0.358 |
Cassidy | -0.352 |
Amen | -0.351 |
Hert | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
helium | +0.092 |
apo | +0.089 |
Cassidy | +0.088 |
Amen | +0.088 |
Hert | +0.084 |
Neg logit contributions | |
cli | -0.086 |
�� | -0.085 |
ette | -0.076 |
� | -0.074 |
� | -0.072 |
Token | for |
Token ID | 329 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
helium | +0.797 |
apo | +0.775 |
Cassidy | +0.762 |
Amen | +0.759 |
Hert | +0.727 |
Neg logit contributions | |
cli | -0.876 |
�� | -0.865 |
ette | -0.778 |
� | -0.766 |
ngth | -0.747 |
Token | go |
Token ID | 467 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
helium | +0.278 |
apo | +0.269 |
Amen | +0.262 |
Cassidy | +0.260 |
Hert | +0.251 |
Neg logit contributions | |
cli | -0.319 |
�� | -0.314 |
ette | -0.284 |
� | -0.284 |
� | -0.276 |
Token | sour |
Token ID | 11348 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
cli | +0.486 |
�� | +0.479 |
� | +0.434 |
ette | +0.432 |
� | +0.422 |
Neg logit contributions | |
helium | -0.459 |
apo | -0.448 |
Amen | -0.435 |
Cassidy | -0.435 |
Hert | -0.417 |
Token | ." |
Token ID | 526 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
helium | +1.035 |
apo | +1.014 |
Amen | +0.980 |
Cassidy | +0.980 |
Hert | +0.941 |
Neg logit contributions | |
cli | -1.054 |
�� | -1.037 |
� | -0.934 |
ette | -0.924 |
� | -0.906 |
Token | Does |
Token ID | 8314 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
helium | +0.144 |
Amen | +0.140 |
apo | +0.140 |
Cassidy | +0.139 |
Hert | +0.133 |
Neg logit contributions | |
cli | -0.211 |
�� | -0.210 |
ette | -0.189 |
� | -0.188 |
� | -0.183 |
Token | that |
Token ID | 326 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
cli | +0.498 |
�� | +0.490 |
� | +0.446 |
ette | +0.445 |
� | +0.436 |
Neg logit contributions | |
helium | -0.426 |
apo | -0.416 |
Amen | -0.405 |
Cassidy | -0.403 |
Hert | -0.388 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
helium | +0.559 |
apo | +0.539 |
Amen | +0.532 |
Cassidy | +0.529 |
Hert | +0.512 |
Neg logit contributions | |
cli | -0.536 |
�� | -0.533 |
ette | -0.472 |
� | -0.468 |
� | -0.453 |
Token | that |
Token ID | 326 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
helium | +2.455 |
apo | +2.332 |
Amen | +2.313 |
Cassidy | +2.307 |
Hert | +2.253 |
Neg logit contributions | |
cli | -2.920 |
�� | -2.867 |
ette | -2.588 |
� | -2.530 |
ngth | -2.524 |
Token | all |
Token ID | 477 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
helium | +0.008 |
apo | +0.008 |
Amen | +0.008 |
Cassidy | +0.008 |
Hert | +0.007 |
Neg logit contributions | |
cli | -0.010 |
�� | -0.010 |
ette | -0.009 |
� | -0.009 |
� | -0.009 |
Token | Got |
Token ID | 11853 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
cli | +0.287 |
�� | +0.282 |
ette | +0.256 |
� | +0.255 |
� | +0.249 |
Neg logit contributions | |
helium | -0.265 |
apo | -0.257 |
Amen | -0.251 |
Cassidy | -0.251 |
Hert | -0.242 |
Token | lands |
Token ID | 4447 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
cli | +0.549 |
�� | +0.545 |
� | +0.488 |
ette | +0.482 |
� | +0.472 |
Neg logit contributions | |
helium | -0.611 |
apo | -0.601 |
Amen | -0.587 |
Cassidy | -0.582 |
Hert | -0.565 |
Token | d |
Token ID | 67 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
cli | +0.967 |
�� | +0.949 |
� | +0.867 |
ette | +0.864 |
� | +0.845 |
Neg logit contributions | |
helium | -0.833 |
apo | -0.816 |
Amen | -0.791 |
Cassidy | -0.789 |
Hert | -0.758 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
helium | +0.826 |
apo | +0.799 |
Cassidy | +0.795 |
Amen | +0.787 |
Hert | +0.759 |
Neg logit contributions | |
cli | -0.852 |
�� | -0.847 |
ette | -0.755 |
� | -0.743 |
ngth | -0.732 |
Token | that |
Token ID | 326 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
helium | +0.307 |
apo | +0.299 |
Cassidy | +0.296 |
Amen | +0.295 |
Hert | +0.283 |
Neg logit contributions | |
cli | -0.319 |
�� | -0.314 |
ette | -0.279 |
� | -0.275 |
� | -0.269 |
Token | he |
Token ID | 339 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
helium | +0.425 |
apo | +0.410 |
Cassidy | +0.405 |
Amen | +0.402 |
Hert | +0.385 |
Neg logit contributions | |
cli | -0.534 |
�� | -0.528 |
ette | -0.477 |
� | -0.473 |
� | -0.464 |
Token | will |
Token ID | 481 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
cli | +0.233 |
�� | +0.230 |
ette | +0.200 |
� | +0.199 |
ngth | +0.197 |
Neg logit contributions | |
helium | -0.245 |
apo | -0.238 |
Cassidy | -0.236 |
Amen | -0.236 |
Hert | -0.226 |
Token | step |
Token ID | 2239 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
helium | +0.798 |
apo | +0.763 |
Amen | +0.755 |
Cassidy | +0.749 |
Hert | +0.723 |
Neg logit contributions | |
cli | -0.975 |
�� | -0.965 |
ette | -0.863 |
� | -0.849 |
ngth | -0.842 |
Token | back |
Token ID | 736 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
helium | +0.237 |
apo | +0.233 |
Cassidy | +0.228 |
Amen | +0.226 |
Hert | +0.220 |
Neg logit contributions | |
cli | -0.190 |
�� | -0.188 |
ette | -0.165 |
� | -0.164 |
� | -0.160 |
Token | from |
Token ID | 422 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
helium | +2.433 |
apo | +2.374 |
Cassidy | +2.319 |
Amen | +2.284 |
Hert | +2.182 |
Neg logit contributions | |
�� | -2.867 |
cli | -2.851 |
ette | -2.503 |
ngth | -2.429 |
� | -2.424 |
Token | saying |
Token ID | 2282 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
helium | +0.622 |
apo | +0.593 |
Cassidy | +0.588 |
Amen | +0.579 |
Hert | +0.558 |
Neg logit contributions | |
cli | -0.741 |
�� | -0.735 |
ette | -0.661 |
� | -0.653 |
� | -0.644 |
Token | � |
Token ID | 564 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
cli | +0.695 |
�� | +0.688 |
ette | +0.620 |
� | +0.617 |
� | +0.604 |
Neg logit contributions | |
helium | -0.604 |
apo | -0.587 |
Amen | -0.578 |
Cassidy | -0.577 |
Hert | -0.548 |
Token | � |
Token ID | 250 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
cli | +1.119 |
�� | +1.094 |
� | +1.019 |
ette | +1.017 |
� | +0.997 |
Neg logit contributions | |
helium | -0.695 |
apo | -0.681 |
Amen | -0.656 |
Cassidy | -0.655 |
Hert | -0.621 |
Token | anything |
Token ID | 49459 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
apo | +0.271 |
helium | +0.269 |
Amen | +0.263 |
Cassidy | +0.260 |
Hert | +0.253 |
Neg logit contributions | |
cli | -0.199 |
�� | -0.197 |
� | -0.173 |
ette | -0.173 |
ngth | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
�� | +0.433 |
cli | +0.430 |
� | +0.380 |
ette | +0.378 |
� | +0.366 |
Neg logit contributions | |
helium | -0.462 |
apo | -0.455 |
Amen | -0.444 |
Cassidy | -0.442 |
Hert | -0.426 |
Token | youtube |
Token ID | 11604 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
cli | +0.297 |
�� | +0.294 |
� | +0.269 |
ette | +0.267 |
� | +0.262 |
Neg logit contributions | |
helium | -0.234 |
apo | -0.231 |
Amen | -0.223 |
Cassidy | -0.221 |
Hert | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
�� | +0.082 |
cli | +0.080 |
� | +0.071 |
ette | +0.070 |
ngth | +0.069 |
Neg logit contributions | |
helium | -0.080 |
apo | -0.080 |
Amen | -0.078 |
Cassidy | -0.077 |
Hert | -0.075 |
Token | com |
Token ID | 785 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
helium | +0.079 |
apo | +0.079 |
Amen | +0.076 |
Cassidy | +0.075 |
Hert | +0.072 |
Neg logit contributions | |
�� | -0.108 |
cli | -0.105 |
� | -0.096 |
ette | -0.095 |
ngth | -0.093 |
Token | / |
Token ID | 14 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
helium | +0.947 |
apo | +0.923 |
Amen | +0.902 |
Cassidy | +0.895 |
Hert | +0.862 |
Neg logit contributions | |
�� | -1.416 |
cli | -1.409 |
� | -1.263 |
ette | -1.258 |
ngth | -1.240 |
Token | watch |
Token ID | 8340 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
helium | +1.476 |
apo | +1.456 |
Amen | +1.391 |
Cassidy | +1.368 |
Hert | +1.314 |
Neg logit contributions | |
cli | -2.386 |
�� | -2.372 |
� | -2.199 |
ette | -2.177 |
� | -2.136 |
Token | ? |
Token ID | 30 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
helium | +2.055 |
Amen | +2.000 |
apo | +1.991 |
Cassidy | +1.949 |
Hert | +1.924 |
Neg logit contributions | |
�� | -3.130 |
cli | -3.034 |
ngth | -2.748 |
� | -2.659 |
ette | -2.652 |
Token | v |
Token ID | 85 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
helium | +1.439 |
apo | +1.433 |
Amen | +1.388 |
Cassidy | +1.364 |
Hert | +1.337 |
Neg logit contributions | |
�� | -1.314 |
cli | -1.281 |
� | -1.162 |
ette | -1.150 |
� | -1.092 |
Token | = |
Token ID | 28 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
helium | +0.321 |
apo | +0.318 |
Amen | +0.299 |
Cassidy | +0.298 |
Hert | +0.285 |
Neg logit contributions | |
�� | -0.602 |
cli | -0.600 |
� | -0.552 |
ette | -0.551 |
� | -0.536 |
Token | 2 |
Token ID | 17 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
helium | +0.358 |
apo | +0.358 |
Amen | +0.343 |
Cassidy | +0.341 |
Hert | +0.329 |
Neg logit contributions | |
cli | -0.333 |
�� | -0.332 |
� | -0.300 |
ette | -0.294 |
� | -0.288 |
Token | g |
Token ID | 70 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
apo | +0.686 |
helium | +0.685 |
Amen | +0.657 |
Cassidy | +0.651 |
Hert | +0.628 |
Neg logit contributions | |
�� | -0.664 |
cli | -0.664 |
� | -0.602 |
ette | -0.589 |
� | -0.576 |
Token | {{ |
Token ID | 22935 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
helium | +1.248 |
apo | +1.223 |
Amen | +1.204 |
Cassidy | +1.190 |
Hert | +1.154 |
Neg logit contributions | |
cli | -0.995 |
�� | -0.983 |
ette | -0.865 |
� | -0.856 |
� | -0.835 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
apo | +2.177 |
helium | +2.148 |
Amen | +2.097 |
Cassidy | +2.030 |
Hert | +1.957 |
Neg logit contributions | |
�� | -2.583 |
cli | -2.535 |
ette | -2.304 |
� | -2.288 |
ngth | -2.220 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
helium | +1.370 |
apo | +1.354 |
Amen | +1.330 |
Cassidy | +1.318 |
Hert | +1.288 |
Neg logit contributions | |
�� | -1.072 |
cli | -1.017 |
ngth | -0.917 |
ette | -0.851 |
� | -0.845 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
helium | +0.263 |
apo | +0.257 |
Amen | +0.250 |
Cassidy | +0.249 |
Hert | +0.238 |
Neg logit contributions | |
cli | -0.344 |
�� | -0.338 |
ette | -0.310 |
� | -0.310 |
� | -0.303 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
�� | +0.025 |
cli | +0.025 |
� | +0.022 |
ette | +0.022 |
ngth | +0.021 |
Neg logit contributions | |
helium | -0.027 |
apo | -0.027 |
Amen | -0.026 |
Cassidy | -0.026 |
Hert | -0.025 |
Token | {{ |
Token ID | 22935 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
helium | +1.008 |
apo | +0.988 |
Amen | +0.963 |
Cassidy | +0.957 |
Hert | +0.921 |
Neg logit contributions | |
cli | -1.067 |
�� | -1.052 |
ette | -0.951 |
� | -0.950 |
� | -0.927 |
Token | 9 |
Token ID | 24 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
apo | +2.731 |
helium | +2.696 |
Amen | +2.664 |
Cassidy | +2.602 |
Hert | +2.525 |
Neg logit contributions | |
�� | -2.378 |
cli | -2.312 |
� | -2.032 |
ngth | -2.029 |
ette | -2.028 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
helium | +0.705 |
apo | +0.698 |
Amen | +0.684 |
Cassidy | +0.679 |
Hert | +0.663 |
Neg logit contributions | |
�� | -0.526 |
cli | -0.506 |
ngth | -0.446 |
� | -0.426 |
ette | -0.424 |
Token | 14 |
Token ID | 1478 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
helium | +0.272 |
apo | +0.265 |
Amen | +0.261 |
Cassidy | +0.259 |
Hert | +0.248 |
Neg logit contributions | |
cli | -0.381 |
�� | -0.377 |
ette | -0.343 |
� | -0.339 |
� | -0.332 |
Token | }, |
Token ID | 5512 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
�� | +0.221 |
cli | +0.220 |
� | +0.197 |
ette | +0.194 |
� | +0.187 |
Neg logit contributions | |
helium | -0.246 |
apo | -0.243 |
Amen | -0.237 |
Cassidy | -0.235 |
Hert | -0.228 |
Token | { |
Token ID | 1391 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
helium | +1.241 |
Amen | +1.214 |
apo | +1.208 |
Cassidy | +1.191 |
Hert | +1.163 |
Neg logit contributions | |
�� | -1.205 |
cli | -1.168 |
ngth | -1.035 |
ette | -1.014 |
� | -0.987 |
Token | pie |
Token ID | 2508 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
cli | +0.080 |
�� | +0.080 |
ette | +0.072 |
� | +0.072 |
� | +0.070 |
Neg logit contributions | |
helium | -0.061 |
apo | -0.060 |
Cassidy | -0.058 |
Amen | -0.058 |
Hert | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
helium | +0.634 |
apo | +0.625 |
Cassidy | +0.608 |
Amen | +0.606 |
Hert | +0.584 |
Neg logit contributions | |
cli | -0.594 |
�� | -0.590 |
� | -0.522 |
ette | -0.521 |
� | -0.506 |
Token | � |
Token ID | 447 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
cli | +0.257 |
�� | +0.254 |
� | +0.224 |
ette | +0.224 |
� | +0.215 |
Neg logit contributions | |
helium | -0.321 |
apo | -0.316 |
Cassidy | -0.310 |
Amen | -0.309 |
Hert | -0.298 |
Token | � |
Token ID | 251 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
cli | +0.219 |
�� | +0.217 |
� | +0.200 |
ette | +0.199 |
� | +0.196 |
Neg logit contributions | |
helium | -0.143 |
apo | -0.140 |
Amen | -0.134 |
Cassidy | -0.134 |
Hert | -0.127 |
Token | Jose |
Token ID | 23409 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
helium | +0.429 |
apo | +0.422 |
Cassidy | +0.420 |
Amen | +0.419 |
Hert | +0.405 |
Neg logit contributions | |
�� | -0.368 |
cli | -0.367 |
� | -0.322 |
ette | -0.319 |
� | -0.309 |
Token | f |
Token ID | 69 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
cli | +0.017 |
�� | +0.017 |
� | +0.015 |
ette | +0.015 |
� | +0.014 |
Neg logit contributions | |
helium | -0.016 |
apo | -0.016 |
Amen | -0.015 |
Cassidy | -0.015 |
Hert | -0.014 |
Token | Fr |
Token ID | 1305 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
helium | +2.579 |
apo | +2.571 |
Amen | +2.533 |
Cassidy | +2.516 |
Hert | +2.465 |
Neg logit contributions | |
cli | -2.520 |
�� | -2.513 |
� | -2.193 |
ette | -2.145 |
ngth | -2.114 |
Token | ue |
Token ID | 518 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
apo | +0.597 |
helium | +0.595 |
Amen | +0.572 |
Cassidy | +0.565 |
Hert | +0.550 |
Neg logit contributions | |
�� | -0.605 |
cli | -0.601 |
� | -0.539 |
ette | -0.528 |
� | -0.512 |
Token | h |
Token ID | 71 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
helium | +0.690 |
apo | +0.681 |
Amen | +0.655 |
Cassidy | +0.646 |
Hert | +0.632 |
Neg logit contributions | |
�� | -0.807 |
cli | -0.786 |
� | -0.706 |
ette | -0.698 |
ngth | -0.680 |
Token | wald |
Token ID | 21667 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
cli | +0.250 |
�� | +0.250 |
� | +0.223 |
ette | +0.221 |
� | +0.212 |
Neg logit contributions | |
helium | -0.277 |
apo | -0.275 |
Cassidy | -0.266 |
Amen | -0.263 |
Hert | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
cli | +0.716 |
�� | +0.704 |
� | +0.620 |
ette | +0.612 |
� | +0.596 |
Neg logit contributions | |
helium | -0.965 |
apo | -0.949 |
Amen | -0.930 |
Cassidy | -0.930 |
Hert | -0.901 |
Token | can |
Token ID | 460 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
cli | +0.353 |
�� | +0.349 |
ette | +0.309 |
� | +0.305 |
� | +0.294 |
Neg logit contributions | |
helium | -0.409 |
apo | -0.400 |
Cassidy | -0.390 |
Amen | -0.390 |
Hert | -0.375 |
Token | repay |
Token ID | 20152 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
helium | +0.185 |
apo | +0.178 |
Amen | +0.173 |
Cassidy | +0.173 |
Hert | +0.166 |
Neg logit contributions | |
cli | -0.226 |
�� | -0.223 |
ette | -0.202 |
� | -0.199 |
ngth | -0.194 |
Token | that |
Token ID | 326 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
cli | +0.057 |
�� | +0.056 |
ette | +0.050 |
� | +0.050 |
� | +0.049 |
Neg logit contributions | |
helium | -0.052 |
apo | -0.051 |
Amen | -0.049 |
Cassidy | -0.049 |
Hert | -0.047 |
Token | debt |
Token ID | 5057 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
cli | +0.031 |
�� | +0.030 |
� | +0.028 |
ette | +0.028 |
� | +0.027 |
Neg logit contributions | |
helium | -0.021 |
apo | -0.021 |
Amen | -0.020 |
Cassidy | -0.020 |
Hert | -0.019 |
Token | once |
Token ID | 1752 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
helium | +0.040 |
apo | +0.039 |
Cassidy | +0.038 |
Amen | +0.038 |
Hert | +0.036 |
Neg logit contributions | |
cli | -0.048 |
�� | -0.048 |
ette | -0.043 |
� | -0.043 |
� | -0.042 |
Token | expansion |
Token ID | 7118 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
helium | +0.906 |
apo | +0.886 |
Amen | +0.859 |
Cassidy | +0.856 |
Hert | +0.823 |
Neg logit contributions | |
cli | -0.963 |
�� | -0.951 |
ette | -0.857 |
� | -0.849 |
� | -0.825 |
Token | returns |
Token ID | 5860 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
helium | +2.652 |
apo | +2.546 |
Amen | +2.487 |
Cassidy | +2.484 |
Hert | +2.397 |
Neg logit contributions | |
cli | -2.558 |
�� | -2.514 |
ngth | -2.183 |
ette | -2.177 |
� | -2.148 |
Token | and |
Token ID | 290 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
helium | +0.101 |
apo | +0.098 |
Amen | +0.096 |
Cassidy | +0.096 |
Hert | +0.092 |
Neg logit contributions | |
cli | -0.093 |
�� | -0.091 |
ette | -0.081 |
� | -0.080 |
� | -0.078 |
Token | produces |
Token ID | 11073 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
helium | +0.249 |
apo | +0.241 |
Amen | +0.235 |
Cassidy | +0.235 |
Hert | +0.225 |
Neg logit contributions | |
cli | -0.289 |
�� | -0.284 |
ette | -0.256 |
� | -0.254 |
� | -0.248 |
Token | a |
Token ID | 257 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
helium | +0.662 |
apo | +0.631 |
Amen | +0.622 |
Cassidy | +0.618 |
Hert | +0.594 |
Neg logit contributions | |
cli | -0.818 |
�� | -0.811 |
ette | -0.733 |
� | -0.722 |
� | -0.707 |
Token | government |
Token ID | 1230 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
cli | +0.227 |
�� | +0.224 |
ette | +0.206 |
� | +0.204 |
� | +0.200 |
Neg logit contributions | |
helium | -0.166 |
apo | -0.159 |
Amen | -0.156 |
Cassidy | -0.155 |
Hert | -0.148 |
Token | Kell |
Token ID | 25043 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
helium | +1.165 |
apo | +1.120 |
Cassidy | +1.107 |
Amen | +1.102 |
Hert | +1.070 |
Neg logit contributions | |
cli | -1.254 |
�� | -1.248 |
� | -1.118 |
ette | -1.116 |
� | -1.089 |
Token | Brook |
Token ID | 7590 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
helium | +0.845 |
apo | +0.823 |
Cassidy | +0.805 |
Amen | +0.802 |
Hert | +0.765 |
Neg logit contributions | |
cli | -1.228 |
�� | -1.215 |
� | -1.112 |
ette | -1.105 |
� | -1.085 |
Token | in |
Token ID | 287 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
cli | +0.440 |
�� | +0.433 |
� | +0.389 |
ette | +0.389 |
� | +0.378 |
Neg logit contributions | |
helium | -0.400 |
apo | -0.393 |
Cassidy | -0.384 |
Amen | -0.382 |
Hert | -0.367 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
helium | +0.185 |
apo | +0.180 |
Cassidy | +0.177 |
Amen | +0.176 |
Hert | +0.170 |
Neg logit contributions | |
cli | -0.204 |
�� | -0.201 |
ette | -0.181 |
� | -0.181 |
� | -0.177 |
Token | th |
Token ID | 400 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
cli | +0.287 |
�� | +0.282 |
� | +0.255 |
ette | +0.254 |
� | +0.248 |
Neg logit contributions | |
helium | -0.309 |
apo | -0.304 |
Amen | -0.296 |
Cassidy | -0.295 |
Hert | -0.285 |
Token | round |
Token ID | 2835 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
helium | +0.216 |
apo | +0.210 |
Amen | +0.204 |
Cassidy | +0.204 |
Hert | +0.195 |
Neg logit contributions | |
cli | -0.307 |
�� | -0.302 |
� | -0.277 |
ette | -0.276 |
� | -0.270 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
helium | +2.392 |
apo | +2.321 |
Cassidy | +2.305 |
Amen | +2.280 |
Hert | +2.190 |
Neg logit contributions | |
cli | -2.692 |
�� | -2.680 |
ette | -2.378 |
� | -2.360 |
ngth | -2.325 |
Token | win |
Token ID | 1592 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
cli | +0.840 |
�� | +0.829 |
� | +0.752 |
ette | +0.751 |
� | +0.734 |
Neg logit contributions | |
helium | -0.738 |
apo | -0.719 |
Amen | -0.701 |
Cassidy | -0.700 |
Hert | -0.671 |
Token | I |
Token ID | 314 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
cli | +0.589 |
�� | +0.583 |
� | +0.525 |
ette | +0.523 |
� | +0.510 |
Neg logit contributions | |
helium | -0.588 |
apo | -0.575 |
Cassidy | -0.559 |
Amen | -0.559 |
Hert | -0.540 |
Token | BF |
Token ID | 29499 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
�� | +0.238 |
cli | +0.238 |
� | +0.218 |
ette | +0.218 |
� | +0.212 |
Neg logit contributions | |
helium | -0.153 |
apo | -0.149 |
Cassidy | -0.143 |
Amen | -0.143 |
Hert | -0.137 |
Token | wel |
Token ID | 5029 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
cli | +0.042 |
�� | +0.042 |
ette | +0.037 |
� | +0.037 |
� | +0.036 |
Neg logit contributions | |
helium | -0.045 |
apo | -0.043 |
Cassidy | -0.043 |
Amen | -0.043 |
Hert | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
helium | +0.115 |
apo | +0.110 |
Amen | +0.110 |
Cassidy | +0.109 |
Hert | +0.105 |
Neg logit contributions | |
cli | -0.113 |
�� | -0.111 |
ette | -0.098 |
� | -0.096 |
ngth | -0.095 |
Token | future |
Token ID | 2003 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
cli | +0.281 |
�� | +0.277 |
ette | +0.251 |
� | +0.249 |
� | +0.243 |
Neg logit contributions | |
helium | -0.261 |
apo | -0.253 |
Amen | -0.248 |
Cassidy | -0.248 |
Hert | -0.239 |
Token | ?" |
Token ID | 1701 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
cli | +0.798 |
�� | +0.785 |
ette | +0.702 |
� | +0.697 |
� | +0.679 |
Neg logit contributions | |
helium | -0.794 |
apo | -0.768 |
Amen | -0.757 |
Cassidy | -0.754 |
Hert | -0.730 |
Token |
|
Token ID | 198 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
helium | +0.476 |
apo | +0.463 |
Amen | +0.442 |
Cassidy | +0.441 |
Hert | +0.416 |
Neg logit contributions | |
cli | -0.872 |
�� | -0.856 |
� | -0.803 |
ette | -0.800 |
� | -0.787 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
helium | +0.235 |
apo | +0.231 |
Amen | +0.224 |
Cassidy | +0.221 |
Hert | +0.209 |
Neg logit contributions | |
�� | -0.548 |
cli | -0.538 |
ngth | -0.491 |
ette | -0.490 |
� | -0.489 |
Token | Analysis |
Token ID | 32750 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
apo | +0.478 |
helium | +0.475 |
Amen | +0.457 |
Cassidy | +0.454 |
Hert | +0.438 |
Neg logit contributions | |
�� | -0.587 |
cli | -0.583 |
� | -0.531 |
ette | -0.520 |
ngth | -0.515 |
Token | Lord |
Token ID | 4453 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
helium | +2.548 |
apo | +2.531 |
Amen | +2.519 |
Cassidy | +2.486 |
Hert | +2.411 |
Neg logit contributions | |
cli | -2.527 |
�� | -2.515 |
ette | -2.199 |
� | -2.173 |
� | -2.166 |
Token | Hes |
Token ID | 44773 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
helium | +0.429 |
apo | +0.401 |
Cassidy | +0.398 |
Amen | +0.396 |
Hert | +0.362 |
Neg logit contributions | |
cli | -1.500 |
�� | -1.492 |
� | -1.385 |
ette | -1.381 |
� | -1.358 |
Token | elt |
Token ID | 2120 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
�� | +0.085 |
cli | +0.084 |
� | +0.074 |
ette | +0.073 |
� | +0.071 |
Neg logit contributions | |
helium | -0.102 |
apo | -0.100 |
Amen | -0.097 |
Cassidy | -0.097 |
Hert | -0.095 |
Token | ine |
Token ID | 500 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
helium | +0.007 |
apo | +0.007 |
Amen | +0.007 |
Cassidy | +0.007 |
Hert | +0.007 |
Neg logit contributions | |
cli | -0.010 |
�� | -0.010 |
� | -0.009 |
ette | -0.009 |
� | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
helium | +1.186 |
apo | +1.159 |
Cassidy | +1.144 |
Amen | +1.143 |
Hert | +1.111 |
Neg logit contributions | |
cli | -0.921 |
�� | -0.913 |
ette | -0.784 |
� | -0.778 |
ngth | -0.771 |
Token | said |
Token ID | 531 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
cli | +0.911 |
�� | +0.894 |
� | +0.814 |
ette | +0.810 |
� | +0.792 |
Neg logit contributions | |
helium | -0.907 |
apo | -0.892 |
Amen | -0.866 |
Cassidy | -0.865 |
Hert | -0.831 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
cli | +0.176 |
�� | +0.174 |
ette | +0.156 |
� | +0.156 |
� | +0.152 |
Neg logit contributions | |
helium | -0.165 |
apo | -0.161 |
Amen | -0.158 |
Cassidy | -0.158 |
Hert | -0.151 |
Token | video |
Token ID | 2008 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
helium | +0.025 |
apo | +0.024 |
Amen | +0.024 |
Cassidy | +0.024 |
Hert | +0.023 |
Neg logit contributions | |
cli | -0.028 |
�� | -0.027 |
ette | -0.025 |
� | -0.024 |
� | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
helium | +0.840 |
apo | +0.820 |
Cassidy | +0.809 |
Amen | +0.802 |
Hert | +0.778 |
Neg logit contributions | |
cli | -0.753 |
�� | -0.744 |
� | -0.647 |
ette | -0.646 |
� | -0.630 |
Token | been |
Token ID | 587 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
helium | +1.115 |
apo | +1.065 |
Cassidy | +1.063 |
Amen | +1.051 |
Hert | +1.013 |
Neg logit contributions | |
cli | -1.246 |
�� | -1.229 |
ette | -1.109 |
� | -1.088 |
� | -1.068 |
Token | doct |
Token ID | 10412 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
helium | +1.056 |
apo | +1.011 |
Cassidy | +0.999 |
Amen | +0.991 |
Hert | +0.943 |
Neg logit contributions | |
cli | -1.449 |
�� | -1.423 |
ette | -1.287 |
� | -1.283 |
� | -1.265 |
Token | ored |
Token ID | 1850 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
helium | +3.003 |
apo | +2.996 |
Amen | +2.894 |
Cassidy | +2.876 |
Hert | +2.823 |
Neg logit contributions | |
�� | -2.062 |
cli | -1.990 |
ngth | -1.679 |
� | -1.662 |
ette | -1.604 |
Token | to |
Token ID | 284 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
helium | +1.308 |
apo | +1.264 |
Amen | +1.254 |
Cassidy | +1.253 |
Hert | +1.204 |
Neg logit contributions | |
cli | -1.194 |
�� | -1.181 |
ette | -1.039 |
� | -1.026 |
� | -1.003 |
Token | misrepresent |
Token ID | 26521 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
helium | +0.128 |
apo | +0.124 |
Amen | +0.121 |
Cassidy | +0.121 |
Hert | +0.116 |
Neg logit contributions | |
cli | -0.145 |
�� | -0.142 |
ette | -0.129 |
� | -0.128 |
� | -0.125 |
Token | what |
Token ID | 644 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
helium | +0.939 |
apo | +0.912 |
Cassidy | +0.900 |
Amen | +0.898 |
Hert | +0.864 |
Neg logit contributions | |
cli | -1.003 |
�� | -0.986 |
ette | -0.882 |
� | -0.881 |
� | -0.863 |
Token | he |
Token ID | 339 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
helium | +0.503 |
apo | +0.491 |
Cassidy | +0.481 |
Amen | +0.480 |
Hert | +0.461 |
Neg logit contributions | |
cli | -0.602 |
�� | -0.595 |
� | -0.537 |
ette | -0.537 |
� | -0.523 |
Token | 27 |
Token ID | 2681 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
helium | +0.828 |
apo | +0.812 |
Amen | +0.781 |
Cassidy | +0.781 |
Hert | +0.742 |
Neg logit contributions | |
cli | -1.253 |
�� | -1.232 |
� | -1.142 |
ette | -1.136 |
� | -1.117 |
Token | # |
Token ID | 1303 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
helium | +1.198 |
apo | +1.151 |
Amen | +1.119 |
Cassidy | +1.088 |
Hert | +1.047 |
Neg logit contributions | |
�� | -1.358 |
cli | -1.343 |
� | -1.217 |
ette | -1.207 |
� | -1.184 |
Token | loop |
Token ID | 9052 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
helium | +1.952 |
apo | +1.917 |
Amen | +1.860 |
Cassidy | +1.840 |
Hert | +1.778 |
Neg logit contributions | |
�� | -1.848 |
cli | -1.838 |
ette | -1.662 |
� | -1.645 |
� | -1.578 |
Token | over |
Token ID | 625 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
helium | +0.942 |
apo | +0.910 |
Amen | +0.888 |
Cassidy | +0.885 |
Hert | +0.847 |
Neg logit contributions | |
cli | -1.244 |
�� | -1.231 |
� | -1.122 |
ette | -1.120 |
� | -1.094 |
Token | the |
Token ID | 262 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
helium | +1.015 |
apo | +0.981 |
Amen | +0.964 |
Cassidy | +0.957 |
Hert | +0.929 |
Neg logit contributions | |
cli | -1.086 |
�� | -1.075 |
ette | -0.970 |
� | -0.969 |
� | -0.943 |
Token | input |
Token ID | 5128 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
helium | +0.543 |
apo | +0.526 |
Amen | +0.508 |
Cassidy | +0.506 |
Hert | +0.484 |
Neg logit contributions | |
cli | -0.861 |
�� | -0.851 |
� | -0.785 |
ette | -0.783 |
� | -0.768 |
Token | image |
Token ID | 2939 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
helium | +2.094 |
apo | +1.926 |
Amen | +1.905 |
Cassidy | +1.888 |
Hert | +1.847 |
Neg logit contributions | |
cli | -2.992 |
�� | -2.976 |
ette | -2.668 |
� | -2.662 |
deals | -2.621 |
Token | paths |
Token ID | 13532 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
helium | +1.403 |
apo | +1.344 |
Cassidy | +1.314 |
Amen | +1.300 |
Hert | +1.272 |
Neg logit contributions | |
cli | -1.790 |
�� | -1.788 |
ette | -1.606 |
� | -1.597 |
� | -1.556 |
Token | for |
Token ID | 329 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
helium | +0.655 |
apo | +0.639 |
Amen | +0.618 |
Cassidy | +0.618 |
Hert | +0.593 |
Neg logit contributions | |
cli | -0.726 |
�� | -0.717 |
� | -0.650 |
ette | -0.647 |
� | -0.636 |
Token | image |
Token ID | 2939 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
helium | +0.228 |
apo | +0.215 |
Amen | +0.208 |
Cassidy | +0.205 |
Hert | +0.199 |
Neg logit contributions | |
cli | -0.325 |
�� | -0.323 |
ette | -0.292 |
� | -0.290 |
ngth | -0.287 |
Token | Path |
Token ID | 15235 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
helium | +0.952 |
apo | +0.933 |
Cassidy | +0.926 |
Amen | +0.910 |
Hert | +0.892 |
Neg logit contributions | |
�� | -1.207 |
cli | -1.194 |
ette | -1.055 |
� | -1.047 |
ngth | -1.033 |
Token | nat |
Token ID | 34664 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
helium | +2.048 |
apo | +1.993 |
Amen | +1.954 |
Cassidy | +1.919 |
Hert | +1.843 |
Neg logit contributions | |
cli | -2.330 |
�� | -2.323 |
ette | -2.106 |
� | -2.060 |
ngth | -2.021 |
Token | ut |
Token ID | 315 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
apo | +1.276 |
helium | +1.243 |
Amen | +1.195 |
Cassidy | +1.185 |
Hert | +1.135 |
Neg logit contributions | |
�� | -1.266 |
cli | -1.239 |
� | -1.117 |
ette | -1.107 |
� | -1.067 |
Token | u |
Token ID | 84 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
apo | +0.741 |
helium | +0.739 |
Amen | +0.708 |
Cassidy | +0.704 |
Hert | +0.674 |
Neg logit contributions | |
�� | -0.742 |
cli | -0.738 |
� | -0.661 |
ette | -0.655 |
� | -0.639 |
Token | wa |
Token ID | 10247 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
helium | +0.623 |
apo | +0.621 |
Amen | +0.593 |
Cassidy | +0.591 |
Hert | +0.568 |
Neg logit contributions | |
cli | -0.600 |
�� | -0.597 |
� | -0.531 |
ette | -0.529 |
� | -0.514 |
Token | na |
Token ID | 12385 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
helium | +0.621 |
apo | +0.616 |
Amen | +0.593 |
Cassidy | +0.592 |
Hert | +0.569 |
Neg logit contributions | |
cli | -0.583 |
�� | -0.577 |
ette | -0.514 |
� | -0.512 |
� | -0.498 |
Token | ang |
Token ID | 3550 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
helium | +1.419 |
apo | +1.396 |
Amen | +1.350 |
Cassidy | +1.346 |
Hert | +1.284 |
Neg logit contributions | |
cli | -1.595 |
�� | -1.584 |
ette | -1.436 |
� | -1.409 |
� | -1.374 |
Token | kan |
Token ID | 43998 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
helium | +2.385 |
apo | +2.325 |
Amen | +2.270 |
Cassidy | +2.231 |
Hert | +2.143 |
Neg logit contributions | |
�� | -2.644 |
cli | -2.639 |
ette | -2.390 |
� | -2.339 |
� | -2.285 |
Token | il |
Token ID | 346 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
apo | +1.391 |
helium | +1.352 |
Amen | +1.304 |
Cassidy | +1.293 |
Hert | +1.235 |
Neg logit contributions | |
�� | -1.484 |
cli | -1.464 |
� | -1.324 |
ette | -1.305 |
� | -1.280 |
Token | ang |
Token ID | 648 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
apo | +1.194 |
helium | +1.180 |
Amen | +1.129 |
Cassidy | +1.116 |
Hert | +1.071 |
Neg logit contributions | |
�� | -1.368 |
cli | -1.344 |
� | -1.214 |
ette | -1.205 |
� | -1.177 |
Token | an |
Token ID | 281 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
helium | +1.499 |
apo | +1.483 |
Amen | +1.432 |
Cassidy | +1.417 |
Hert | +1.359 |
Neg logit contributions | |
cli | -1.602 |
�� | -1.598 |
ette | -1.431 |
� | -1.421 |
� | -1.386 |
Token | ak |
Token ID | 461 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
apo | +1.282 |
helium | +1.268 |
Amen | +1.222 |
Cassidy | +1.208 |
Hert | +1.158 |
Neg logit contributions | |
cli | -1.328 |
�� | -1.319 |
� | -1.183 |
ette | -1.180 |
� | -1.146 |
Token | Is |
Token ID | 1148 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
cli | +0.008 |
�� | +0.008 |
ette | +0.007 |
� | +0.007 |
� | +0.007 |
Neg logit contributions | |
helium | -0.007 |
apo | -0.007 |
Amen | -0.007 |
Cassidy | -0.007 |
Hert | -0.007 |
Token | Not |
Token ID | 3673 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
cli | +0.570 |
�� | +0.561 |
� | +0.511 |
ette | +0.508 |
� | +0.498 |
Neg logit contributions | |
helium | -0.534 |
apo | -0.524 |
Amen | -0.509 |
Cassidy | -0.507 |
Hert | -0.487 |
Token | Valid |
Token ID | 47139 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
cli | +0.569 |
�� | +0.559 |
� | +0.511 |
ette | +0.508 |
� | +0.498 |
Neg logit contributions | |
helium | -0.511 |
apo | -0.502 |
Amen | -0.486 |
Cassidy | -0.485 |
Hert | -0.466 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
helium | +0.455 |
apo | +0.448 |
Amen | +0.435 |
Cassidy | +0.433 |
Hert | +0.420 |
Neg logit contributions | |
cli | -0.361 |
�� | -0.357 |
� | -0.314 |
ette | -0.313 |
� | -0.305 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
cli | +0.036 |
�� | +0.036 |
� | +0.032 |
ette | +0.032 |
� | +0.031 |
Neg logit contributions | |
helium | -0.036 |
apo | -0.036 |
Amen | -0.035 |
Cassidy | -0.035 |
Hert | -0.033 |
Token | return |
Token ID | 1441 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
cli | +0.960 |
�� | +0.939 |
� | +0.845 |
ette | +0.839 |
� | +0.820 |
Neg logit contributions | |
helium | -1.207 |
apo | -1.189 |
Amen | -1.158 |
Cassidy | -1.157 |
Hert | -1.116 |
Token | space |
Token ID | 2272 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
cli | +3.790 |
�� | +3.737 |
� | +3.503 |
� | +3.388 |
ette | +3.371 |
Neg logit contributions | |
helium | -4.095 |
apo | -4.089 |
Cassidy | -3.984 |
Amen | -3.924 |
Hert | -3.794 |
Token | ; |
Token ID | 26 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
helium | +0.220 |
apo | +0.214 |
Amen | +0.210 |
Cassidy | +0.208 |
Hert | +0.201 |
Neg logit contributions | |
cli | -0.215 |
�� | -0.212 |
ette | -0.190 |
� | -0.189 |
� | -0.184 |
Token | // |
Token ID | 3373 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
cli | +0.217 |
�� | +0.213 |
ette | +0.189 |
� | +0.188 |
� | +0.183 |
Neg logit contributions | |
helium | -0.280 |
apo | -0.274 |
Amen | -0.268 |
Cassidy | -0.267 |
Hert | -0.258 |
Token | 4 |
Token ID | 604 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
helium | +1.516 |
apo | +1.492 |
Amen | +1.449 |
Cassidy | +1.431 |
Hert | +1.376 |
Neg logit contributions | |
cli | -1.382 |
�� | -1.376 |
ette | -1.223 |
� | -1.199 |
� | -1.169 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
helium | +0.289 |
apo | +0.284 |
Amen | +0.278 |
Cassidy | +0.276 |
Hert | +0.267 |
Neg logit contributions | |
�� | -0.289 |
cli | -0.285 |
� | -0.250 |
ette | -0.250 |
ngth | -0.246 |
Token | normal |
Token ID | 3487 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
�� | +0.007 |
cli | +0.007 |
� | +0.007 |
ette | +0.007 |
ngth | +0.006 |
Neg logit contributions | |
helium | -0.007 |
apo | -0.007 |
Cassidy | -0.007 |
Amen | -0.007 |
Hert | -0.007 |
Token | . |
Token ID | 764 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
cli | +0.001 |
�� | +0.001 |
� | +0.001 |
ette | +0.001 |
� | +0.001 |
Neg logit contributions | |
helium | -0.001 |
apo | -0.001 |
Amen | -0.001 |
Cassidy | -0.001 |
Hert | -0.001 |
Token | y |
Token ID | 331 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
helium | +0.849 |
apo | +0.830 |
Amen | +0.810 |
Cassidy | +0.802 |
Hert | +0.774 |
Neg logit contributions | |
cli | -0.917 |
�� | -0.905 |
� | -0.824 |
ette | -0.822 |
� | -0.801 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
cli | +0.474 |
�� | +0.466 |
� | +0.419 |
ette | +0.418 |
� | +0.408 |
Neg logit contributions | |
helium | -0.514 |
apo | -0.505 |
Cassidy | -0.489 |
Amen | -0.488 |
Hert | -0.473 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
cli | +0.932 |
�� | +0.915 |
ette | +0.827 |
� | +0.826 |
� | +0.805 |
Neg logit contributions | |
helium | -0.951 |
apo | -0.927 |
Amen | -0.906 |
Cassidy | -0.903 |
Hert | -0.871 |
Token | return |
Token ID | 1441 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
cli | +1.069 |
�� | +1.056 |
� | +0.961 |
ette | +0.960 |
� | +0.938 |
Neg logit contributions | |
helium | -0.928 |
apo | -0.905 |
Amen | -0.880 |
Cassidy | -0.877 |
Hert | -0.841 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
cli | +3.474 |
�� | +3.395 |
� | +3.138 |
ette | +3.097 |
� | +3.051 |
Neg logit contributions | |
helium | -3.233 |
apo | -3.210 |
Amen | -3.105 |
Cassidy | -3.094 |
Hert | -2.972 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
helium | +0.932 |
apo | +0.909 |
Amen | +0.885 |
Cassidy | +0.884 |
Hert | +0.855 |
Neg logit contributions | |
�� | -0.814 |
cli | -0.810 |
� | -0.711 |
ette | -0.704 |
� | -0.695 |
Token | # |
Token ID | 1303 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
cli | +0.085 |
�� | +0.084 |
ette | +0.075 |
� | +0.075 |
� | +0.073 |
Neg logit contributions | |
helium | -0.088 |
apo | -0.085 |
Amen | -0.084 |
Cassidy | -0.083 |
Hert | -0.080 |
Token | endif |
Token ID | 32088 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
helium | +0.452 |
apo | +0.446 |
Amen | +0.427 |
Cassidy | +0.425 |
Hert | +0.407 |
Neg logit contributions | |
cli | -0.570 |
�� | -0.566 |
� | -0.519 |
ette | -0.516 |
� | -0.502 |
Token | } |
Token ID | 1782 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
cli | +0.227 |
�� | +0.225 |
ette | +0.202 |
� | +0.202 |
� | +0.197 |
Neg logit contributions | |
helium | -0.242 |
apo | -0.234 |
Amen | -0.230 |
Cassidy | -0.229 |
Hert | -0.221 |
Token | ( |
Token ID | 357 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
cli | +0.618 |
�� | +0.606 |
� | +0.552 |
ette | +0.549 |
� | +0.537 |
Neg logit contributions | |
helium | -0.616 |
apo | -0.606 |
Amen | -0.589 |
Cassidy | -0.587 |
Hert | -0.565 |
Token | part |
Token ID | 3911 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
helium | +0.595 |
apo | +0.586 |
Amen | +0.569 |
Cassidy | +0.560 |
Hert | +0.544 |
Neg logit contributions | |
cli | -0.617 |
�� | -0.610 |
ette | -0.551 |
� | -0.547 |
� | -0.533 |
Token | in |
Token ID | 287 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
cli | +0.145 |
�� | +0.142 |
� | +0.130 |
ette | +0.129 |
� | +0.127 |
Neg logit contributions | |
helium | -0.135 |
apo | -0.133 |
Amen | -0.129 |
Cassidy | -0.129 |
Hert | -0.124 |
Token | parts |
Token ID | 3354 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
cli | +0.359 |
�� | +0.350 |
ette | +0.316 |
� | +0.315 |
� | +0.306 |
Neg logit contributions | |
helium | -0.364 |
apo | -0.356 |
Amen | -0.347 |
Cassidy | -0.345 |
Hert | -0.334 |
Token | ) |
Token ID | 8 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
helium | +0.125 |
apo | +0.122 |
Amen | +0.118 |
Cassidy | +0.118 |
Hert | +0.114 |
Neg logit contributions | |
cli | -0.161 |
�� | -0.160 |
ette | -0.145 |
� | -0.144 |
� | -0.141 |
Token | return |
Token ID | 1441 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
cli | +0.326 |
�� | +0.319 |
� | +0.287 |
ette | +0.285 |
� | +0.278 |
Neg logit contributions | |
helium | -0.402 |
apo | -0.395 |
Amen | -0.385 |
Cassidy | -0.384 |
Hert | -0.371 |
Token | ob |
Token ID | 909 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
cli | +3.181 |
�� | +3.149 |
� | +2.899 |
ette | +2.846 |
� | +2.823 |
Neg logit contributions | |
helium | -3.342 |
apo | -3.288 |
Cassidy | -3.223 |
Amen | -3.192 |
Hert | -3.079 |
Token | b |
Token ID | 65 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
apo | +0.835 |
helium | +0.827 |
Amen | +0.791 |
Cassidy | +0.769 |
Hert | +0.746 |
Neg logit contributions | |
�� | -1.283 |
cli | -1.248 |
� | -1.150 |
ette | -1.141 |
ngth | -1.109 |
Token | _ |
Token ID | 62 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
cli | +0.265 |
�� | +0.260 |
� | +0.234 |
ette | +0.233 |
� | +0.227 |
Neg logit contributions | |
helium | -0.295 |
apo | -0.290 |
Amen | -0.282 |
Cassidy | -0.281 |
Hert | -0.271 |
Token | sub |
Token ID | 7266 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
apo | +0.050 |
helium | +0.050 |
Amen | +0.048 |
Cassidy | +0.047 |
Hert | +0.046 |
Neg logit contributions | |
cli | -0.048 |
�� | -0.048 |
� | -0.043 |
ette | -0.043 |
� | -0.042 |
Token | div |
Token ID | 7146 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
cli | +0.209 |
�� | +0.206 |
� | +0.186 |
ette | +0.185 |
� | +0.181 |
Neg logit contributions | |
helium | -0.225 |
apo | -0.223 |
Amen | -0.215 |
Cassidy | -0.214 |
Hert | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
cli | +0.030 |
�� | +0.030 |
ette | +0.027 |
� | +0.027 |
� | +0.026 |
Neg logit contributions | |
helium | -0.019 |
apo | -0.018 |
Amen | -0.018 |
Cassidy | -0.018 |
Hert | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
helium | +0.083 |
apo | +0.081 |
Amen | +0.078 |
Cassidy | +0.078 |
Hert | +0.073 |
Neg logit contributions | |
�� | -0.181 |
cli | -0.179 |
ette | -0.164 |
� | -0.164 |
ngth | -0.161 |
Token | � |
Token ID | 447 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
apo | +0.322 |
helium | +0.320 |
Amen | +0.305 |
Cassidy | +0.305 |
Hert | +0.294 |
Neg logit contributions | |
�� | -0.362 |
cli | -0.359 |
� | -0.324 |
ette | -0.321 |
ngth | -0.313 |
Token | � |
Token ID | 250 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
cli | +0.019 |
�� | +0.019 |
� | +0.018 |
ette | +0.018 |
� | +0.017 |
Neg logit contributions | |
helium | -0.012 |
apo | -0.012 |
Amen | -0.011 |
Cassidy | -0.011 |
Hert | -0.011 |
Token | Take |
Token ID | 12322 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
helium | +0.037 |
apo | +0.036 |
Amen | +0.035 |
Cassidy | +0.035 |
Hert | +0.033 |
Neg logit contributions | |
cli | -0.045 |
�� | -0.045 |
� | -0.041 |
ette | -0.040 |
� | -0.039 |
Token | away |
Token ID | 1497 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
cli | +0.234 |
�� | +0.229 |
ette | +0.207 |
� | +0.205 |
� | +0.201 |
Neg logit contributions | |
helium | -0.228 |
apo | -0.223 |
Cassidy | -0.218 |
Amen | -0.217 |
Hert | -0.209 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
cli | +3.334 |
�� | +3.253 |
� | +3.025 |
ette | +2.981 |
� | +2.946 |
Neg logit contributions | |
helium | -3.128 |
apo | -3.099 |
Amen | -2.995 |
Cassidy | -2.987 |
Hert | -2.872 |
Token | thunder |
Token ID | 18355 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
cli | +0.819 |
�� | +0.809 |
ette | +0.736 |
� | +0.733 |
� | +0.718 |
Neg logit contributions | |
helium | -0.683 |
apo | -0.665 |
Amen | -0.647 |
Cassidy | -0.647 |
Hert | -0.618 |
Token | storm |
Token ID | 12135 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
cli | +1.123 |
�� | +1.105 |
� | +1.002 |
ette | +0.997 |
� | +0.975 |
Neg logit contributions | |
helium | -1.115 |
apo | -1.096 |
Amen | -1.064 |
Cassidy | -1.062 |
Hert | -1.022 |
Token | mechanism |
Token ID | 9030 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
helium | +0.086 |
apo | +0.084 |
Amen | +0.082 |
Cassidy | +0.082 |
Hert | +0.078 |
Neg logit contributions | |
cli | -0.090 |
�� | -0.090 |
� | -0.080 |
ette | -0.080 |
� | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
helium | +0.599 |
apo | +0.590 |
Cassidy | +0.576 |
Amen | +0.575 |
Hert | +0.554 |
Neg logit contributions | |
cli | -0.501 |
�� | -0.494 |
ette | -0.433 |
� | -0.429 |
� | -0.416 |
Token | 09 |
Token ID | 2931 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
�� | +0.161 |
cli | +0.160 |
� | +0.142 |
ette | +0.141 |
� | +0.138 |
Neg logit contributions | |
helium | -0.164 |
apo | -0.162 |
Amen | -0.159 |
Cassidy | -0.158 |
Hert | -0.152 |
Token | - |
Token ID | 12 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
helium | +0.345 |
apo | +0.338 |
Cassidy | +0.334 |
Amen | +0.332 |
Hert | +0.323 |
Neg logit contributions | |
cli | -0.228 |
�� | -0.224 |
� | -0.195 |
ette | -0.195 |
� | -0.187 |
Token | 05 |
Token ID | 2713 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
helium | +0.150 |
apo | +0.148 |
Amen | +0.144 |
Cassidy | +0.143 |
Hert | +0.138 |
Neg logit contributions | |
�� | -0.172 |
cli | -0.170 |
� | -0.153 |
ette | -0.152 |
ngth | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
helium | +0.488 |
apo | +0.475 |
Cassidy | +0.463 |
Amen | +0.463 |
Hert | +0.444 |
Neg logit contributions | |
cli | -0.674 |
�� | -0.667 |
ette | -0.609 |
� | -0.606 |
� | -0.594 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
helium | +0.114 |
apo | +0.111 |
Amen | +0.107 |
Cassidy | +0.106 |
Hert | +0.100 |
Neg logit contributions | |
�� | -0.250 |
cli | -0.247 |
ette | -0.226 |
� | -0.226 |
ngth | -0.223 |
Token | Dear |
Token ID | 20266 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
helium | +0.009 |
apo | +0.009 |
Amen | +0.008 |
Cassidy | +0.008 |
Hert | +0.008 |
Neg logit contributions | |
cli | -0.009 |
�� | -0.009 |
� | -0.009 |
ette | -0.009 |
� | -0.008 |
Token | users |
Token ID | 2985 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
cli | +3.549 |
�� | +3.471 |
� | +3.237 |
ette | +3.188 |
� | +3.149 |
Neg logit contributions | |
helium | -2.912 |
apo | -2.893 |
Amen | -2.742 |
Cassidy | -2.737 |
Hert | -2.619 |
Token | , |
Token ID | 11 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
cli | +0.145 |
�� | +0.141 |
� | +0.126 |
ette | +0.125 |
� | +0.122 |
Neg logit contributions | |
helium | -0.206 |
apo | -0.203 |
Amen | -0.198 |
Cassidy | -0.197 |
Hert | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
cli | +0.871 |
�� | +0.857 |
� | +0.795 |
ette | +0.791 |
� | +0.779 |
Neg logit contributions | |
helium | -0.555 |
apo | -0.543 |
Amen | -0.522 |
Cassidy | -0.521 |
Hert | -0.495 |
Token |
|
Token ID | 198 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
cli | +1.236 |
�� | +1.223 |
� | +1.134 |
ette | +1.131 |
� | +1.111 |
Neg logit contributions | |
helium | -0.629 |
apo | -0.612 |
Amen | -0.588 |
Cassidy | -0.586 |
Hert | -0.552 |
Token | After |
Token ID | 3260 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
cli | +0.702 |
�� | +0.694 |
� | +0.636 |
ette | +0.632 |
� | +0.616 |
Neg logit contributions | |
helium | -0.603 |
apo | -0.593 |
Amen | -0.574 |
Cassidy | -0.571 |
Hert | -0.547 |
Token | [ |
Token ID | 685 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
cli | +0.174 |
�� | +0.171 |
� | +0.154 |
ette | +0.153 |
� | +0.150 |
Neg logit contributions | |
helium | -0.174 |
apo | -0.171 |
Amen | -0.166 |
Cassidy | -0.166 |
Hert | -0.159 |
Token | 10 |
Token ID | 940 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
apo | +0.078 |
helium | +0.078 |
Amen | +0.075 |
Cassidy | +0.075 |
Hert | +0.072 |
Neg logit contributions | |
�� | -0.091 |
cli | -0.089 |
� | -0.081 |
ette | -0.080 |
ngth | -0.078 |
Token | : |
Token ID | 25 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
�� | +0.079 |
cli | +0.078 |
� | +0.069 |
ette | +0.069 |
ngth | +0.068 |
Neg logit contributions | |
helium | -0.066 |
apo | -0.065 |
Amen | -0.063 |
Cassidy | -0.063 |
Hert | -0.061 |
Token | 47 |
Token ID | 2857 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
cli | +0.461 |
�� | +0.447 |
� | +0.383 |
ette | +0.380 |
� | +0.366 |
Neg logit contributions | |
helium | -1.001 |
apo | -0.988 |
Amen | -0.968 |
Cassidy | -0.965 |
Hert | -0.939 |
Token | ] |
Token ID | 60 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
�� | +0.470 |
cli | +0.469 |
� | +0.400 |
ette | +0.397 |
� | +0.380 |
Neg logit contributions | |
helium | -0.772 |
apo | -0.763 |
Amen | -0.748 |
Cassidy | -0.745 |
Hert | -0.724 |
Token | <@ |
Token ID | 32406 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
cli | +1.558 |
�� | +1.522 |
� | +1.420 |
ette | +1.375 |
� | +1.332 |
Neg logit contributions | |
helium | -2.214 |
apo | -2.186 |
Cassidy | -2.116 |
Amen | -2.108 |
Hert | -2.051 |
Token | t |
Token ID | 83 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
cli | +3.245 |
�� | +3.123 |
ette | +2.898 |
� | +2.830 |
� | +2.818 |
Neg logit contributions | |
helium | -3.169 |
apo | -3.045 |
Cassidy | -3.036 |
Amen | -3.027 |
Hert | -2.923 |
Token | ay |
Token ID | 323 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
apo | +0.805 |
helium | +0.783 |
Amen | +0.754 |
Cassidy | +0.745 |
Hert | +0.729 |
Neg logit contributions | |
�� | -0.877 |
cli | -0.857 |
� | -0.781 |
ette | -0.756 |
� | -0.742 |
Token | l |
Token ID | 75 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
apo | +0.506 |
helium | +0.505 |
Amen | +0.484 |
Cassidy | +0.482 |
Hert | +0.465 |
Neg logit contributions | |
cli | -0.453 |
�� | -0.453 |
� | -0.409 |
ette | -0.396 |
� | -0.391 |
Token | ort |
Token ID | 419 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
apo | +0.398 |
helium | +0.397 |
Cassidy | +0.385 |
Amen | +0.383 |
Hert | +0.372 |
Neg logit contributions | |
�� | -0.271 |
cli | -0.270 |
� | -0.238 |
ette | -0.227 |
� | -0.223 |
Token | ot |
Token ID | 313 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
helium | +0.670 |
apo | +0.669 |
Amen | +0.636 |
Cassidy | +0.633 |
Hert | +0.612 |
Neg logit contributions | |
cli | -0.712 |
�� | -0.706 |
� | -0.647 |
ette | -0.628 |
� | -0.623 |
Token | ump |
Token ID | 931 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
cli | +0.996 |
�� | +0.979 |
� | +0.888 |
ette | +0.882 |
� | +0.862 |
Neg logit contributions | |
helium | -1.042 |
apo | -1.027 |
Amen | -0.997 |
Cassidy | -0.994 |
Hert | -0.958 |
Token | 220 |
Token ID | 17572 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
cli | +1.288 |
�� | +1.263 |
� | +1.143 |
ette | +1.134 |
� | +1.110 |
Neg logit contributions | |
helium | -1.440 |
apo | -1.418 |
Amen | -1.379 |
Cassidy | -1.376 |
Hert | -1.327 |
Token | 22 |
Token ID | 1828 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
cli | +1.149 |
�� | +1.127 |
� | +1.014 |
ette | +1.007 |
� | +0.983 |
Neg logit contributions | |
helium | -1.402 |
apo | -1.380 |
Amen | -1.344 |
Cassidy | -1.341 |
Hert | -1.295 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
cli | +1.540 |
�� | +1.496 |
ette | +1.349 |
� | +1.347 |
� | +1.312 |
Neg logit contributions | |
helium | -1.935 |
apo | -1.903 |
Amen | -1.856 |
Cassidy | -1.854 |
Hert | -1.786 |
Token | jpg |
Token ID | 9479 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
cli | +1.843 |
�� | +1.797 |
ette | +1.632 |
� | +1.627 |
� | +1.594 |
Neg logit contributions | |
helium | -1.919 |
apo | -1.877 |
Cassidy | -1.833 |
Amen | -1.831 |
Hert | -1.758 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
cli | +0.997 |
�� | +0.988 |
� | +0.916 |
ette | +0.912 |
� | +0.897 |
Neg logit contributions | |
helium | -0.502 |
apo | -0.489 |
Amen | -0.470 |
Cassidy | -0.468 |
Hert | -0.441 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
cli | +3.837 |
�� | +3.588 |
� | +3.573 |
� | +3.556 |
ette | +3.539 |
Neg logit contributions | |
helium | -2.463 |
apo | -2.404 |
mosqu | -2.326 |
unden | -2.314 |
Cassidy | -2.287 |
Token | Email |
Token ID | 15333 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
cli | +1.819 |
�� | +1.664 |
ette | +1.532 |
� | +1.485 |
� | +1.477 |
Neg logit contributions | |
helium | -3.570 |
apo | -3.493 |
Amen | -3.437 |
Cassidy | -3.436 |
Hert | -3.289 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
cli | +1.396 |
�� | +1.376 |
� | +1.283 |
ette | +1.278 |
� | +1.258 |
Neg logit contributions | |
helium | -0.723 |
apo | -0.704 |
Amen | -0.675 |
Cassidy | -0.673 |
Hert | -0.634 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
cli | +2.471 |
�� | +2.434 |
� | +2.270 |
ette | +2.262 |
� | +2.227 |
Neg logit contributions | |
helium | -1.282 |
apo | -1.249 |
Amen | -1.197 |
Cassidy | -1.193 |
Hert | -1.124 |
Token | Dis |
Token ID | 7279 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
�� | +1.293 |
cli | +1.289 |
� | +1.114 |
ette | +1.106 |
ngth | +1.078 |
Neg logit contributions | |
helium | -1.824 |
apo | -1.811 |
Amen | -1.761 |
Cassidy | -1.748 |
Hert | -1.697 |
Token | where |
Token ID | 810 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
cli | +0.465 |
�� | +0.461 |
� | +0.412 |
ette | +0.411 |
� | +0.400 |
Neg logit contributions | |
helium | -0.462 |
apo | -0.453 |
Amen | -0.442 |
Cassidy | -0.438 |
Hert | -0.424 |
Token | each |
Token ID | 1123 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
helium | +0.128 |
apo | +0.125 |
Amen | +0.121 |
Cassidy | +0.121 |
Hert | +0.117 |
Neg logit contributions | |
cli | -0.150 |
�� | -0.148 |
ette | -0.134 |
� | -0.134 |
� | -0.131 |
Token | part |
Token ID | 636 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
helium | +1.257 |
apo | +1.214 |
Amen | +1.186 |
Cassidy | +1.162 |
Hert | +1.158 |
Neg logit contributions | |
�� | -1.397 |
cli | -1.395 |
ette | -1.228 |
� | -1.226 |
ngth | -1.214 |
Token | between |
Token ID | 1022 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
helium | +0.171 |
apo | +0.169 |
Amen | +0.163 |
Cassidy | +0.161 |
Hert | +0.158 |
Neg logit contributions | |
cli | -0.135 |
�� | -0.135 |
� | -0.117 |
ette | -0.117 |
� | -0.112 |
Token | ' |
Token ID | 705 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
cli | +0.928 |
�� | +0.914 |
� | +0.836 |
ette | +0.833 |
� | +0.817 |
Neg logit contributions | |
helium | -0.762 |
apo | -0.747 |
Amen | -0.724 |
Cassidy | -0.721 |
Hert | -0.692 |
Token | :' |
Token ID | 32105 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
cli | +0.288 |
�� | +0.285 |
� | +0.258 |
ette | +0.255 |
� | +0.249 |
Neg logit contributions | |
helium | -0.283 |
apo | -0.279 |
Amen | -0.270 |
Cassidy | -0.267 |
Hert | -0.259 |
Token | is |
Token ID | 318 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
cli | +2.672 |
�� | +2.584 |
� | +2.352 |
ette | +2.339 |
� | +2.288 |
Neg logit contributions | |
helium | -3.549 |
apo | -3.502 |
Cassidy | -3.423 |
Amen | -3.412 |
Hert | -3.289 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
cli | +0.180 |
�� | +0.178 |
� | +0.160 |
ette | +0.160 |
� | +0.156 |
Neg logit contributions | |
helium | -0.159 |
apo | -0.156 |
Amen | -0.151 |
Cassidy | -0.150 |
Hert | -0.145 |
Token | argument |
Token ID | 4578 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
cli | +0.002 |
�� | +0.002 |
ette | +0.002 |
� | +0.002 |
� | +0.002 |
Neg logit contributions | |
helium | -0.001 |
apo | -0.001 |
Amen | -0.001 |
Cassidy | -0.001 |
Hert | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
helium | +1.718 |
apo | +1.659 |
Amen | +1.613 |
Cassidy | +1.602 |
Hert | +1.575 |
Neg logit contributions | |
�� | -1.731 |
cli | -1.685 |
� | -1.481 |
ette | -1.461 |
deals | -1.449 |
Token | a |
Token ID | 257 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
cli | +0.101 |
�� | +0.101 |
ette | +0.090 |
� | +0.089 |
� | +0.087 |
Neg logit contributions | |
helium | -0.093 |
apo | -0.091 |
Amen | -0.088 |
Cassidy | -0.088 |
Hert | -0.086 |
Token | pub |
Token ID | 2240 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
cli | +1.113 |
�� | +1.091 |
� | +0.998 |
ette | +0.990 |
� | +0.971 |
Neg logit contributions | |
helium | -1.093 |
apo | -1.077 |
Amen | -1.045 |
Cassidy | -1.043 |
Hert | -1.003 |
Token | fn |
Token ID | 24714 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
cli | +1.733 |
�� | +1.702 |
� | +1.559 |
ette | +1.551 |
� | +1.521 |
Neg logit contributions | |
helium | -1.517 |
apo | -1.489 |
Amen | -1.444 |
Cassidy | -1.440 |
Hert | -1.381 |
Token | new |
Token ID | 649 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
cli | +2.379 |
�� | +2.338 |
� | +2.138 |
ette | +2.122 |
� | +2.084 |
Neg logit contributions | |
helium | -2.202 |
apo | -2.169 |
Amen | -2.106 |
Cassidy | -2.099 |
Hert | -2.013 |
Token | ( |
Token ID | 357 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
helium | +0.317 |
apo | +0.312 |
Amen | +0.304 |
Cassidy | +0.302 |
Hert | +0.291 |
Neg logit contributions | |
cli | -0.279 |
�� | -0.274 |
� | -0.247 |
ette | -0.246 |
� | -0.241 |
Token | t |
Token ID | 256 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
cli | +0.060 |
�� | +0.059 |
ette | +0.053 |
� | +0.053 |
� | +0.051 |
Neg logit contributions | |
helium | -0.076 |
apo | -0.074 |
Amen | -0.072 |
Cassidy | -0.072 |
Hert | -0.070 |
Token | : |
Token ID | 1058 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
cli | +0.870 |
�� | +0.854 |
� | +0.768 |
ette | +0.766 |
� | +0.748 |
Neg logit contributions | |
helium | -1.003 |
apo | -0.988 |
Amen | -0.959 |
Cassidy | -0.958 |
Hert | -0.925 |
Token | T |
Token ID | 309 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
cli | +2.474 |
�� | +2.425 |
� | +2.182 |
ette | +2.139 |
� | +2.105 |
Neg logit contributions | |
apo | -3.565 |
helium | -3.559 |
Cassidy | -3.443 |
Amen | -3.438 |
Hert | -3.314 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cli | +0.242 |
�� | +0.238 |
� | +0.217 |
ette | +0.215 |
� | +0.213 |
Neg logit contributions | |
helium | -0.218 |
apo | -0.213 |
Cassidy | -0.206 |
Amen | -0.205 |
Hert | -0.198 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
cli | +0.861 |
�� | +0.846 |
� | +0.782 |
ette | +0.777 |
� | +0.765 |
Neg logit contributions | |
helium | -0.646 |
apo | -0.634 |
Amen | -0.613 |
Cassidy | -0.611 |
Hert | -0.582 |
Token | Own |
Token ID | 11744 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
cli | +2.097 |
�� | +2.057 |
� | +1.868 |
ette | +1.855 |
� | +1.817 |
Neg logit contributions | |
helium | -2.268 |
apo | -2.240 |
Amen | -2.172 |
Cassidy | -2.170 |
Hert | -2.088 |
Token | ed |
Token ID | 276 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
helium | +0.571 |
apo | +0.559 |
Amen | +0.541 |
Cassidy | +0.540 |
Hert | +0.522 |
Neg logit contributions | |
cli | -0.513 |
�� | -0.511 |
� | -0.449 |
ette | -0.442 |
ngth | -0.442 |
Token | * |
Token ID | 1635 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
cli | +0.728 |
�� | +0.714 |
ette | +0.636 |
� | +0.634 |
� | +0.617 |
Neg logit contributions | |
helium | -0.938 |
apo | -0.920 |
Cassidy | -0.900 |
Amen | -0.899 |
Hert | -0.870 |
Token | Get |
Token ID | 3497 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
cli | +2.359 |
�� | +2.318 |
� | +2.143 |
ette | +2.131 |
� | +2.094 |
Neg logit contributions | |
helium | -1.718 |
apo | -1.685 |
Amen | -1.629 |
Cassidy | -1.623 |
Hert | -1.547 |
Token | Volume |
Token ID | 31715 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
helium | +0.405 |
apo | +0.396 |
Cassidy | +0.384 |
Amen | +0.383 |
Hert | +0.371 |
Neg logit contributions | |
cli | -0.400 |
�� | -0.394 |
� | -0.355 |
ette | -0.355 |
� | -0.344 |
Token | () |
Token ID | 3419 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
cli | +0.024 |
�� | +0.023 |
ette | +0.021 |
� | +0.021 |
� | +0.020 |
Neg logit contributions | |
helium | -0.030 |
apo | -0.029 |
Cassidy | -0.028 |
Amen | -0.028 |
Hert | -0.027 |
Token | ; |
Token ID | 2162 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
cli | +0.279 |
�� | +0.274 |
ette | +0.244 |
� | +0.242 |
� | +0.235 |
Neg logit contributions | |
helium | -0.364 |
apo | -0.357 |
Cassidy | -0.348 |
Amen | -0.348 |
Hert | -0.337 |
Token | return |
Token ID | 1441 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
helium | +0.197 |
apo | +0.191 |
Cassidy | +0.186 |
Amen | +0.186 |
Hert | +0.180 |
Neg logit contributions | |
cli | -0.164 |
�� | -0.162 |
ette | -0.144 |
� | -0.142 |
� | -0.139 |
Token | f |
Token ID | 277 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
cli | +3.069 |
�� | +2.998 |
� | +2.785 |
ette | +2.734 |
� | +2.705 |
Neg logit contributions | |
helium | -2.914 |
apo | -2.892 |
Amen | -2.806 |
Cassidy | -2.783 |
Hert | -2.669 |
Token | Mass |
Token ID | 20273 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
helium | +1.348 |
apo | +1.321 |
Cassidy | +1.283 |
Amen | +1.274 |
Hert | +1.233 |
Neg logit contributions | |
cli | -1.355 |
�� | -1.330 |
ette | -1.193 |
� | -1.192 |
� | -1.161 |
Token | ; |
Token ID | 2162 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
cli | +0.445 |
�� | +0.438 |
ette | +0.388 |
� | +0.387 |
� | +0.376 |
Neg logit contributions | |
helium | -0.565 |
apo | -0.552 |
Amen | -0.540 |
Cassidy | -0.540 |
Hert | -0.522 |
Token | } |
Token ID | 1782 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
helium | +0.328 |
apo | +0.321 |
Amen | +0.313 |
Cassidy | +0.312 |
Hert | +0.301 |
Neg logit contributions | |
cli | -0.297 |
�� | -0.292 |
� | -0.263 |
ette | -0.262 |
� | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
helium | +0.814 |
apo | +0.788 |
Amen | +0.768 |
Cassidy | +0.766 |
Hert | +0.737 |
Neg logit contributions | |
cli | -0.933 |
�� | -0.926 |
ette | -0.838 |
� | -0.830 |
� | -0.811 |
Token | When |
Token ID | 1649 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
cli | +0.185 |
�� | +0.183 |
ette | +0.166 |
� | +0.164 |
� | +0.161 |
Neg logit contributions | |
helium | -0.133 |
apo | -0.129 |
Amen | -0.128 |
Cassidy | -0.128 |
Hert | -0.122 |
Token | Re |
Token ID | 797 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
cli | +0.212 |
�� | +0.210 |
ette | +0.191 |
� | +0.189 |
� | +0.184 |
Neg logit contributions | |
helium | -0.178 |
apo | -0.174 |
Cassidy | -0.170 |
Amen | -0.170 |
Hert | -0.163 |
Token | |
Token ID | 3907 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
�� | +0.052 |
cli | +0.052 |
� | +0.045 |
ette | +0.044 |
� | +0.042 |
Neg logit contributions | |
helium | -0.082 |
apo | -0.082 |
Amen | -0.079 |
Cassidy | -0.079 |
Hert | -0.077 |
Token | pub |
Token ID | 12984 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
cli | +0.655 |
�� | +0.644 |
� | +0.589 |
ette | +0.586 |
� | +0.575 |
Neg logit contributions | |
helium | -0.572 |
apo | -0.562 |
Amen | -0.545 |
Cassidy | -0.543 |
Hert | -0.521 |
Token | |
Token ID | 3907 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
cli | +1.146 |
�� | +1.122 |
� | +0.978 |
ette | +0.969 |
� | +0.937 |
Neg logit contributions | |
helium | -2.021 |
apo | -1.994 |
Amen | -1.949 |
Cassidy | -1.949 |
Hert | -1.891 |
Token | lic |
Token ID | 677 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
cli | +0.895 |
�� | +0.887 |
� | +0.804 |
ette | +0.798 |
� | +0.783 |
Neg logit contributions | |
helium | -0.833 |
apo | -0.821 |
Amen | -0.795 |
Cassidy | -0.794 |
Hert | -0.763 |
Token | |
Token ID | 3907 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
cli | +2.131 |
�� | +2.055 |
� | +1.834 |
ette | +1.807 |
� | +1.792 |
Neg logit contributions | |
helium | -3.812 |
apo | -3.764 |
Amen | -3.686 |
Cassidy | -3.645 |
Hert | -3.554 |
Token | ans |
Token ID | 504 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
cli | +0.150 |
�� | +0.150 |
� | +0.135 |
ette | +0.133 |
� | +0.130 |
Neg logit contributions | |
helium | -0.139 |
apo | -0.139 |
Amen | -0.134 |
Cassidy | -0.134 |
Hert | -0.128 |
Token | want |
Token ID | 765 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
cli | +0.998 |
�� | +0.982 |
ette | +0.889 |
� | +0.889 |
� | +0.865 |
Neg logit contributions | |
helium | -0.931 |
apo | -0.911 |
Cassidy | -0.885 |
Amen | -0.884 |
Hert | -0.850 |
Token | to |
Token ID | 284 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
cli | +0.541 |
�� | +0.536 |
ette | +0.480 |
� | +0.477 |
� | +0.464 |
Neg logit contributions | |
helium | -0.595 |
apo | -0.580 |
Cassidy | -0.568 |
Amen | -0.567 |
Hert | -0.545 |
Token | say |
Token ID | 910 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
cli | +0.067 |
�� | +0.066 |
ette | +0.059 |
� | +0.058 |
� | +0.057 |
Neg logit contributions | |
helium | -0.065 |
apo | -0.063 |
Amen | -0.062 |
Cassidy | -0.061 |
Hert | -0.059 |
Token | float |
Token ID | 12178 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
cli | +0.273 |
�� | +0.268 |
� | +0.235 |
ette | +0.234 |
� | +0.227 |
Neg logit contributions | |
helium | -0.428 |
apo | -0.423 |
Cassidy | -0.411 |
Amen | -0.410 |
Hert | -0.398 |
Token | ambient |
Token ID | 25237 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
cli | +1.039 |
�� | +1.020 |
� | +0.931 |
ette | +0.929 |
� | +0.907 |
Neg logit contributions | |
helium | -0.919 |
apo | -0.896 |
Cassidy | -0.869 |
Amen | -0.866 |
Hert | -0.835 |
Token | D |
Token ID | 35 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
cli | +1.260 |
�� | +1.238 |
� | +1.117 |
ette | +1.116 |
� | +1.089 |
Neg logit contributions | |
helium | -1.309 |
apo | -1.282 |
Cassidy | -1.243 |
Amen | -1.241 |
Hert | -1.198 |
Token | ensity |
Token ID | 6377 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
cli | +1.830 |
�� | +1.798 |
� | +1.660 |
ette | +1.652 |
� | +1.622 |
Neg logit contributions | |
helium | -1.379 |
apo | -1.351 |
Amen | -1.308 |
Cassidy | -1.304 |
Hert | -1.245 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
cli | +1.520 |
�� | +1.492 |
� | +1.351 |
ette | +1.346 |
� | +1.316 |
Neg logit contributions | |
helium | -1.598 |
apo | -1.568 |
Amen | -1.524 |
Cassidy | -1.523 |
Hert | -1.467 |
Token | const |
Token ID | 1500 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
cli | +0.945 |
�� | +0.923 |
� | +0.832 |
ette | +0.825 |
� | +0.808 |
Neg logit contributions | |
helium | -1.212 |
apo | -1.194 |
Amen | -1.164 |
Cassidy | -1.162 |
Hert | -1.120 |
Token | { |
Token ID | 1391 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
cli | +2.695 |
�� | +2.604 |
� | +2.380 |
ette | +2.362 |
� | +2.326 |
Neg logit contributions | |
helium | -3.177 |
apo | -3.138 |
Cassidy | -3.054 |
Amen | -3.053 |
Hert | -2.930 |
Token | const |
Token ID | 1500 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
cli | +1.380 |
�� | +1.351 |
� | +1.225 |
ette | +1.217 |
� | +1.191 |
Neg logit contributions | |
helium | -1.527 |
apo | -1.503 |
Amen | -1.463 |
Cassidy | -1.460 |
Hert | -1.406 |
Token | float |
Token ID | 12178 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
cli | +1.423 |
�� | +1.392 |
� | +1.253 |
ette | +1.245 |
� | +1.216 |
Neg logit contributions | |
helium | -1.756 |
apo | -1.729 |
Amen | -1.685 |
Cassidy | -1.681 |
Hert | -1.622 |
Token | f |
Token ID | 277 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
cli | +0.410 |
�� | +0.403 |
ette | +0.366 |
� | +0.366 |
� | +0.356 |
Neg logit contributions | |
helium | -0.377 |
apo | -0.367 |
Cassidy | -0.356 |
Amen | -0.353 |
Hert | -0.343 |
Token | Mass |
Token ID | 20273 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
helium | +0.044 |
apo | +0.043 |
Cassidy | +0.042 |
Amen | +0.042 |
Hert | +0.040 |
Neg logit contributions | |
cli | -0.044 |
�� | -0.044 |
� | -0.040 |
ette | -0.039 |
� | -0.039 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
cli | +0.050 |
�� | +0.048 |
ette | +0.045 |
� | +0.045 |
� | +0.045 |
Neg logit contributions | |
helium | -0.031 |
apo | -0.030 |
Cassidy | -0.029 |
Amen | -0.028 |
Hert | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
helium | +0.577 |
apo | +0.566 |
Amen | +0.552 |
Cassidy | +0.551 |
Hert | +0.532 |
Neg logit contributions | |
cli | -0.533 |
�� | -0.526 |
ette | -0.468 |
� | -0.466 |
� | -0.453 |
Token | CA |
Token ID | 7257 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
cli | +0.189 |
�� | +0.186 |
� | +0.172 |
ette | +0.171 |
� | +0.168 |
Neg logit contributions | |
helium | -0.132 |
apo | -0.129 |
Amen | -0.124 |
Cassidy | -0.124 |
Hert | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
helium | +0.268 |
apo | +0.263 |
Amen | +0.257 |
Cassidy | +0.256 |
Hert | +0.245 |
Neg logit contributions | |
cli | -0.286 |
�� | -0.282 |
ette | -0.254 |
� | -0.253 |
� | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
cli | +1.257 |
�� | +1.241 |
� | +1.155 |
ette | +1.151 |
� | +1.132 |
Neg logit contributions | |
helium | -0.647 |
apo | -0.630 |
Amen | -0.604 |
Cassidy | -0.602 |
Hert | -0.567 |
Token | Dear |
Token ID | 20266 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
cli | +0.986 |
�� | +0.970 |
� | +0.883 |
ette | +0.878 |
� | +0.857 |
Neg logit contributions | |
helium | -0.962 |
apo | -0.947 |
Amen | -0.918 |
Cassidy | -0.915 |
Hert | -0.880 |
Token | Supervisor |
Token ID | 45673 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
cli | +2.914 |
�� | +2.845 |
� | +2.632 |
ette | +2.609 |
� | +2.554 |
Neg logit contributions | |
helium | -2.934 |
apo | -2.890 |
Amen | -2.777 |
Cassidy | -2.774 |
Hert | -2.658 |
Token | Camp |
Token ID | 5425 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
helium | +1.781 |
Amen | +1.760 |
Cassidy | +1.750 |
apo | +1.748 |
Hert | +1.684 |
Neg logit contributions | |
cli | -1.779 |
�� | -1.760 |
� | -1.551 |
ette | -1.527 |
ngth | -1.507 |
Token | os |
Token ID | 418 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
cli | +0.022 |
�� | +0.022 |
� | +0.020 |
ette | +0.019 |
� | +0.019 |
Neg logit contributions | |
helium | -0.019 |
apo | -0.019 |
Amen | -0.018 |
Cassidy | -0.018 |
Hert | -0.017 |
Token | : |
Token ID | 25 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
cli | +0.110 |
�� | +0.108 |
� | +0.097 |
ette | +0.096 |
� | +0.094 |
Neg logit contributions | |
helium | -0.147 |
apo | -0.144 |
Amen | -0.141 |
Cassidy | -0.140 |
Hert | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
cli | +1.156 |
�� | +1.137 |
� | +1.066 |
ette | +1.057 |
� | +1.044 |
Neg logit contributions | |
helium | -0.664 |
apo | -0.648 |
Cassidy | -0.615 |
Amen | -0.613 |
Hert | -0.580 |
Token | of |
Token ID | 286 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
�� | +0.163 |
cli | +0.161 |
ette | +0.140 |
� | +0.139 |
� | +0.135 |
Neg logit contributions | |
helium | -0.183 |
apo | -0.179 |
Amen | -0.177 |
Cassidy | -0.175 |
Hert | -0.170 |
Token | the |
Token ID | 262 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
cli | +0.366 |
�� | +0.358 |
ette | +0.326 |
� | +0.321 |
� | +0.314 |
Neg logit contributions | |
helium | -0.358 |
apo | -0.348 |
Amen | -0.340 |
Cassidy | -0.339 |
Hert | -0.329 |
Token | Joint |
Token ID | 16798 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
cli | +0.595 |
�� | +0.583 |
ette | +0.513 |
� | +0.497 |
� | +0.486 |
Neg logit contributions | |
helium | -0.858 |
apo | -0.827 |
Amen | -0.821 |
Cassidy | -0.814 |
Hert | -0.799 |
Token | Chiefs |
Token ID | 18733 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
helium | +0.638 |
apo | +0.625 |
Amen | +0.619 |
Cassidy | +0.612 |
Hert | +0.589 |
Neg logit contributions | |
�� | -0.838 |
cli | -0.830 |
ette | -0.739 |
ngth | -0.726 |
� | -0.721 |
Token | of |
Token ID | 286 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
helium | +0.058 |
apo | +0.057 |
Amen | +0.056 |
Cassidy | +0.056 |
Hert | +0.054 |
Neg logit contributions | |
cli | -0.045 |
�� | -0.044 |
� | -0.039 |
ette | -0.039 |
� | -0.038 |
Token | Staff |
Token ID | 9983 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
cli | +0.934 |
�� | +0.930 |
ette | +0.854 |
� | +0.839 |
� | +0.823 |
Neg logit contributions | |
helium | -0.545 |
apo | -0.534 |
Amen | -0.515 |
Cassidy | -0.508 |
Hert | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
cli | +2.295 |
�� | +2.236 |
� | +2.014 |
ette | +1.981 |
� | +1.951 |
Neg logit contributions | |
helium | -3.460 |
apo | -3.410 |
Amen | -3.322 |
Cassidy | -3.319 |
Hert | -3.216 |
Token | called |
Token ID | 1444 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
cli | +0.218 |
�� | +0.215 |
ette | +0.195 |
� | +0.193 |
� | +0.188 |
Neg logit contributions | |
helium | -0.192 |
apo | -0.186 |
Amen | -0.182 |
Cassidy | -0.182 |
Hert | -0.175 |
Token | Jones |
Token ID | 5437 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
cli | +0.845 |
�� | +0.832 |
ette | +0.751 |
� | +0.746 |
� | +0.728 |
Neg logit contributions | |
helium | -0.823 |
apo | -0.803 |
Amen | -0.791 |
Cassidy | -0.790 |
Hert | -0.758 |
Token | on |
Token ID | 319 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
cli | +0.541 |
�� | +0.530 |
� | +0.471 |
ette | +0.470 |
� | +0.456 |
Neg logit contributions | |
helium | -0.686 |
apo | -0.676 |
Amen | -0.661 |
Cassidy | -0.660 |
Hert | -0.635 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
cli | +0.368 |
�� | +0.363 |
ette | +0.327 |
� | +0.321 |
� | +0.316 |
Neg logit contributions | |
helium | -0.360 |
apo | -0.345 |
Cassidy | -0.344 |
Amen | -0.341 |
Hert | -0.330 |
Token | data |
Token ID | 7890 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
cli | +0.858 |
�� | +0.844 |
� | +0.711 |
ette | +0.694 |
� | +0.673 |
Neg logit contributions | |
helium | -1.997 |
apo | -1.973 |
Amen | -1.927 |
Cassidy | -1.925 |
Hert | -1.871 |
Token | _ |
Token ID | 62 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
cli | +0.184 |
�� | +0.182 |
� | +0.159 |
ette | +0.157 |
� | +0.154 |
Neg logit contributions | |
helium | -0.275 |
apo | -0.270 |
Cassidy | -0.265 |
Amen | -0.262 |
Hert | -0.255 |
Token | full |
Token ID | 12853 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
cli | +0.380 |
�� | +0.378 |
� | +0.345 |
ette | +0.341 |
� | +0.335 |
Neg logit contributions | |
helium | -0.329 |
apo | -0.327 |
Amen | -0.312 |
Cassidy | -0.311 |
Hert | -0.298 |
Token | v |
Token ID | 410 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
helium | +0.058 |
apo | +0.057 |
Cassidy | +0.055 |
Amen | +0.055 |
Hert | +0.053 |
Neg logit contributions | |
cli | -0.055 |
�� | -0.054 |
� | -0.048 |
ette | -0.048 |
� | -0.047 |
Token | ) |
Token ID | 8 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
cli | +1.037 |
�� | +1.024 |
� | +0.924 |
ette | +0.914 |
� | +0.898 |
Neg logit contributions | |
helium | -1.103 |
apo | -1.085 |
Amen | -1.052 |
Cassidy | -1.051 |
Hert | -1.012 |
Token | { |
Token ID | 1391 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
cli | +1.029 |
�� | +1.010 |
� | +0.900 |
ette | +0.898 |
� | +0.874 |
Neg logit contributions | |
helium | -1.275 |
apo | -1.253 |
Amen | -1.222 |
Cassidy | -1.218 |
Hert | -1.178 |
Token | v |
Token ID | 410 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
cli | +2.801 |
�� | +2.736 |
� | +2.509 |
ette | +2.485 |
� | +2.440 |
Neg logit contributions | |
helium | -2.951 |
apo | -2.912 |
Amen | -2.830 |
Cassidy | -2.825 |
Hert | -2.715 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
cli | +0.314 |
�� | +0.311 |
� | +0.276 |
ette | +0.276 |
� | +0.268 |
Neg logit contributions | |
helium | -0.345 |
apo | -0.339 |
Amen | -0.329 |
Cassidy | -0.328 |
Hert | -0.318 |
Token | ver |
Token ID | 332 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
cli | +1.351 |
�� | +1.331 |
� | +1.214 |
ette | +1.212 |
� | +1.187 |
Neg logit contributions | |
helium | -1.091 |
apo | -1.072 |
Amen | -1.032 |
Cassidy | -1.030 |
Hert | -0.984 |
Token | tex |
Token ID | 16886 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
cli | +0.975 |
�� | +0.960 |
� | +0.855 |
ette | +0.850 |
� | +0.829 |
Neg logit contributions | |
helium | -1.242 |
apo | -1.224 |
Amen | -1.191 |
Cassidy | -1.187 |
Hert | -1.148 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cli | +0.248 |
�� | +0.246 |
� | +0.220 |
ette | +0.218 |
� | +0.215 |
Neg logit contributions | |
helium | -0.244 |
apo | -0.240 |
Amen | -0.232 |
Cassidy | -0.232 |
Hert | -0.224 |
Token | data |
Token ID | 7890 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
�� | +0.713 |
cli | +0.687 |
� | +0.586 |
ette | +0.564 |
� | +0.541 |
Neg logit contributions | |
helium | -1.539 |
apo | -1.536 |
Amen | -1.490 |
Cassidy | -1.484 |
Hert | -1.435 |
Token | _ |
Token ID | 62 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
helium | +0.020 |
apo | +0.020 |
Cassidy | +0.019 |
Amen | +0.019 |
Hert | +0.019 |
Neg logit contributions | |
�� | -0.014 |
cli | -0.013 |
ette | -0.011 |
� | -0.011 |
ngth | -0.011 |
Token | full |
Token ID | 12853 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
cli | +0.563 |
�� | +0.550 |
� | +0.503 |
ette | +0.502 |
� | +0.492 |
Neg logit contributions | |
helium | -0.516 |
apo | -0.504 |
Amen | -0.492 |
Cassidy | -0.491 |
Hert | -0.471 |
Token | v |
Token ID | 410 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
helium | +0.194 |
apo | +0.190 |
Cassidy | +0.185 |
Amen | +0.184 |
Hert | +0.178 |
Neg logit contributions | |
cli | -0.175 |
�� | -0.171 |
ette | -0.153 |
� | -0.153 |
� | -0.149 |
Token | ) |
Token ID | 8 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
helium | +0.104 |
apo | +0.102 |
Amen | +0.099 |
Cassidy | +0.099 |
Hert | +0.094 |
Neg logit contributions | |
cli | -0.125 |
�� | -0.123 |
� | -0.113 |
ette | -0.112 |
� | -0.110 |
Token | { |
Token ID | 1391 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
cli | +0.961 |
�� | +0.936 |
� | +0.848 |
ette | +0.838 |
� | +0.820 |
Neg logit contributions | |
helium | -1.339 |
apo | -1.326 |
Cassidy | -1.292 |
Amen | -1.290 |
Hert | -1.242 |
Token | // |
Token ID | 3373 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
cli | +2.583 |
�� | +2.530 |
� | +2.308 |
ette | +2.273 |
� | +2.235 |
Neg logit contributions | |
helium | -3.096 |
apo | -3.070 |
Amen | -2.990 |
Cassidy | -2.982 |
Hert | -2.864 |
Token | Time |
Token ID | 3862 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
helium | +1.520 |
apo | +1.505 |
Amen | +1.450 |
Cassidy | +1.434 |
Hert | +1.405 |
Neg logit contributions | |
cli | -1.557 |
�� | -1.552 |
ette | -1.385 |
� | -1.355 |
� | -1.317 |
Token | component |
Token ID | 7515 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
helium | +0.059 |
apo | +0.058 |
Amen | +0.056 |
Cassidy | +0.056 |
Hert | +0.055 |
Neg logit contributions | |
cli | -0.064 |
�� | -0.063 |
ette | -0.057 |
� | -0.056 |
� | -0.055 |
Token | const |
Token ID | 1500 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
helium | +1.132 |
apo | +1.088 |
Amen | +1.064 |
Cassidy | +1.064 |
Hert | +1.043 |
Neg logit contributions | |
cli | -1.088 |
�� | -1.083 |
ette | -0.947 |
� | -0.934 |
� | -0.913 |
Token | float |
Token ID | 12178 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
cli | +1.641 |
�� | +1.607 |
� | +1.448 |
ette | +1.440 |
� | +1.406 |
Neg logit contributions | |
helium | -1.954 |
apo | -1.922 |
Amen | -1.872 |
Cassidy | -1.869 |
Hert | -1.803 |
Token | set |
Token ID | 2617 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
cli | +0.374 |
�� | +0.371 |
� | +0.326 |
ette | +0.325 |
� | +0.314 |
Neg logit contributions | |
helium | -0.524 |
apo | -0.522 |
Amen | -0.506 |
Cassidy | -0.502 |
Hert | -0.488 |
Token | dir |
Token ID | 26672 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
helium | +0.171 |
apo | +0.167 |
Amen | +0.163 |
Cassidy | +0.162 |
Hert | +0.157 |
Neg logit contributions | |
cli | -0.169 |
�� | -0.167 |
ette | -0.149 |
� | -0.149 |
� | -0.145 |
Token | = |
Token ID | 28 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
helium | +0.296 |
apo | +0.292 |
Amen | +0.279 |
Cassidy | +0.275 |
Hert | +0.265 |
Neg logit contributions | |
cli | -0.466 |
�� | -0.464 |
� | -0.426 |
ette | -0.422 |
� | -0.417 |
Token | c |
Token ID | 66 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
cli | +0.421 |
�� | +0.418 |
� | +0.372 |
ette | +0.368 |
� | +0.358 |
Neg logit contributions | |
helium | -0.504 |
apo | -0.501 |
Amen | -0.484 |
Cassidy | -0.481 |
Hert | -0.468 |
Token | \ |
Token ID | 59 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
cli | +0.662 |
�� | +0.656 |
� | +0.588 |
ette | +0.583 |
� | +0.571 |
Neg logit contributions | |
helium | -0.671 |
apo | -0.663 |
Amen | -0.639 |
Cassidy | -0.637 |
Hert | -0.616 |
Token | :\ |
Token ID | 7479 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
cli | +2.291 |
�� | +2.243 |
� | +2.042 |
ette | +2.030 |
� | +1.988 |
Neg logit contributions | |
helium | -2.378 |
apo | -2.335 |
Amen | -2.271 |
Cassidy | -2.269 |
Hert | -2.180 |
Token | tmp |
Token ID | 22065 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
cli | +2.764 |
�� | +2.696 |
� | +2.457 |
ette | +2.448 |
� | +2.399 |
Neg logit contributions | |
helium | -2.947 |
apo | -2.893 |
Cassidy | -2.822 |
Amen | -2.819 |
Hert | -2.701 |
Token | : |
Token ID | 25 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
cli | +0.493 |
�� | +0.489 |
� | +0.430 |
ette | +0.424 |
� | +0.415 |
Neg logit contributions | |
helium | -0.688 |
apo | -0.682 |
Amen | -0.663 |
Cassidy | -0.658 |
Hert | -0.641 |
Token | */ |
Token ID | 9466 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
cli | +0.992 |
�� | +0.978 |
� | +0.875 |
ette | +0.870 |
� | +0.849 |
Neg logit contributions | |
helium | -1.152 |
apo | -1.136 |
Amen | -1.105 |
Cassidy | -1.100 |
Hert | -1.064 |
Token | This |
Token ID | 770 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
�� | +0.416 |
cli | +0.412 |
� | +0.366 |
ette | +0.364 |
� | +0.357 |
Neg logit contributions | |
helium | -0.363 |
apo | -0.354 |
Amen | -0.350 |
Cassidy | -0.346 |
Hert | -0.335 |
Token | sets |
Token ID | 5621 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
�� | +0.361 |
cli | +0.355 |
� | +0.310 |
ette | +0.309 |
ngth | +0.299 |
Neg logit contributions | |
helium | -0.391 |
apo | -0.381 |
Amen | -0.371 |
Cassidy | -0.369 |
Hert | -0.362 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
cli | +0.004 |
�� | +0.004 |
� | +0.003 |
ette | +0.003 |
� | +0.003 |
Neg logit contributions | |
helium | -0.006 |
apo | -0.006 |
Amen | -0.006 |
Cassidy | -0.006 |
Hert | -0.006 |
Token | "] |
Token ID | 8973 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
helium | +0.428 |
apo | +0.419 |
Amen | +0.414 |
Cassidy | +0.407 |
Hert | +0.398 |
Neg logit contributions | |
cli | -0.417 |
�� | -0.414 |
� | -0.365 |
ette | -0.363 |
ngth | -0.357 |
Token | [ |
Token ID | 685 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
cli | +0.403 |
�� | +0.399 |
� | +0.359 |
ette | +0.357 |
� | +0.348 |
Neg logit contributions | |
helium | -0.399 |
apo | -0.391 |
Amen | -0.383 |
Cassidy | -0.381 |
Hert | -0.366 |
Token | EC |
Token ID | 2943 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
helium | +0.007 |
apo | +0.007 |
Cassidy | +0.007 |
Amen | +0.007 |
Hert | +0.006 |
Neg logit contributions | |
�� | -0.004 |
cli | -0.004 |
ette | -0.004 |
� | -0.004 |
ngth | -0.003 |
Token | O |
Token ID | 46 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
cli | +0.670 |
�� | +0.655 |
� | +0.589 |
ette | +0.586 |
� | +0.569 |
Neg logit contributions | |
helium | -0.829 |
apo | -0.817 |
Amen | -0.799 |
Cassidy | -0.797 |
Hert | -0.770 |
Token | " |
Token ID | 366 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
cli | +1.152 |
�� | +1.127 |
� | +1.041 |
ette | +1.024 |
� | +1.008 |
Neg logit contributions | |
helium | -1.100 |
apo | -1.079 |
Cassidy | -1.044 |
Amen | -1.036 |
Hert | -0.999 |
Token | A |
Token ID | 32 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
cli | +2.727 |
�� | +2.649 |
� | +2.432 |
� | +2.406 |
ette | +2.399 |
Neg logit contributions | |
helium | -2.887 |
apo | -2.811 |
Amen | -2.770 |
Cassidy | -2.741 |
Hert | -2.660 |
Token | 46 |
Token ID | 3510 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
cli | +0.515 |
�� | +0.512 |
� | +0.460 |
ette | +0.453 |
� | +0.441 |
Neg logit contributions | |
helium | -0.585 |
apo | -0.580 |
Amen | -0.558 |
Cassidy | -0.556 |
Hert | -0.538 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cli | +1.295 |
�� | +1.269 |
� | +1.148 |
ette | +1.141 |
� | +1.116 |
Neg logit contributions | |
helium | -1.457 |
apo | -1.433 |
Amen | -1.395 |
Cassidy | -1.392 |
Hert | -1.341 |
Token | [ |
Token ID | 685 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
cli | +1.289 |
�� | +1.259 |
� | +1.148 |
ette | +1.142 |
� | +1.118 |
Neg logit contributions | |
helium | -1.371 |
apo | -1.349 |
Amen | -1.308 |
Cassidy | -1.306 |
Hert | -1.258 |
Token | White |
Token ID | 12256 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
�� | +0.207 |
cli | +0.202 |
ette | +0.187 |
� | +0.183 |
ngth | +0.181 |
Neg logit contributions | |
helium | -0.133 |
apo | -0.131 |
Amen | -0.128 |
Cassidy | -0.128 |
Hert | -0.122 |
Token | a |
Token ID | 257 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
helium | +0.213 |
apo | +0.208 |
Amen | +0.203 |
Cassidy | +0.202 |
Hert | +0.195 |
Neg logit contributions | |
cli | -0.229 |
�� | -0.226 |
� | -0.204 |
ette | -0.203 |
� | -0.198 |
Token | 44 |
Token ID | 5846 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
helium | +0.345 |
apo | +0.331 |
Cassidy | +0.324 |
Amen | +0.323 |
Hert | +0.312 |
Neg logit contributions | |
cli | -0.402 |
�� | -0.400 |
ette | -0.361 |
� | -0.355 |
� | -0.348 |
Token | th |
Token ID | 400 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
cli | +0.841 |
�� | +0.822 |
� | +0.729 |
ette | +0.724 |
� | +0.703 |
Neg logit contributions | |
helium | -1.251 |
apo | -1.233 |
Amen | -1.204 |
Cassidy | -1.202 |
Hert | -1.164 |
Token | - |
Token ID | 12 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
cli | +1.174 |
�� | +1.154 |
� | +1.038 |
ette | +1.036 |
� | +1.008 |
Neg logit contributions | |
helium | -1.280 |
apo | -1.255 |
Amen | -1.222 |
Cassidy | -1.219 |
Hert | -1.180 |
Token | second |
Token ID | 12227 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
�� | +0.562 |
cli | +0.560 |
ette | +0.499 |
� | +0.499 |
� | +0.478 |
Neg logit contributions | |
helium | -0.593 |
apo | -0.591 |
Amen | -0.567 |
Cassidy | -0.564 |
Hert | -0.550 |
Token | lead |
Token ID | 1085 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
cli | +1.200 |
�� | +1.181 |
ette | +1.063 |
� | +1.060 |
� | +1.036 |
Neg logit contributions | |
helium | -1.082 |
apo | -1.046 |
Cassidy | -1.022 |
Amen | -1.020 |
Hert | -0.982 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
cli | +2.698 |
�� | +2.616 |
� | +2.448 |
ette | +2.418 |
� | +2.375 |
Neg logit contributions | |
helium | -2.875 |
apo | -2.835 |
Amen | -2.750 |
Cassidy | -2.729 |
Hert | -2.634 |
Token | When |
Token ID | 1649 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
cli | +0.113 |
�� | +0.112 |
� | +0.102 |
ette | +0.101 |
� | +0.100 |
Neg logit contributions | |
helium | -0.077 |
apo | -0.075 |
Amen | -0.074 |
Cassidy | -0.074 |
Hert | -0.070 |
Token | Bolton |
Token ID | 35293 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
cli | +0.133 |
�� | +0.131 |
� | +0.119 |
ette | +0.118 |
� | +0.115 |
Neg logit contributions | |
helium | -0.125 |
apo | -0.122 |
Cassidy | -0.119 |
Amen | -0.119 |
Hert | -0.114 |
Token | only |
Token ID | 691 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
cli | +0.099 |
�� | +0.098 |
� | +0.088 |
ette | +0.088 |
ngth | +0.086 |
Neg logit contributions | |
helium | -0.089 |
apo | -0.087 |
Cassidy | -0.085 |
Amen | -0.084 |
Hert | -0.082 |
Token | semi |
Token ID | 10663 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
cli | +0.925 |
�� | +0.913 |
� | +0.830 |
ette | +0.827 |
� | +0.810 |
Neg logit contributions | |
helium | -0.766 |
apo | -0.749 |
Cassidy | -0.726 |
Amen | -0.724 |
Hert | -0.696 |
Token | that |
Token ID | 326 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
helium | +0.630 |
apo | +0.611 |
Cassidy | +0.608 |
Amen | +0.601 |
Hert | +0.576 |
Neg logit contributions | |
cli | -0.735 |
�� | -0.731 |
ette | -0.655 |
� | -0.641 |
ngth | -0.633 |
Token | ." |
Token ID | 526 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
helium | +0.420 |
apo | +0.406 |
Amen | +0.404 |
Cassidy | +0.402 |
Hert | +0.382 |
Neg logit contributions | |
cli | -0.455 |
�� | -0.451 |
ette | -0.396 |
� | -0.394 |
� | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
helium | +0.201 |
apo | +0.195 |
Amen | +0.187 |
Cassidy | +0.186 |
Hert | +0.176 |
Neg logit contributions | |
cli | -0.373 |
�� | -0.366 |
� | -0.343 |
ette | -0.342 |
� | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
�� | +0.035 |
cli | +0.035 |
� | +0.032 |
ette | +0.032 |
� | +0.031 |
Neg logit contributions | |
helium | -0.017 |
apo | -0.016 |
Amen | -0.016 |
Cassidy | -0.016 |
Hert | -0.015 |
Token | ST |
Token ID | 2257 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
apo | +0.216 |
helium | +0.214 |
Amen | +0.205 |
Cassidy | +0.204 |
Hert | +0.195 |
Neg logit contributions | |
�� | -0.259 |
cli | -0.256 |
� | -0.233 |
ette | -0.229 |
ngth | -0.226 |
Token | ORY |
Token ID | 15513 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
cli | +0.792 |
�� | +0.779 |
� | +0.704 |
ette | +0.703 |
� | +0.685 |
Neg logit contributions | |
helium | -0.798 |
apo | -0.786 |
Amen | -0.762 |
Cassidy | -0.761 |
Hert | -0.733 |
Token | : |
Token ID | 25 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
cli | +2.712 |
�� | +2.641 |
� | +2.469 |
ette | +2.427 |
� | +2.394 |
Neg logit contributions | |
helium | -2.813 |
apo | -2.768 |
Amen | -2.670 |
Cassidy | -2.664 |
Hert | -2.561 |
Token | Long |
Token ID | 5882 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
cli | +0.731 |
�� | +0.722 |
ette | +0.648 |
� | +0.644 |
� | +0.629 |
Neg logit contributions | |
helium | -0.668 |
apo | -0.655 |
Amen | -0.644 |
Cassidy | -0.643 |
Hert | -0.618 |
Token | - |
Token ID | 12 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
helium | +0.082 |
apo | +0.081 |
Amen | +0.079 |
Cassidy | +0.079 |
Hert | +0.076 |
Neg logit contributions | |
cli | -0.085 |
�� | -0.083 |
� | -0.075 |
ette | -0.074 |
� | -0.073 |
Token | awaited |
Token ID | 41742 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
cli | +0.464 |
�� | +0.458 |
� | +0.416 |
ette | +0.413 |
� | +0.404 |
Neg logit contributions | |
helium | -0.443 |
apo | -0.437 |
Amen | -0.424 |
Cassidy | -0.422 |
Hert | -0.406 |
Token | New |
Token ID | 968 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
helium | +0.351 |
apo | +0.339 |
Amen | +0.336 |
Cassidy | +0.335 |
Hert | +0.323 |
Neg logit contributions | |
cli | -0.365 |
�� | -0.355 |
ette | -0.318 |
� | -0.312 |
ngth | -0.309 |
Token | can |
Token ID | 460 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
cli | +0.917 |
�� | +0.899 |
� | +0.817 |
ette | +0.814 |
� | +0.793 |
Neg logit contributions | |
helium | -0.776 |
apo | -0.754 |
Amen | -0.739 |
Cassidy | -0.737 |
Hert | -0.707 |
Token | go |
Token ID | 467 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
cli | +0.686 |
�� | +0.678 |
� | +0.610 |
ette | +0.608 |
� | +0.593 |
Neg logit contributions | |
helium | -0.579 |
apo | -0.562 |
Amen | -0.551 |
Cassidy | -0.546 |
Hert | -0.526 |
Token | out |
Token ID | 503 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
cli | +0.438 |
�� | +0.432 |
ette | +0.385 |
� | +0.385 |
� | +0.374 |
Neg logit contributions | |
helium | -0.458 |
apo | -0.447 |
Amen | -0.440 |
Cassidy | -0.439 |
Hert | -0.420 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
helium | +0.425 |
apo | +0.413 |
Amen | +0.409 |
Cassidy | +0.408 |
Hert | +0.390 |
Neg logit contributions | |
cli | -0.405 |
�� | -0.398 |
ette | -0.353 |
� | -0.350 |
� | -0.341 |
Token | run |
Token ID | 1057 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
cli | +1.012 |
�� | +0.995 |
� | +0.903 |
ette | +0.901 |
� | +0.880 |
Neg logit contributions | |
helium | -0.913 |
apo | -0.891 |
Amen | -0.871 |
Cassidy | -0.867 |
Hert | -0.832 |
Token | by |
Token ID | 416 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
helium | +0.266 |
apo | +0.257 |
Amen | +0.255 |
Cassidy | +0.254 |
Hert | +0.244 |
Neg logit contributions | |
cli | -0.259 |
�� | -0.255 |
ette | -0.227 |
� | -0.225 |
� | -0.219 |
Token | themselves |
Token ID | 2405 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
helium | +0.640 |
Amen | +0.585 |
Cassidy | +0.571 |
apo | +0.560 |
Hert | +0.529 |
Neg logit contributions | |
cli | -2.087 |
�� | -2.076 |
ette | -1.918 |
� | -1.912 |
ngth | -1.906 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
cli | +1.168 |
�� | +1.147 |
� | +1.026 |
ette | +1.023 |
� | +0.996 |
Neg logit contributions | |
helium | -1.383 |
apo | -1.358 |
Amen | -1.327 |
Cassidy | -1.324 |
Hert | -1.276 |
Token | but |
Token ID | 475 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
cli | +0.181 |
�� | +0.178 |
ette | +0.159 |
� | +0.159 |
� | +0.154 |
Neg logit contributions | |
helium | -0.186 |
apo | -0.181 |
Amen | -0.178 |
Cassidy | -0.177 |
Hert | -0.170 |
Token | when |
Token ID | 618 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
helium | +0.457 |
apo | +0.437 |
Amen | +0.436 |
Cassidy | +0.435 |
Hert | +0.418 |
Neg logit contributions | |
cli | -0.528 |
�� | -0.521 |
ette | -0.470 |
� | -0.466 |
� | -0.453 |
Token | you |
Token ID | 345 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
cli | +0.335 |
�� | +0.330 |
� | +0.302 |
ette | +0.301 |
� | +0.294 |
Neg logit contributions | |
helium | -0.255 |
apo | -0.247 |
Amen | -0.241 |
Cassidy | -0.241 |
Hert | -0.230 |
Token | rave |
Token ID | 5758 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
helium | +0.106 |
apo | +0.104 |
Cassidy | +0.101 |
Amen | +0.101 |
Hert | +0.098 |
Neg logit contributions | |
cli | -0.097 |
�� | -0.096 |
� | -0.086 |
ette | -0.084 |
� | -0.082 |
Token | : |
Token ID | 25 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
helium | +0.616 |
apo | +0.606 |
Cassidy | +0.593 |
Amen | +0.587 |
Hert | +0.578 |
Neg logit contributions | |
cli | -0.507 |
�� | -0.499 |
� | -0.440 |
ette | -0.440 |
� | -0.425 |
Token |
|
Token ID | 198 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
cli | +0.455 |
�� | +0.449 |
� | +0.411 |
ette | +0.410 |
� | +0.403 |
Neg logit contributions | |
helium | -0.338 |
apo | -0.330 |
Amen | -0.321 |
Cassidy | -0.320 |
Hert | -0.307 |
Token |
|
Token ID | 198 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
helium | +0.232 |
apo | +0.226 |
Amen | +0.219 |
Cassidy | +0.217 |
Hert | +0.205 |
Neg logit contributions | |
�� | -0.529 |
cli | -0.521 |
ette | -0.476 |
� | -0.475 |
ngth | -0.473 |
Token | i |
Token ID | 72 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
helium | +0.554 |
apo | +0.552 |
Amen | +0.523 |
Cassidy | +0.522 |
Hert | +0.504 |
Neg logit contributions | |
�� | -0.615 |
cli | -0.611 |
� | -0.563 |
ette | -0.550 |
ngth | -0.533 |
Token | T |
Token ID | 51 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
helium | +0.012 |
apo | +0.012 |
Cassidy | +0.011 |
Amen | +0.011 |
Hert | +0.011 |
Neg logit contributions | |
cli | -0.010 |
�� | -0.010 |
� | -0.009 |
ette | -0.009 |
� | -0.009 |
Token | unes |
Token ID | 4015 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
apo | +1.495 |
helium | +1.492 |
Amen | +1.409 |
Cassidy | +1.404 |
Hert | +1.359 |
Neg logit contributions | |
cli | -1.530 |
�� | -1.516 |
� | -1.361 |
ette | -1.339 |
� | -1.312 |
Token | ( |
Token ID | 357 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
helium | +0.151 |
apo | +0.146 |
Cassidy | +0.144 |
Amen | +0.144 |
Hert | +0.139 |
Neg logit contributions | |
cli | -0.143 |
�� | -0.141 |
ette | -0.126 |
� | -0.125 |
� | -0.122 |
Token | HD |
Token ID | 10227 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
cli | +0.170 |
�� | +0.169 |
� | +0.152 |
ette | +0.151 |
� | +0.147 |
Neg logit contributions | |
helium | -0.185 |
apo | -0.183 |
Cassidy | -0.176 |
Amen | -0.175 |
Hert | -0.170 |
Token | ) |
Token ID | 8 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
cli | +0.486 |
�� | +0.479 |
� | +0.436 |
ette | +0.435 |
� | +0.426 |
Neg logit contributions | |
helium | -0.415 |
apo | -0.407 |
Cassidy | -0.394 |
Amen | -0.394 |
Hert | -0.379 |
Token | | |
Token ID | 930 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
helium | +0.004 |
apo | +0.004 |
Cassidy | +0.004 |
Amen | +0.004 |
Hert | +0.003 |
Neg logit contributions | |
cli | -0.005 |
�� | -0.005 |
ette | -0.005 |
� | -0.005 |
� | -0.004 |
Token | Should |
Token ID | 10358 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
cli | +0.427 |
�� | +0.421 |
� | +0.375 |
ette | +0.371 |
� | +0.362 |
Neg logit contributions | |
helium | -0.425 |
apo | -0.417 |
Amen | -0.415 |
Cassidy | -0.410 |
Hert | -0.397 |
Token | Not |
Token ID | 1892 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
helium | +0.771 |
Amen | +0.759 |
apo | +0.757 |
Cassidy | +0.741 |
Hert | +0.719 |
Neg logit contributions | |
cli | -1.085 |
�� | -1.075 |
� | -0.967 |
ette | -0.959 |
� | -0.940 |
Token | Be |
Token ID | 1355 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
helium | +0.202 |
Amen | +0.198 |
apo | +0.196 |
Cassidy | +0.195 |
Hert | +0.188 |
Neg logit contributions | |
cli | -0.280 |
�� | -0.277 |
� | -0.248 |
ette | -0.248 |
� | -0.242 |
Token | Ent |
Token ID | 7232 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
helium | +0.360 |
Amen | +0.355 |
apo | +0.355 |
Cassidy | +0.350 |
Hert | +0.335 |
Neg logit contributions | |
cli | -0.455 |
�� | -0.448 |
ette | -0.404 |
� | -0.403 |
� | -0.396 |
Token | itled |
Token ID | 7803 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
apo | +0.317 |
helium | +0.314 |
Amen | +0.291 |
Cassidy | +0.287 |
Hert | +0.273 |
Neg logit contributions | |
cli | -0.868 |
�� | -0.865 |
� | -0.798 |
ette | -0.795 |
ngth | -0.777 |
Token | To |
Token ID | 1675 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
helium | +0.212 |
apo | +0.209 |
Amen | +0.206 |
Cassidy | +0.204 |
Hert | +0.197 |
Neg logit contributions | |
cli | -0.220 |
�� | -0.217 |
ette | -0.195 |
� | -0.195 |
� | -0.190 |
Token | Hold |
Token ID | 9340 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Amen | +1.519 |
helium | +1.516 |
Cassidy | +1.470 |
apo | +1.441 |
Hert | +1.427 |
Neg logit contributions | |
cli | -1.877 |
�� | -1.839 |
ette | -1.618 |
ngth | -1.613 |
� | -1.609 |
Token | Such |
Token ID | 8013 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
helium | +0.155 |
Amen | +0.153 |
Cassidy | +0.150 |
apo | +0.150 |
Hert | +0.145 |
Neg logit contributions | |
cli | -0.192 |
�� | -0.190 |
� | -0.169 |
ette | -0.169 |
ngth | -0.165 |
Token | Views |
Token ID | 29978 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Amen | +0.753 |
helium | +0.753 |
Cassidy | +0.735 |
apo | +0.720 |
Hert | +0.713 |
Neg logit contributions | |
cli | -0.930 |
�� | -0.926 |
ette | -0.818 |
� | -0.806 |
ngth | -0.804 |
Token | ." |
Token ID | 526 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
helium | +0.415 |
apo | +0.407 |
Amen | +0.404 |
Cassidy | +0.399 |
Hert | +0.384 |
Neg logit contributions | |
cli | -0.470 |
�� | -0.464 |
ette | -0.418 |
� | -0.415 |
� | -0.405 |
Token | ... |
Token ID | 986 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
cli | +1.208 |
�� | +1.187 |
� | +1.087 |
ette | +1.084 |
� | +1.063 |
Neg logit contributions | |
helium | -0.952 |
apo | -0.934 |
Amen | -0.909 |
Cassidy | -0.906 |
Hert | -0.867 |
Token | or |
Token ID | 393 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
cli | +0.389 |
�� | +0.382 |
ette | +0.336 |
� | +0.332 |
� | +0.323 |
Neg logit contributions | |
helium | -0.498 |
apo | -0.487 |
Amen | -0.479 |
Cassidy | -0.479 |
Hert | -0.459 |
Token | challenging |
Token ID | 9389 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
helium | +0.025 |
apo | +0.024 |
Cassidy | +0.024 |
Amen | +0.024 |
Hert | +0.023 |
Neg logit contributions | |
cli | -0.028 |
�� | -0.028 |
ette | -0.025 |
� | -0.025 |
� | -0.024 |
Token | this |
Token ID | 428 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
helium | +0.214 |
apo | +0.204 |
Cassidy | +0.203 |
Amen | +0.202 |
Hert | +0.193 |
Neg logit contributions | |
cli | -0.256 |
�� | -0.252 |
ette | -0.228 |
� | -0.225 |
ngth | -0.220 |
Token | particularly |
Token ID | 3573 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
cli | +0.390 |
�� | +0.383 |
ette | +0.345 |
� | +0.342 |
ngth | +0.334 |
Neg logit contributions | |
helium | -0.371 |
apo | -0.356 |
Cassidy | -0.353 |
Amen | -0.352 |
Hert | -0.336 |
Token | fan |
Token ID | 4336 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
helium | +0.308 |
Cassidy | +0.296 |
apo | +0.295 |
Amen | +0.293 |
Hert | +0.279 |
Neg logit contributions | |
cli | -0.324 |
�� | -0.318 |
ette | -0.284 |
� | -0.279 |
ngth | -0.277 |
Token | base |
Token ID | 2779 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
cli | +0.836 |
�� | +0.822 |
� | +0.745 |
ette | +0.745 |
� | +0.725 |
Neg logit contributions | |
helium | -0.785 |
apo | -0.764 |
Amen | -0.747 |
Cassidy | -0.747 |
Hert | -0.714 |
Token | , |
Token ID | 11 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
helium | +2.088 |
Amen | +2.021 |
Cassidy | +2.009 |
apo | +1.995 |
Hert | +1.910 |
Neg logit contributions | |
cli | -1.695 |
�� | -1.687 |
ette | -1.449 |
� | -1.409 |
ngth | -1.404 |
Token | nothing |
Token ID | 2147 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
helium | +0.326 |
apo | +0.315 |
Amen | +0.312 |
Cassidy | +0.310 |
Hert | +0.298 |
Neg logit contributions | |
cli | -0.375 |
�� | -0.370 |
ette | -0.335 |
� | -0.331 |
� | -0.322 |
Token | could |
Token ID | 714 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
helium | +0.309 |
apo | +0.298 |
Cassidy | +0.297 |
Amen | +0.295 |
Hert | +0.284 |
Neg logit contributions | |
cli | -0.291 |
�� | -0.287 |
ette | -0.251 |
� | -0.249 |
ngth | -0.245 |
Token | be |
Token ID | 307 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
helium | +0.115 |
apo | +0.111 |
Amen | +0.108 |
Cassidy | +0.108 |
Hert | +0.104 |
Neg logit contributions | |
cli | -0.115 |
�� | -0.114 |
ette | -0.101 |
� | -0.100 |
� | -0.096 |
Token | further |
Token ID | 2252 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
cli | +0.235 |
�� | +0.232 |
� | +0.217 |
ette | +0.216 |
� | +0.213 |
Neg logit contributions | |
helium | -0.093 |
apo | -0.090 |
Amen | -0.085 |
Cassidy | -0.085 |
Hert | -0.079 |
Token | v |
Token ID | 410 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
cli | +0.963 |
�� | +0.951 |
� | +0.859 |
ette | +0.859 |
� | +0.839 |
Neg logit contributions | |
helium | -0.855 |
apo | -0.834 |
Amen | -0.814 |
Cassidy | -0.808 |
Hert | -0.774 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
helium | +0.192 |
apo | +0.190 |
Amen | +0.184 |
Cassidy | +0.183 |
Hert | +0.176 |
Neg logit contributions | |
�� | -0.187 |
cli | -0.186 |
� | -0.166 |
ette | -0.162 |
� | -0.158 |
Token | urs |
Token ID | 1834 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
helium | +1.071 |
apo | +1.044 |
Amen | +1.018 |
Cassidy | +1.006 |
Hert | +0.971 |
Neg logit contributions | |
cli | -1.149 |
�� | -1.144 |
� | -1.019 |
ette | -1.011 |
� | -0.984 |
Token | et |
Token ID | 2123 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
helium | +0.736 |
apo | +0.707 |
Amen | +0.702 |
Cassidy | +0.692 |
Hert | +0.665 |
Neg logit contributions | |
cli | -0.774 |
�� | -0.772 |
ette | -0.679 |
� | -0.676 |
� | -0.661 |
Token | le |
Token ID | 443 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
helium | +1.405 |
apo | +1.363 |
Amen | +1.347 |
Cassidy | +1.333 |
Hert | +1.274 |
Neg logit contributions | |
cli | -1.518 |
�� | -1.499 |
ette | -1.335 |
� | -1.327 |
ngth | -1.294 |
Token | urs |
Token ID | 1834 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
helium | +0.258 |
apo | +0.252 |
Amen | +0.246 |
Cassidy | +0.244 |
Hert | +0.235 |
Neg logit contributions | |
cli | -0.274 |
�� | -0.274 |
ette | -0.245 |
� | -0.243 |
� | -0.236 |
Token | dev |
Token ID | 1614 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
helium | +1.758 |
apo | +1.685 |
Amen | +1.668 |
Cassidy | +1.643 |
Hert | +1.575 |
Neg logit contributions | |
cli | -1.882 |
�� | -1.880 |
ette | -1.650 |
� | -1.631 |
ngth | -1.607 |
Token | oir |
Token ID | 10840 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
apo | +1.135 |
helium | +1.123 |
Amen | +1.081 |
Cassidy | +1.066 |
Hert | +1.028 |
Neg logit contributions | |
�� | -1.159 |
cli | -1.111 |
� | -1.006 |
ngth | -0.963 |
ette | -0.958 |
Token | s |
Token ID | 82 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
helium | +0.702 |
apo | +0.685 |
Amen | +0.672 |
Cassidy | +0.663 |
Hert | +0.635 |
Neg logit contributions | |
cli | -0.734 |
�� | -0.729 |
� | -0.644 |
ette | -0.643 |
� | -0.627 |
Token | en |
Token ID | 551 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
helium | +0.256 |
apo | +0.249 |
Amen | +0.245 |
Cassidy | +0.242 |
Hert | +0.233 |
Neg logit contributions | |
cli | -0.254 |
�� | -0.251 |
ette | -0.221 |
� | -0.221 |
� | -0.216 |
Token | vers |
Token ID | 690 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
cli | +0.462 |
�� | +0.458 |
ette | +0.415 |
� | +0.414 |
� | +0.405 |
Neg logit contributions | |
helium | -0.409 |
apo | -0.399 |
Amen | -0.390 |
Cassidy | -0.389 |
Hert | -0.372 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
cli | +0.912 |
�� | +0.894 |
� | +0.807 |
ette | +0.801 |
� | +0.783 |
Neg logit contributions | |
helium | -1.151 |
apo | -1.135 |
Amen | -1.107 |
Cassidy | -1.104 |
Hert | -1.065 |
Token | ment |
Token ID | 6229 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
cli | +0.099 |
�� | +0.097 |
ette | +0.088 |
� | +0.087 |
� | +0.085 |
Neg logit contributions | |
helium | -0.090 |
apo | -0.087 |
Amen | -0.085 |
Cassidy | -0.084 |
Hert | -0.081 |
Token | hol |
Token ID | 3937 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
cli | +0.106 |
�� | +0.106 |
� | +0.096 |
ette | +0.095 |
� | +0.093 |
Neg logit contributions | |
helium | -0.080 |
apo | -0.079 |
Amen | -0.075 |
Cassidy | -0.075 |
Hert | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
cli | +0.497 |
�� | +0.488 |
ette | +0.438 |
� | +0.437 |
� | +0.427 |
Neg logit contributions | |
helium | -0.482 |
apo | -0.471 |
Amen | -0.458 |
Cassidy | -0.456 |
Hert | -0.438 |
Token | other |
Token ID | 584 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
helium | +0.405 |
apo | +0.389 |
Amen | +0.380 |
Cassidy | +0.376 |
Hert | +0.367 |
Neg logit contributions | |
cli | -0.438 |
�� | -0.428 |
ette | -0.390 |
� | -0.381 |
� | -0.373 |
Token | flavors |
Token ID | 17361 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
cli | +0.092 |
�� | +0.090 |
ette | +0.082 |
� | +0.081 |
� | +0.079 |
Neg logit contributions | |
helium | -0.082 |
apo | -0.079 |
Amen | -0.077 |
Cassidy | -0.076 |
Hert | -0.074 |
Token | in |
Token ID | 287 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
helium | +0.664 |
apo | +0.656 |
Cassidy | +0.628 |
Amen | +0.628 |
Hert | +0.604 |
Neg logit contributions | |
cli | -0.748 |
�� | -0.736 |
ette | -0.652 |
� | -0.650 |
� | -0.638 |
Token | tobacco |
Token ID | 11219 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
cli | +0.589 |
�� | +0.575 |
ette | +0.523 |
� | +0.517 |
� | +0.507 |
Neg logit contributions | |
helium | -0.530 |
apo | -0.512 |
Amen | -0.499 |
Cassidy | -0.497 |
Hert | -0.480 |
Token | products |
Token ID | 3186 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
helium | +0.331 |
apo | +0.322 |
Amen | +0.313 |
Cassidy | +0.311 |
Hert | +0.299 |
Neg logit contributions | |
cli | -0.389 |
�� | -0.382 |
ette | -0.343 |
� | -0.340 |
� | -0.331 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
cli | +0.178 |
�� | +0.175 |
ette | +0.155 |
� | +0.152 |
� | +0.149 |
Neg logit contributions | |
helium | -0.194 |
apo | -0.190 |
Cassidy | -0.186 |
Amen | -0.185 |
Hert | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
cli | +0.176 |
�� | +0.173 |
� | +0.160 |
ette | +0.160 |
� | +0.157 |
Neg logit contributions | |
helium | -0.095 |
apo | -0.093 |
Amen | -0.090 |
Cassidy | -0.090 |
Hert | -0.085 |
Token | President |
Token ID | 1992 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
cli | +0.316 |
�� | +0.308 |
ette | +0.281 |
� | +0.275 |
ngth | +0.271 |
Neg logit contributions | |
helium | -0.314 |
apo | -0.306 |
Cassidy | -0.302 |
Amen | -0.299 |
Hert | -0.291 |
Token | made |
Token ID | 925 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
helium | +0.584 |
apo | +0.578 |
Cassidy | +0.562 |
Amen | +0.557 |
Hert | +0.537 |
Neg logit contributions | |
cli | -0.568 |
�� | -0.553 |
� | -0.500 |
ette | -0.499 |
ngth | -0.487 |
Token | about |
Token ID | 546 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
cli | +0.436 |
�� | +0.432 |
ette | +0.391 |
� | +0.386 |
� | +0.379 |
Neg logit contributions | |
helium | -0.348 |
apo | -0.343 |
Cassidy | -0.333 |
Amen | -0.333 |
Hert | -0.317 |
Token | the |
Token ID | 262 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
helium | +0.119 |
apo | +0.115 |
Cassidy | +0.114 |
Amen | +0.113 |
Hert | +0.109 |
Neg logit contributions | |
cli | -0.129 |
�� | -0.127 |
ette | -0.115 |
� | -0.113 |
ngth | -0.112 |
Token | terrorist |
Token ID | 7417 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
cli | +0.221 |
�� | +0.217 |
ette | +0.199 |
� | +0.194 |
� | +0.192 |
Neg logit contributions | |
helium | -0.197 |
apo | -0.191 |
Cassidy | -0.189 |
Amen | -0.187 |
Hert | -0.181 |
Token | attacks |
Token ID | 3434 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
helium | +0.342 |
apo | +0.338 |
Cassidy | +0.330 |
Amen | +0.327 |
Hert | +0.314 |
Neg logit contributions | |
cli | -0.405 |
�� | -0.400 |
ette | -0.362 |
� | -0.362 |
� | -0.352 |
Token | on |
Token ID | 319 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
helium | +0.269 |
apo | +0.266 |
Cassidy | +0.258 |
Amen | +0.258 |
Hert | +0.247 |
Neg logit contributions | |
cli | -0.309 |
�� | -0.304 |
ette | -0.276 |
� | -0.276 |
� | -0.269 |
Token | London |
Token ID | 3576 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
helium | +0.623 |
apo | +0.620 |
Cassidy | +0.612 |
Amen | +0.610 |
Hert | +0.581 |
Neg logit contributions | |
cli | -0.636 |
�� | -0.622 |
ette | -0.555 |
� | -0.551 |
ngth | -0.541 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
helium | +1.307 |
apo | +1.305 |
Amen | +1.289 |
Cassidy | +1.277 |
Hert | +1.209 |
Neg logit contributions | |
cli | -1.283 |
�� | -1.280 |
� | -1.125 |
ette | -1.124 |
� | -1.085 |
Token | In |
Token ID | 554 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
cli | +0.185 |
�� | +0.184 |
ette | +0.166 |
� | +0.164 |
� | +0.162 |
Neg logit contributions | |
helium | -0.123 |
apo | -0.120 |
Cassidy | -0.119 |
Amen | -0.119 |
Hert | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
cli | +0.145 |
�� | +0.144 |
ette | +0.130 |
� | +0.129 |
� | +0.126 |
Neg logit contributions | |
helium | -0.132 |
apo | -0.128 |
Amen | -0.126 |
Cassidy | -0.126 |
Hert | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
�� | +0.197 |
cli | +0.197 |
� | +0.180 |
ette | +0.180 |
� | +0.176 |
Neg logit contributions | |
helium | -0.095 |
apo | -0.093 |
Amen | -0.089 |
Cassidy | -0.089 |
Hert | -0.084 |
Token | T |
Token ID | 51 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
cli | +0.373 |
�� | +0.370 |
� | +0.337 |
ette | +0.334 |
� | +0.325 |
Neg logit contributions | |
helium | -0.321 |
apo | -0.318 |
Cassidy | -0.307 |
Amen | -0.306 |
Hert | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
helium | +0.092 |
apo | +0.092 |
Cassidy | +0.087 |
Amen | +0.087 |
Hert | +0.084 |
Neg logit contributions | |
cli | -0.125 |
�� | -0.124 |
� | -0.113 |
ette | -0.112 |
� | -0.110 |
Token | J |
Token ID | 41 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
cli | +0.603 |
�� | +0.591 |
� | +0.525 |
ette | +0.520 |
� | +0.508 |
Neg logit contributions | |
helium | -0.770 |
apo | -0.759 |
Cassidy | -0.744 |
Amen | -0.743 |
Hert | -0.719 |
Token | . |
Token ID | 13 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
cli | +0.203 |
�� | +0.201 |
� | +0.179 |
ette | +0.176 |
� | +0.172 |
Neg logit contributions | |
helium | -0.214 |
apo | -0.213 |
Cassidy | -0.210 |
Amen | -0.208 |
Hert | -0.202 |
Token | Osh |
Token ID | 46614 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
cli | +0.593 |
�� | +0.586 |
� | +0.524 |
ette | +0.520 |
� | +0.511 |
Neg logit contributions | |
helium | -0.561 |
apo | -0.551 |
Cassidy | -0.546 |
Amen | -0.544 |
Hert | -0.525 |
Token | ie |
Token ID | 494 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
apo | +0.777 |
helium | +0.775 |
Cassidy | +0.761 |
Amen | +0.760 |
Hert | +0.732 |
Neg logit contributions | |
�� | -0.520 |
cli | -0.512 |
ngth | -0.431 |
ette | -0.429 |
� | -0.423 |
Token |
|
Token ID | 198 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
helium | +0.374 |
apo | +0.365 |
Cassidy | +0.354 |
Amen | +0.351 |
Hert | +0.338 |
Neg logit contributions | |
cli | -0.608 |
�� | -0.603 |
ette | -0.551 |
� | -0.549 |
� | -0.536 |
Token |
|
Token ID | 198 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
helium | +0.267 |
apo | +0.260 |
Amen | +0.252 |
Cassidy | +0.250 |
Hert | +0.236 |
Neg logit contributions | |
�� | -0.589 |
cli | -0.582 |
ette | -0.532 |
� | -0.532 |
ngth | -0.526 |
Token | Nick |
Token ID | 23609 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
helium | +0.254 |
apo | +0.253 |
Cassidy | +0.245 |
Amen | +0.243 |
Hert | +0.235 |
Neg logit contributions | |
cli | -0.290 |
�� | -0.290 |
� | -0.262 |
ette | -0.259 |
� | -0.251 |
Token | las |
Token ID | 21921 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
cli | +0.143 |
�� | +0.141 |
� | +0.127 |
ette | +0.125 |
� | +0.123 |
Neg logit contributions | |
apo | -0.128 |
helium | -0.128 |
Cassidy | -0.127 |
Amen | -0.124 |
Hert | -0.121 |
Token | to |
Token ID | 284 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
helium | +0.587 |
apo | +0.574 |
Amen | +0.564 |
Cassidy | +0.562 |
Hert | +0.543 |
Neg logit contributions | |
�� | -0.616 |
cli | -0.614 |
ette | -0.537 |
� | -0.534 |
� | -0.520 |
Token | collapse |
Token ID | 9807 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
helium | +0.028 |
apo | +0.028 |
Amen | +0.027 |
Cassidy | +0.027 |
Hert | +0.026 |
Neg logit contributions | |
cli | -0.031 |
�� | -0.030 |
ette | -0.027 |
� | -0.027 |
� | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
helium | +0.828 |
apo | +0.807 |
Amen | +0.788 |
Cassidy | +0.786 |
Hert | +0.757 |
Neg logit contributions | |
cli | -0.839 |
�� | -0.836 |
ette | -0.734 |
� | -0.727 |
� | -0.707 |
Token | In |
Token ID | 554 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
cli | +0.102 |
�� | +0.102 |
ette | +0.091 |
� | +0.090 |
� | +0.088 |
Neg logit contributions | |
helium | -0.080 |
apo | -0.078 |
Amen | -0.078 |
Cassidy | -0.077 |
Hert | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
helium | +0.257 |
apo | +0.252 |
Amen | +0.246 |
Cassidy | +0.246 |
Hert | +0.235 |
Neg logit contributions | |
cli | -0.306 |
�� | -0.303 |
ette | -0.274 |
� | -0.272 |
� | -0.266 |
Token | end |
Token ID | 886 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
helium | +0.398 |
apo | +0.387 |
Amen | +0.378 |
Cassidy | +0.377 |
Hert | +0.360 |
Neg logit contributions | |
cli | -0.531 |
�� | -0.522 |
ette | -0.479 |
� | -0.476 |
� | -0.465 |
Token | of |
Token ID | 286 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
helium | +0.468 |
apo | +0.459 |
Amen | +0.452 |
Cassidy | +0.448 |
Hert | +0.436 |
Neg logit contributions | |
cli | -0.334 |
�� | -0.332 |
ette | -0.285 |
� | -0.284 |
� | -0.274 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
cli | +0.047 |
�� | +0.047 |
ette | +0.042 |
� | +0.041 |
� | +0.040 |
Neg logit contributions | |
helium | -0.045 |
apo | -0.044 |
Amen | -0.043 |
Cassidy | -0.043 |
Hert | -0.041 |
Token | month |
Token ID | 1227 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
cli | +0.106 |
�� | +0.105 |
ette | +0.095 |
� | +0.095 |
� | +0.092 |
Neg logit contributions | |
helium | -0.086 |
apo | -0.084 |
Amen | -0.082 |
Cassidy | -0.082 |
Hert | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
helium | +0.002 |
apo | +0.002 |
Amen | +0.001 |
Cassidy | +0.001 |
Hert | +0.001 |
Neg logit contributions | |
cli | -0.001 |
�� | -0.001 |
� | -0.001 |
ette | -0.001 |
� | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
helium | +0.683 |
apo | +0.667 |
Amen | +0.657 |
Cassidy | +0.650 |
Hert | +0.629 |
Neg logit contributions | |
cli | -0.685 |
�� | -0.683 |
ette | -0.602 |
� | -0.600 |
� | -0.582 |
Token | this |
Token ID | 428 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
helium | +0.261 |
apo | +0.252 |
Cassidy | +0.247 |
Amen | +0.246 |
Hert | +0.238 |
Neg logit contributions | |
cli | -0.320 |
�� | -0.315 |
ette | -0.287 |
� | -0.285 |
� | -0.279 |
Token | demographic |
Token ID | 16728 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
helium | +0.195 |
apo | +0.188 |
Cassidy | +0.184 |
Amen | +0.183 |
Hert | +0.177 |
Neg logit contributions | |
cli | -0.237 |
�� | -0.234 |
ette | -0.211 |
� | -0.209 |
� | -0.205 |
Token | group |
Token ID | 1448 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
cli | +0.316 |
�� | +0.311 |
ette | +0.277 |
� | +0.276 |
� | +0.268 |
Neg logit contributions | |
helium | -0.368 |
apo | -0.362 |
Cassidy | -0.353 |
Amen | -0.352 |
Hert | -0.339 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
helium | +0.069 |
apo | +0.068 |
Cassidy | +0.067 |
Amen | +0.067 |
Hert | +0.064 |
Neg logit contributions | |
cli | -0.060 |
�� | -0.059 |
ette | -0.053 |
� | -0.052 |
� | -0.051 |
Token | In |
Token ID | 554 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
cli | +0.215 |
�� | +0.213 |
ette | +0.193 |
� | +0.193 |
� | +0.189 |
Neg logit contributions | |
helium | -0.151 |
apo | -0.148 |
Cassidy | -0.145 |
Amen | -0.145 |
Hert | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
cli | +0.346 |
�� | +0.342 |
ette | +0.311 |
� | +0.311 |
� | +0.304 |
Neg logit contributions | |
helium | -0.286 |
apo | -0.280 |
Cassidy | -0.272 |
Amen | -0.272 |
Hert | -0.261 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
helium | +0.057 |
apo | +0.055 |
Cassidy | +0.054 |
Amen | +0.054 |
Hert | +0.051 |
Neg logit contributions | |
cli | -0.074 |
�� | -0.073 |
ette | -0.066 |
� | -0.066 |
� | -0.065 |
Token | presidential |
Token ID | 4787 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
helium | +0.398 |
apo | +0.389 |
Cassidy | +0.385 |
Amen | +0.383 |
Hert | +0.370 |
Neg logit contributions | |
cli | -0.346 |
�� | -0.337 |
ette | -0.299 |
� | -0.295 |
ngth | -0.291 |
Token | race |
Token ID | 3234 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
cli | +0.510 |
�� | +0.498 |
� | +0.444 |
ette | +0.443 |
� | +0.430 |
Neg logit contributions | |
helium | -0.618 |
apo | -0.604 |
Cassidy | -0.591 |
Amen | -0.590 |
Hert | -0.568 |
Token | , |
Token ID | 11 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
helium | +0.261 |
apo | +0.257 |
Cassidy | +0.254 |
Amen | +0.252 |
Hert | +0.244 |
Neg logit contributions | |
cli | -0.169 |
�� | -0.167 |
ette | -0.144 |
� | -0.142 |
� | -0.138 |
Token | Republican |
Token ID | 3415 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
helium | +0.428 |
apo | +0.415 |
Cassidy | +0.412 |
Amen | +0.409 |
Hert | +0.394 |
Neg logit contributions | |
cli | -0.437 |
�� | -0.433 |
ette | -0.388 |
� | -0.385 |
� | -0.374 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
helium | +0.060 |
apo | +0.058 |
Cassidy | +0.056 |
Amen | +0.056 |
Hert | +0.054 |
Neg logit contributions | |
cli | -0.067 |
�� | -0.066 |
ette | -0.060 |
� | -0.060 |
� | -0.058 |
Token | He |
Token ID | 679 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
cli | +0.530 |
�� | +0.526 |
� | +0.480 |
ette | +0.480 |
� | +0.470 |
Neg logit contributions | |
helium | -0.329 |
apo | -0.320 |
Amen | -0.314 |
Cassidy | -0.312 |
Hert | -0.298 |
Token | had |
Token ID | 550 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
helium | +0.117 |
apo | +0.115 |
Cassidy | +0.112 |
Amen | +0.112 |
Hert | +0.109 |
Neg logit contributions | |
�� | -0.100 |
cli | -0.099 |
� | -0.087 |
ette | -0.086 |
ngth | -0.083 |
Token | 19 |
Token ID | 678 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
helium | +0.666 |
apo | +0.633 |
Amen | +0.631 |
Cassidy | +0.630 |
Hert | +0.607 |
Neg logit contributions | |
cli | -0.800 |
�� | -0.797 |
ette | -0.719 |
� | -0.708 |
� | -0.691 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
cli | +0.429 |
�� | +0.421 |
� | +0.384 |
ette | +0.382 |
� | +0.374 |
Neg logit contributions | |
helium | -0.403 |
apo | -0.395 |
Amen | -0.383 |
Cassidy | -0.383 |
Hert | -0.368 |
Token | points |
Token ID | 2173 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
cli | +0.804 |
�� | +0.788 |
� | +0.706 |
ette | +0.697 |
� | +0.684 |
Neg logit contributions | |
helium | -1.133 |
apo | -1.118 |
Cassidy | -1.090 |
Amen | -1.088 |
Hert | -1.050 |
Token | against |
Token ID | 1028 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
cli | +0.546 |
�� | +0.539 |
ette | +0.487 |
� | +0.487 |
� | +0.476 |
Neg logit contributions | |
helium | -0.452 |
apo | -0.441 |
Cassidy | -0.429 |
Amen | -0.428 |
Hert | -0.411 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
cli | +0.457 |
�� | +0.450 |
ette | +0.404 |
� | +0.403 |
� | +0.393 |
Neg logit contributions | |
helium | -0.462 |
apo | -0.451 |
Amen | -0.441 |
Cassidy | -0.440 |
Hert | -0.426 |
Token | Saints |
Token ID | 13048 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
helium | +0.487 |
apo | +0.470 |
Cassidy | +0.463 |
Amen | +0.461 |
Hert | +0.449 |
Neg logit contributions | |
cli | -0.471 |
�� | -0.460 |
ette | -0.414 |
� | -0.408 |
ngth | -0.398 |
Token | last |
Token ID | 938 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
helium | +0.790 |
apo | +0.769 |
Cassidy | +0.752 |
Amen | +0.746 |
Hert | +0.715 |
Neg logit contributions | |
cli | -1.097 |
�� | -1.087 |
ette | -0.974 |
� | -0.971 |
ngth | -0.951 |
Token | year |
Token ID | 614 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
helium | +0.206 |
apo | +0.201 |
Amen | +0.196 |
Cassidy | +0.196 |
Hert | +0.188 |
Neg logit contributions | |
cli | -0.266 |
�� | -0.261 |
ette | -0.237 |
� | -0.236 |
� | -0.231 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
cli | +0.103 |
�� | +0.102 |
� | +0.091 |
ette | +0.090 |
� | +0.088 |
Neg logit contributions | |
helium | -0.113 |
apo | -0.110 |
Cassidy | -0.108 |
Amen | -0.108 |
Hert | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
helium | +0.867 |
apo | +0.840 |
Amen | +0.821 |
Cassidy | +0.821 |
Hert | +0.791 |
Neg logit contributions | |
cli | -0.912 |
�� | -0.900 |
� | -0.812 |
ette | -0.811 |
� | -0.794 |
Token | device |
Token ID | 3335 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
cli | +0.126 |
�� | +0.124 |
� | +0.113 |
ette | +0.113 |
� | +0.111 |
Neg logit contributions | |
helium | -0.094 |
apo | -0.090 |
Amen | -0.088 |
Cassidy | -0.088 |
Hert | -0.084 |
Token | has |
Token ID | 468 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
cli | +0.459 |
�� | +0.455 |
� | +0.395 |
ette | +0.394 |
� | +0.381 |
Neg logit contributions | |
helium | -0.585 |
apo | -0.569 |
Cassidy | -0.559 |
Amen | -0.558 |
Hert | -0.541 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
cli | +0.070 |
�� | +0.070 |
ette | +0.062 |
� | +0.061 |
� | +0.060 |
Neg logit contributions | |
helium | -0.071 |
apo | -0.068 |
Cassidy | -0.067 |
Amen | -0.067 |
Hert | -0.065 |
Token | blank |
Token ID | 9178 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
helium | +0.084 |
apo | +0.081 |
Cassidy | +0.079 |
Amen | +0.078 |
Hert | +0.076 |
Neg logit contributions | |
cli | -0.107 |
�� | -0.105 |
ette | -0.096 |
� | -0.095 |
� | -0.093 |
Token | spot |
Token ID | 4136 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
cli | +1.365 |
�� | +1.341 |
� | +1.234 |
ette | +1.229 |
� | +1.204 |
Neg logit contributions | |
helium | -1.135 |
apo | -1.115 |
Amen | -1.081 |
Cassidy | -1.078 |
Hert | -1.031 |
Token | next |
Token ID | 1306 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
cli | +0.624 |
�� | +0.616 |
� | +0.549 |
ette | +0.548 |
� | +0.536 |
Neg logit contributions | |
helium | -0.643 |
apo | -0.630 |
Amen | -0.615 |
Cassidy | -0.612 |
Hert | -0.589 |
Token | to |
Token ID | 284 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
cli | +0.306 |
�� | +0.300 |
� | +0.268 |
ette | +0.267 |
� | +0.260 |
Neg logit contributions | |
helium | -0.388 |
apo | -0.381 |
Amen | -0.372 |
Cassidy | -0.372 |
Hert | -0.359 |
Token | it |
Token ID | 340 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
cli | +0.105 |
�� | +0.103 |
� | +0.094 |
ette | +0.093 |
� | +0.091 |
Neg logit contributions | |
helium | -0.099 |
apo | -0.097 |
Amen | -0.094 |
Cassidy | -0.094 |
Hert | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
helium | +0.179 |
apo | +0.175 |
Amen | +0.171 |
Cassidy | +0.171 |
Hert | +0.165 |
Neg logit contributions | |
cli | -0.162 |
�� | -0.160 |
� | -0.141 |
ette | -0.141 |
� | -0.136 |
Token | s |
Token ID | 82 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
cli | +0.432 |
�� | +0.428 |
� | +0.385 |
ette | +0.384 |
� | +0.373 |
Neg logit contributions | |
helium | -0.415 |
apo | -0.409 |
Amen | -0.398 |
Cassidy | -0.397 |
Hert | -0.382 |
Token | team |
Token ID | 1074 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
helium | +0.390 |
apo | +0.380 |
Amen | +0.370 |
Cassidy | +0.367 |
Hert | +0.357 |
Neg logit contributions | |
cli | -0.452 |
�� | -0.448 |
ette | -0.403 |
� | -0.401 |
� | -0.389 |
Token | � |
Token ID | 447 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
cli | +0.214 |
�� | +0.212 |
ette | +0.189 |
� | +0.187 |
� | +0.181 |
Neg logit contributions | |
helium | -0.200 |
apo | -0.196 |
Cassidy | -0.191 |
Amen | -0.190 |
Hert | -0.183 |
Token | � |
Token ID | 247 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
helium | +0.162 |
apo | +0.158 |
Amen | +0.153 |
Cassidy | +0.152 |
Hert | +0.145 |
Neg logit contributions | |
cli | -0.233 |
�� | -0.228 |
� | -0.212 |
ette | -0.211 |
� | -0.207 |
Token | s |
Token ID | 82 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
�� | +0.053 |
cli | +0.053 |
ette | +0.047 |
� | +0.047 |
� | +0.045 |
Neg logit contributions | |
helium | -0.049 |
apo | -0.048 |
Amen | -0.047 |
Cassidy | -0.046 |
Hert | -0.045 |
Token | study |
Token ID | 2050 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
cli | +0.427 |
�� | +0.424 |
ette | +0.383 |
� | +0.382 |
� | +0.371 |
Neg logit contributions | |
helium | -0.374 |
apo | -0.367 |
Amen | -0.354 |
Cassidy | -0.352 |
Hert | -0.341 |
Token | is |
Token ID | 318 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
cli | +0.705 |
�� | +0.697 |
ette | +0.618 |
� | +0.614 |
� | +0.595 |
Neg logit contributions | |
helium | -0.775 |
apo | -0.763 |
Cassidy | -0.740 |
Amen | -0.738 |
Hert | -0.715 |
Token | one |
Token ID | 530 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
helium | +0.472 |
apo | +0.456 |
Cassidy | +0.449 |
Amen | +0.444 |
Hert | +0.425 |
Neg logit contributions | |
cli | -0.664 |
�� | -0.655 |
ette | -0.599 |
� | -0.589 |
� | -0.578 |
Token | of |
Token ID | 286 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
helium | +0.344 |
apo | +0.337 |
Cassidy | +0.328 |
Amen | +0.328 |
Hert | +0.317 |
Neg logit contributions | |
cli | -0.278 |
�� | -0.272 |
ette | -0.242 |
� | -0.242 |
� | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
cli | +0.672 |
�� | +0.665 |
ette | +0.601 |
� | +0.595 |
� | +0.580 |
Neg logit contributions | |
helium | -0.660 |
apo | -0.645 |
Cassidy | -0.629 |
Amen | -0.629 |
Hert | -0.605 |
Token | first |
Token ID | 717 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
helium | +0.413 |
apo | +0.394 |
Cassidy | +0.381 |
Amen | +0.374 |
Hert | +0.358 |
Neg logit contributions | |
cli | -0.812 |
�� | -0.811 |
ette | -0.747 |
� | -0.735 |
� | -0.721 |
Token | , |
Token ID | 11 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
helium | +0.006 |
apo | +0.006 |
Cassidy | +0.006 |
Amen | +0.006 |
Hert | +0.006 |
Neg logit contributions | |
cli | -0.006 |
�� | -0.006 |
ette | -0.005 |
� | -0.005 |
� | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
helium | +0.056 |
apo | +0.054 |
Cassidy | +0.053 |
Amen | +0.053 |
Hert | +0.051 |
Neg logit contributions | |
cli | -0.064 |
�� | -0.063 |
ette | -0.057 |
� | -0.056 |
� | -0.055 |
Token | large |
Token ID | 1588 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
helium | +0.399 |
apo | +0.386 |
Cassidy | +0.381 |
Amen | +0.379 |
Hert | +0.368 |
Neg logit contributions | |
cli | -0.453 |
�� | -0.448 |
ette | -0.405 |
� | -0.397 |
� | -0.390 |
Token | part |
Token ID | 636 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
helium | +0.262 |
apo | +0.254 |
Cassidy | +0.248 |
Amen | +0.248 |
Hert | +0.239 |
Neg logit contributions | |
cli | -0.279 |
�� | -0.274 |
ette | -0.245 |
� | -0.244 |
� | -0.238 |
Token | , |
Token ID | 11 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
helium | +1.309 |
apo | +1.273 |
Cassidy | +1.263 |
Amen | +1.256 |
Hert | +1.225 |
Neg logit contributions | |
cli | -0.946 |
�� | -0.924 |
ette | -0.812 |
� | -0.779 |
ngth | -0.774 |
Token | by |
Token ID | 416 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
helium | +0.532 |
apo | +0.521 |
Cassidy | +0.509 |
Amen | +0.509 |
Hert | +0.491 |
Neg logit contributions | |
cli | -0.571 |
�� | -0.563 |
ette | -0.508 |
� | -0.503 |
� | -0.489 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
cli | +0.578 |
�� | +0.568 |
ette | +0.514 |
� | +0.508 |
� | +0.497 |
Neg logit contributions | |
helium | -0.539 |
apo | -0.520 |
Cassidy | -0.515 |
Amen | -0.514 |
Hert | -0.496 |
Token | machine |
Token ID | 4572 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
helium | +0.019 |
apo | +0.018 |
Cassidy | +0.018 |
Amen | +0.018 |
Hert | +0.017 |
Neg logit contributions | |
cli | -0.022 |
�� | -0.022 |
ette | -0.020 |
� | -0.020 |
� | -0.019 |
Token | at |
Token ID | 379 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
helium | +0.365 |
apo | +0.357 |
Amen | +0.348 |
Cassidy | +0.347 |
Hert | +0.336 |
Neg logit contributions | |
cli | -0.369 |
�� | -0.362 |
� | -0.326 |
ette | -0.325 |
� | -0.316 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
helium | +0.242 |
apo | +0.235 |
Cassidy | +0.231 |
Amen | +0.231 |
Hert | +0.224 |
Neg logit contributions | |
cli | -0.267 |
�� | -0.262 |
ette | -0.235 |
� | -0.233 |
� | -0.228 |
Token | Franklin |
Token ID | 14021 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
helium | +0.111 |
apo | +0.107 |
Amen | +0.106 |
Cassidy | +0.105 |
Hert | +0.102 |
Neg logit contributions | |
cli | -0.123 |
�� | -0.121 |
ette | -0.109 |
� | -0.108 |
� | -0.107 |
Token | sweeping |
Token ID | 18404 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
cli | +0.075 |
�� | +0.074 |
� | +0.067 |
ette | +0.067 |
� | +0.065 |
Neg logit contributions | |
helium | -0.057 |
apo | -0.055 |
Cassidy | -0.054 |
Amen | -0.054 |
Hert | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
cli | +0.700 |
�� | +0.688 |
� | +0.623 |
ette | +0.620 |
� | +0.606 |
Neg logit contributions | |
helium | -0.659 |
apo | -0.644 |
Amen | -0.629 |
Cassidy | -0.629 |
Hert | -0.603 |
Token | nominations |
Token ID | 30994 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
helium | +0.644 |
apo | +0.620 |
Cassidy | +0.612 |
Amen | +0.611 |
Hert | +0.592 |
Neg logit contributions | |
cli | -0.692 |
�� | -0.679 |
ette | -0.608 |
� | -0.604 |
� | -0.593 |
Token | as |
Token ID | 355 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
cli | +0.181 |
�� | +0.178 |
� | +0.160 |
ette | +0.160 |
� | +0.156 |
Neg logit contributions | |
helium | -0.162 |
apo | -0.159 |
Amen | -0.155 |
Cassidy | -0.154 |
Hert | -0.148 |
Token | decisively |
Token ID | 47948 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
cli | +0.199 |
�� | +0.195 |
� | +0.177 |
ette | +0.176 |
� | +0.173 |
Neg logit contributions | |
helium | -0.171 |
apo | -0.167 |
Cassidy | -0.163 |
Amen | -0.163 |
Hert | -0.156 |
Token | as |
Token ID | 355 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
helium | +0.300 |
apo | +0.295 |
Amen | +0.286 |
Cassidy | +0.285 |
Hert | +0.272 |
Neg logit contributions | |
cli | -0.369 |
�� | -0.364 |
ette | -0.330 |
� | -0.329 |
� | -0.321 |
Token | John |
Token ID | 1757 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
cli | +0.852 |
�� | +0.837 |
� | +0.764 |
ette | +0.761 |
� | +0.746 |
Neg logit contributions | |
helium | -0.741 |
apo | -0.727 |
Amen | -0.706 |
Cassidy | -0.705 |
Hert | -0.675 |
Token | C |
Token ID | 327 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
cli | +1.240 |
�� | +1.217 |
� | +1.108 |
ette | +1.102 |
� | +1.079 |
Neg logit contributions | |
helium | -1.199 |
apo | -1.178 |
Amen | -1.146 |
Cassidy | -1.145 |
Hert | -1.099 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
helium | +0.456 |
apo | +0.451 |
Cassidy | +0.440 |
Amen | +0.439 |
Hert | +0.424 |
Neg logit contributions | |
cli | -0.501 |
�� | -0.500 |
� | -0.448 |
ette | -0.442 |
� | -0.430 |
Token | Wright |
Token ID | 12206 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
cli | +0.024 |
�� | +0.024 |
ette | +0.022 |
� | +0.022 |
� | +0.021 |
Neg logit contributions | |
helium | -0.020 |
apo | -0.019 |
Amen | -0.019 |
Cassidy | -0.019 |
Hert | -0.018 |
Token | ? |
Token ID | 30 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
cli | +0.726 |
�� | +0.711 |
� | +0.637 |
ette | +0.633 |
� | +0.617 |
Neg logit contributions | |
helium | -0.807 |
apo | -0.799 |
Cassidy | -0.776 |
Amen | -0.773 |
Hert | -0.746 |
Token | icide |
Token ID | 5285 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
cli | +0.573 |
�� | +0.562 |
� | +0.507 |
ette | +0.504 |
� | +0.492 |
Neg logit contributions | |
helium | -0.672 |
apo | -0.661 |
Amen | -0.644 |
Cassidy | -0.642 |
Hert | -0.619 |
Token | pre |
Token ID | 3866 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
cli | +0.290 |
�� | +0.285 |
� | +0.259 |
ette | +0.257 |
� | +0.252 |
Neg logit contributions | |
helium | -0.297 |
apo | -0.292 |
Amen | -0.284 |
Cassidy | -0.283 |
Hert | -0.272 |
Token | vention |
Token ID | 4018 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
cli | +0.378 |
�� | +0.369 |
� | +0.328 |
ette | +0.326 |
� | +0.317 |
Neg logit contributions | |
helium | -0.561 |
apo | -0.553 |
Amen | -0.540 |
Cassidy | -0.539 |
Hert | -0.521 |
Token | / |
Token ID | 14 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
cli | +0.313 |
�� | +0.308 |
� | +0.280 |
ette | +0.278 |
� | +0.272 |
Neg logit contributions | |
helium | -0.313 |
apo | -0.308 |
Amen | -0.299 |
Cassidy | -0.298 |
Hert | -0.287 |
Token | doc |
Token ID | 15390 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
cli | +0.524 |
�� | +0.516 |
� | +0.476 |
ette | +0.474 |
� | +0.465 |
Neg logit contributions | |
helium | -0.387 |
apo | -0.379 |
Amen | -0.366 |
Cassidy | -0.365 |
Hert | -0.348 |
Token | uments |
Token ID | 2886 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
cli | +0.211 |
�� | +0.208 |
� | +0.180 |
ette | +0.174 |
� | +0.170 |
Neg logit contributions | |
helium | -0.410 |
apo | -0.405 |
Amen | -0.398 |
Cassidy | -0.396 |
Hert | -0.385 |
Token | / |
Token ID | 14 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
cli | +2.667 |
�� | +2.594 |
ette | +2.407 |
� | +2.401 |
� | +2.353 |
Neg logit contributions | |
helium | -2.338 |
apo | -2.271 |
Cassidy | -2.213 |
Amen | -2.211 |
Hert | -2.123 |
Token | older |
Token ID | 19892 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
cli | +0.871 |
�� | +0.857 |
� | +0.787 |
ette | +0.783 |
� | +0.767 |
Neg logit contributions | |
helium | -0.706 |
apo | -0.694 |
Amen | -0.671 |
Cassidy | -0.669 |
Hert | -0.640 |
Token | adult |
Token ID | 49922 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
cli | +0.965 |
�� | +0.941 |
� | +0.837 |
ette | +0.832 |
� | +0.810 |
Neg logit contributions | |
helium | -1.413 |
apo | -1.389 |
Amen | -1.357 |
Cassidy | -1.356 |
Hert | -1.313 |
Token | / |
Token ID | 14 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
cli | +2.446 |
�� | +2.370 |
ette | +2.224 |
� | +2.215 |
� | +2.185 |
Neg logit contributions | |
helium | -1.589 |
apo | -1.523 |
Cassidy | -1.493 |
Amen | -1.482 |
Hert | -1.416 |
Token | plan |
Token ID | 11578 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
cli | +0.520 |
�� | +0.513 |
� | +0.473 |
ette | +0.471 |
� | +0.463 |
Neg logit contributions | |
helium | -0.349 |
apo | -0.343 |
Amen | -0.330 |
Cassidy | -0.329 |
Hert | -0.313 |
Token | .) |
Token ID | 2014 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
cli | +0.235 |
�� | +0.232 |
ette | +0.208 |
� | +0.207 |
� | +0.202 |
Neg logit contributions | |
helium | -0.225 |
apo | -0.221 |
Amen | -0.215 |
Cassidy | -0.215 |
Hert | -0.206 |
Token | So |
Token ID | 1406 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
helium | +0.744 |
Amen | +0.729 |
apo | +0.718 |
Cassidy | +0.714 |
Hert | +0.687 |
Neg logit contributions | |
cli | -1.159 |
�� | -1.157 |
ette | -1.033 |
� | -1.021 |
ngth | -1.009 |
Token | I |
Token ID | 314 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
cli | +0.566 |
�� | +0.558 |
ette | +0.501 |
� | +0.498 |
� | +0.485 |
Neg logit contributions | |
helium | -0.537 |
apo | -0.524 |
Amen | -0.514 |
Cassidy | -0.510 |
Hert | -0.492 |
Token | might |
Token ID | 1244 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
cli | +1.196 |
�� | +1.178 |
� | +1.068 |
ette | +1.064 |
� | +1.038 |
Neg logit contributions | |
helium | -1.153 |
apo | -1.132 |
Amen | -1.098 |
Cassidy | -1.096 |
Hert | -1.055 |
Token | as |
Token ID | 355 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
cli | +0.328 |
�� | +0.328 |
ette | +0.294 |
� | +0.292 |
� | +0.283 |
Neg logit contributions | |
helium | -0.297 |
apo | -0.289 |
Amen | -0.281 |
Cassidy | -0.279 |
Hert | -0.270 |
Token | well |
Token ID | 880 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
�� | +0.672 |
cli | +0.669 |
ette | +0.593 |
� | +0.585 |
ngth | +0.568 |
Neg logit contributions | |
helium | -0.748 |
apo | -0.730 |
Amen | -0.717 |
Cassidy | -0.714 |
Hert | -0.687 |
Token | make |
Token ID | 787 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
cli | +2.519 |
�� | +2.451 |
� | +2.284 |
ette | +2.252 |
� | +2.231 |
Neg logit contributions | |
helium | -2.497 |
apo | -2.489 |
Cassidy | -2.403 |
Amen | -2.393 |
Hert | -2.297 |
Token | them |
Token ID | 606 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
cli | +0.078 |
�� | +0.077 |
ette | +0.070 |
� | +0.069 |
� | +0.068 |
Neg logit contributions | |
helium | -0.069 |
apo | -0.067 |
Amen | -0.065 |
Cassidy | -0.065 |
Hert | -0.063 |
Token | useful |
Token ID | 4465 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
cli | +0.414 |
�� | +0.408 |
ette | +0.371 |
� | +0.368 |
� | +0.360 |
Neg logit contributions | |
helium | -0.345 |
apo | -0.335 |
Amen | -0.328 |
Cassidy | -0.326 |
Hert | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
helium | +0.069 |
apo | +0.067 |
Amen | +0.065 |
Cassidy | +0.065 |
Hert | +0.063 |
Neg logit contributions | |
cli | -0.070 |
�� | -0.069 |
ette | -0.062 |
� | -0.061 |
� | -0.060 |
Token | A |
Token ID | 317 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
cli | +0.060 |
�� | +0.060 |
ette | +0.054 |
� | +0.053 |
� | +0.052 |
Neg logit contributions | |
helium | -0.039 |
apo | -0.037 |
Amen | -0.037 |
Cassidy | -0.037 |
Hert | -0.035 |
Token | data |
Token ID | 7890 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
cli | +0.858 |
�� | +0.844 |
� | +0.711 |
ette | +0.694 |
� | +0.673 |
Neg logit contributions | |
helium | -1.997 |
apo | -1.973 |
Amen | -1.927 |
Cassidy | -1.925 |
Hert | -1.871 |
Token | _ |
Token ID | 62 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
cli | +0.184 |
�� | +0.182 |
� | +0.159 |
ette | +0.157 |
� | +0.154 |
Neg logit contributions | |
helium | -0.275 |
apo | -0.270 |
Cassidy | -0.265 |
Amen | -0.262 |
Hert | -0.255 |
Token | full |
Token ID | 12853 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
cli | +0.380 |
�� | +0.378 |
� | +0.345 |
ette | +0.341 |
� | +0.335 |
Neg logit contributions | |
helium | -0.329 |
apo | -0.327 |
Amen | -0.312 |
Cassidy | -0.311 |
Hert | -0.298 |
Token | v |
Token ID | 410 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
helium | +0.058 |
apo | +0.057 |
Cassidy | +0.055 |
Amen | +0.055 |
Hert | +0.053 |
Neg logit contributions | |
cli | -0.055 |
�� | -0.054 |
� | -0.048 |
ette | -0.048 |
� | -0.047 |
Token | ) |
Token ID | 8 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
cli | +1.037 |
�� | +1.024 |
� | +0.924 |
ette | +0.914 |
� | +0.898 |
Neg logit contributions | |
helium | -1.103 |
apo | -1.085 |
Amen | -1.052 |
Cassidy | -1.051 |
Hert | -1.012 |
Token | { |
Token ID | 1391 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
cli | +1.029 |
�� | +1.010 |
� | +0.900 |
ette | +0.898 |
� | +0.874 |
Neg logit contributions | |
helium | -1.275 |
apo | -1.253 |
Amen | -1.222 |
Cassidy | -1.218 |
Hert | -1.178 |
Token | v |
Token ID | 410 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
cli | +2.801 |
�� | +2.736 |
� | +2.509 |
ette | +2.485 |
� | +2.440 |
Neg logit contributions | |
helium | -2.951 |
apo | -2.912 |
Amen | -2.830 |
Cassidy | -2.825 |
Hert | -2.715 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
cli | +0.314 |
�� | +0.311 |
� | +0.276 |
ette | +0.276 |
� | +0.268 |
Neg logit contributions | |
helium | -0.345 |
apo | -0.339 |
Amen | -0.329 |
Cassidy | -0.328 |
Hert | -0.318 |
Token | ver |
Token ID | 332 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
cli | +1.351 |
�� | +1.331 |
� | +1.214 |
ette | +1.212 |
� | +1.187 |
Neg logit contributions | |
helium | -1.091 |
apo | -1.072 |
Amen | -1.032 |
Cassidy | -1.030 |
Hert | -0.984 |
Token | tex |
Token ID | 16886 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
cli | +0.975 |
�� | +0.960 |
� | +0.855 |
ette | +0.850 |
� | +0.829 |
Neg logit contributions | |
helium | -1.242 |
apo | -1.224 |
Amen | -1.191 |
Cassidy | -1.187 |
Hert | -1.148 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cli | +0.248 |
�� | +0.246 |
� | +0.220 |
ette | +0.218 |
� | +0.215 |
Neg logit contributions | |
helium | -0.244 |
apo | -0.240 |
Amen | -0.232 |
Cassidy | -0.232 |
Hert | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
�� | +0.352 |
cli | +0.350 |
ette | +0.305 |
� | +0.304 |
� | +0.296 |
Neg logit contributions | |
helium | -0.368 |
apo | -0.363 |
Amen | -0.353 |
Cassidy | -0.350 |
Hert | -0.339 |
Token | Thus |
Token ID | 6660 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
�� | +0.248 |
cli | +0.248 |
ette | +0.220 |
� | +0.218 |
� | +0.214 |
Neg logit contributions | |
helium | -0.236 |
apo | -0.230 |
Amen | -0.228 |
Cassidy | -0.225 |
Hert | -0.218 |
Token | to |
Token ID | 284 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
�� | +0.276 |
cli | +0.276 |
ette | +0.242 |
� | +0.241 |
� | +0.237 |
Neg logit contributions | |
helium | -0.286 |
apo | -0.281 |
Amen | -0.273 |
Cassidy | -0.272 |
Hert | -0.263 |
Token | include |
Token ID | 2291 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
cli | +0.365 |
�� | +0.365 |
ette | +0.326 |
� | +0.325 |
� | +0.316 |
Neg logit contributions | |
helium | -0.312 |
apo | -0.305 |
Amen | -0.295 |
Cassidy | -0.294 |
Hert | -0.283 |
Token | "\ |
Token ID | 37082 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
cli | +0.901 |
�� | +0.889 |
� | +0.798 |
ette | +0.797 |
� | +0.779 |
Neg logit contributions | |
helium | -0.895 |
apo | -0.876 |
Amen | -0.854 |
Cassidy | -0.852 |
Hert | -0.822 |
Token | :" |
Token ID | 11097 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
cli | +1.898 |
�� | +1.849 |
� | +1.656 |
ette | +1.648 |
� | +1.608 |
Neg logit contributions | |
helium | -2.587 |
apo | -2.544 |
Amen | -2.485 |
Cassidy | -2.483 |
Hert | -2.396 |
Token | you |
Token ID | 345 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
cli | +2.840 |
�� | +2.774 |
� | +2.551 |
ette | +2.544 |
� | +2.488 |
Neg logit contributions | |
helium | -2.684 |
apo | -2.639 |
Amen | -2.561 |
Cassidy | -2.556 |
Hert | -2.453 |
Token | have |
Token ID | 423 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
cli | +0.893 |
�� | +0.888 |
� | +0.787 |
ette | +0.786 |
� | +0.762 |
Neg logit contributions | |
helium | -0.940 |
apo | -0.924 |
Amen | -0.895 |
Cassidy | -0.894 |
Hert | -0.863 |
Token | to |
Token ID | 284 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
cli | +0.438 |
�� | +0.436 |
ette | +0.383 |
� | +0.382 |
� | +0.372 |
Neg logit contributions | |
helium | -0.519 |
apo | -0.510 |
Cassidy | -0.498 |
Amen | -0.496 |
Hert | -0.480 |
Token | specify |
Token ID | 11986 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
cli | +0.380 |
�� | +0.376 |
� | +0.339 |
ette | +0.339 |
� | +0.331 |
Neg logit contributions | |
helium | -0.310 |
apo | -0.303 |
Amen | -0.294 |
Cassidy | -0.292 |
Hert | -0.280 |
Token | " |
Token ID | 366 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
helium | +0.061 |
apo | +0.060 |
Amen | +0.058 |
Cassidy | +0.058 |
Hert | +0.056 |
Neg logit contributions | |
cli | -0.062 |
�� | -0.062 |
ette | -0.055 |
� | -0.055 |
� | -0.053 |
Token | which |
Token ID | 543 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
helium | +0.189 |
apo | +0.184 |
Cassidy | +0.179 |
Amen | +0.179 |
Hert | +0.173 |
Neg logit contributions | |
cli | -0.219 |
�� | -0.216 |
� | -0.193 |
ette | -0.192 |
� | -0.188 |
Token | show |
Token ID | 905 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
cli | +0.209 |
�� | +0.207 |
ette | +0.184 |
� | +0.183 |
� | +0.179 |
Neg logit contributions | |
helium | -0.201 |
apo | -0.195 |
Cassidy | -0.191 |
Amen | -0.190 |
Hert | -0.184 |
Token | any |
Token ID | 597 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
helium | +0.079 |
apo | +0.076 |
Amen | +0.075 |
Cassidy | +0.075 |
Hert | +0.072 |
Neg logit contributions | |
cli | -0.091 |
�� | -0.090 |
ette | -0.081 |
� | -0.081 |
� | -0.079 |
Token | noticeable |
Token ID | 19787 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
cli | +0.394 |
�� | +0.387 |
� | +0.353 |
ette | +0.353 |
� | +0.346 |
Neg logit contributions | |
helium | -0.304 |
apo | -0.295 |
Amen | -0.287 |
Cassidy | -0.287 |
Hert | -0.275 |
Token | over |
Token ID | 625 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
cli | +0.205 |
�� | +0.201 |
� | +0.183 |
ette | +0.183 |
� | +0.179 |
Neg logit contributions | |
helium | -0.171 |
apo | -0.166 |
Amen | -0.162 |
Cassidy | -0.162 |
Hert | -0.155 |
Token | shoot |
Token ID | 30408 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
cli | +0.164 |
�� | +0.161 |
� | +0.146 |
ette | +0.145 |
� | +0.142 |
Neg logit contributions | |
helium | -0.170 |
apo | -0.167 |
Amen | -0.162 |
Cassidy | -0.162 |
Hert | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
cli | +2.234 |
�� | +2.181 |
� | +2.007 |
ette | +1.992 |
� | +1.950 |
Neg logit contributions | |
helium | -2.386 |
apo | -2.354 |
Amen | -2.278 |
Cassidy | -2.278 |
Hert | -2.189 |
Token | and |
Token ID | 290 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
cli | +0.452 |
�� | +0.447 |
� | +0.398 |
ette | +0.397 |
� | +0.385 |
Neg logit contributions | |
helium | -0.511 |
apo | -0.498 |
Amen | -0.488 |
Cassidy | -0.487 |
Hert | -0.470 |
Token | overall |
Token ID | 4045 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
cli | +0.031 |
�� | +0.031 |
ette | +0.028 |
� | +0.027 |
� | +0.027 |
Neg logit contributions | |
helium | -0.028 |
apo | -0.027 |
Cassidy | -0.026 |
Amen | -0.026 |
Hert | -0.025 |
Token | we |
Token ID | 356 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
helium | +1.280 |
apo | +1.221 |
Cassidy | +1.217 |
Amen | +1.213 |
Hert | +1.174 |
Neg logit contributions | |
cli | -1.337 |
�� | -1.320 |
ette | -1.186 |
� | -1.169 |
� | -1.144 |
Token | would |
Token ID | 561 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
cli | +0.643 |
�� | +0.634 |
� | +0.573 |
ette | +0.571 |
� | +0.555 |
Neg logit contributions | |
helium | -0.638 |
apo | -0.624 |
Amen | -0.607 |
Cassidy | -0.607 |
Hert | -0.584 |