Token | thought |
Token ID | 1807 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
puts | +0.002 |
endant | +0.002 |
picks | +0.001 |
dumps | +0.001 |
finds | +0.001 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
lot | -0.002 |
Wendy | -0.002 |
Bet | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Bet | +0.005 |
forward | +0.005 |
mate | +0.005 |
lot | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.007 |
pasta | -0.006 |
ice | -0.006 |
picks | -0.006 |
Token | looked |
Token ID | 3114 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.004 |
dumps | -0.004 |
picks | -0.004 |
Token | like |
Token ID | 588 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
endant | +0.017 |
puts | +0.017 |
pasta | +0.016 |
dumps | +0.016 |
picks | +0.016 |
Neg logit contributions | |
mate | -0.016 |
Bet | -0.016 |
Monkey | -0.016 |
Wendy | -0.016 |
June | -0.015 |
Token | ac |
Token ID | 936 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
pasta | +0.011 |
ice | +0.010 |
puts | +0.010 |
endant | +0.009 |
necklace | +0.009 |
Neg logit contributions | |
forward | -0.014 |
Bet | -0.013 |
mate | -0.013 |
stretched | -0.013 |
lot | -0.012 |
Token | rob |
Token ID | 22609 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
forward | +0.017 |
lot | +0.017 |
mate | +0.016 |
Wendy | +0.016 |
often | +0.016 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.006 |
pasta | -0.006 |
ice | -0.006 |
weighs | -0.006 |
Token | ats |
Token ID | 1381 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
forward | +0.089 |
lot | +0.088 |
mate | +0.085 |
Wendy | +0.085 |
Monkey | +0.082 |
Neg logit contributions | |
endant | -0.105 |
puts | -0.096 |
pasta | -0.093 |
dumps | -0.091 |
picks | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Bet | +0.020 |
lot | +0.020 |
mate | +0.020 |
known | +0.020 |
June | +0.019 |
Neg logit contributions | |
ice | -0.015 |
puts | -0.014 |
pasta | -0.014 |
endant | -0.013 |
frost | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
mate | +0.000 |
forward | +0.000 |
lot | +0.000 |
known | +0.000 |
Wendy | +0.000 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
picks | -0.001 |
dumps | -0.001 |
pasta | -0.001 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
forward | +0.005 |
lot | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
often | +0.005 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.004 |
dumps | -0.004 |
picks | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ice | +0.001 |
puts | +0.001 |
pasta | +0.001 |
picks | +0.001 |
frost | +0.001 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.001 |
stretched | -0.001 |
Bet | -0.001 |
lot | -0.001 |
Token | clown |
Token ID | 25573 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
endant | +0.011 |
ice | +0.011 |
pasta | +0.010 |
puts | +0.010 |
frost | +0.010 |
Neg logit contributions | |
mate | -0.011 |
forward | -0.011 |
lot | -0.010 |
Bet | -0.010 |
Monkey | -0.010 |
Token | s |
Token ID | 82 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
lot | +0.017 |
mate | +0.017 |
forward | +0.017 |
Wendy | +0.016 |
Bet | +0.016 |
Neg logit contributions | |
endant | -0.025 |
puts | -0.023 |
ice | -0.023 |
pasta | -0.023 |
picks | -0.023 |
Token | juggling |
Token ID | 48097 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
mate | +0.001 |
forward | +0.001 |
Bet | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
Neg logit contributions | |
endant | -0.002 |
ice | -0.002 |
pasta | -0.002 |
puts | -0.002 |
view | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Wendy | +0.010 |
mate | +0.010 |
forward | +0.010 |
Bet | +0.009 |
June | +0.009 |
Neg logit contributions | |
ice | -0.008 |
pasta | -0.008 |
endant | -0.008 |
puts | -0.007 |
shirts | -0.007 |
Token | ac |
Token ID | 936 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
puts | +0.009 |
ice | +0.008 |
pasta | +0.008 |
picks | +0.008 |
sprink | +0.007 |
Neg logit contributions | |
forward | -0.011 |
mate | -0.011 |
lot | -0.010 |
Bet | -0.010 |
Wendy | -0.009 |
Token | rob |
Token ID | 22609 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
ice | +0.000 |
pasta | +0.000 |
view | +0.000 |
Neg logit contributions | |
forward | -0.000 |
lot | -0.000 |
mate | -0.000 |
Wendy | -0.000 |
often | -0.000 |
Token | ats |
Token ID | 1381 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
forward | +0.075 |
lot | +0.075 |
mate | +0.072 |
Wendy | +0.071 |
often | +0.069 |
Neg logit contributions | |
endant | -0.099 |
puts | -0.091 |
pasta | -0.088 |
dumps | -0.086 |
picks | -0.086 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Bet | +0.010 |
June | +0.010 |
mate | +0.010 |
Wendy | +0.010 |
lot | +0.009 |
Neg logit contributions | |
ice | -0.008 |
frost | -0.007 |
puts | -0.007 |
pasta | -0.007 |
picks | -0.007 |
Token | flips |
Token ID | 45971 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ice | +0.006 |
puts | +0.006 |
pasta | +0.005 |
picks | +0.005 |
sandwich | +0.005 |
Neg logit contributions | |
Bet | -0.007 |
mate | -0.007 |
forward | -0.007 |
June | -0.007 |
Wendy | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Bet | +0.010 |
mate | +0.010 |
Wendy | +0.010 |
known | +0.010 |
June | +0.010 |
Neg logit contributions | |
ice | -0.007 |
pasta | -0.007 |
puts | -0.007 |
shirts | -0.006 |
view | -0.006 |
Token | But |
Token ID | 887 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
picks | +0.003 |
pasta | +0.003 |
ice | +0.003 |
Neg logit contributions | |
mate | -0.004 |
forward | -0.004 |
lot | -0.003 |
stretched | -0.003 |
forever | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
forward | +0.006 |
mate | +0.006 |
lot | +0.006 |
Wendy | +0.006 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.004 |
picks | -0.004 |
pasta | -0.004 |
ice | -0.004 |
Token | clown |
Token ID | 25573 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
endant | +0.017 |
puts | +0.016 |
pasta | +0.016 |
ice | +0.016 |
picks | +0.015 |
Neg logit contributions | |
forward | -0.015 |
mate | -0.015 |
lot | -0.015 |
Wendy | -0.014 |
often | -0.014 |
Token | s |
Token ID | 82 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
mate | +0.019 |
lot | +0.019 |
forward | +0.018 |
Wendy | +0.018 |
known | +0.018 |
Neg logit contributions | |
endant | -0.027 |
puts | -0.026 |
ice | -0.026 |
pasta | -0.026 |
picks | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
pasta | +0.006 |
ice | +0.006 |
picks | +0.006 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.006 |
mate | -0.006 |
Wendy | -0.006 |
Monkey | -0.005 |
Token | ac |
Token ID | 936 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
puts | +0.025 |
endant | +0.025 |
pasta | +0.024 |
ice | +0.024 |
picks | +0.024 |
Neg logit contributions | |
forward | -0.033 |
mate | -0.032 |
Wendy | -0.030 |
lot | -0.030 |
Bet | -0.030 |
Token | rob |
Token ID | 22609 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.005 |
mate | -0.005 |
Wendy | -0.005 |
often | -0.005 |
Token | ats |
Token ID | 1381 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
forward | +0.078 |
lot | +0.076 |
mate | +0.075 |
Wendy | +0.074 |
Monkey | +0.072 |
Neg logit contributions | |
endant | -0.096 |
puts | -0.088 |
pasta | -0.085 |
picks | -0.083 |
dumps | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
mate | +0.009 |
June | +0.009 |
lot | +0.009 |
Bet | +0.009 |
known | +0.009 |
Neg logit contributions | |
ice | -0.006 |
puts | -0.006 |
picks | -0.006 |
frost | -0.005 |
pasta | -0.005 |
Token | lions |
Token ID | 31420 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
endant | +0.034 |
puts | +0.032 |
pasta | +0.031 |
ice | +0.030 |
picks | +0.030 |
Neg logit contributions | |
forward | -0.046 |
mate | -0.045 |
lot | -0.043 |
Wendy | -0.043 |
often | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
forward | +0.034 |
mate | +0.034 |
Wendy | +0.034 |
lot | +0.034 |
Bet | +0.032 |
Neg logit contributions | |
endant | -0.038 |
puts | -0.037 |
ice | -0.036 |
pasta | -0.036 |
picks | -0.035 |
Token | elephants |
Token ID | 25368 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
endant | +0.024 |
puts | +0.022 |
pasta | +0.022 |
ice | +0.022 |
picks | +0.021 |
Neg logit contributions | |
forward | -0.029 |
mate | -0.029 |
Wendy | -0.028 |
lot | -0.027 |
often | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
lot | +0.016 |
forward | +0.016 |
mate | +0.015 |
Wendy | +0.015 |
Monkey | +0.015 |
Neg logit contributions | |
endant | -0.029 |
puts | -0.027 |
pasta | -0.027 |
ice | -0.027 |
picks | -0.026 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
lot | +0.028 |
forward | +0.025 |
often | +0.023 |
Wendy | +0.022 |
known | +0.021 |
Neg logit contributions | |
endant | -0.042 |
dumps | -0.036 |
view | -0.036 |
inner | -0.036 |
ode | -0.035 |
Token | watching |
Token ID | 4964 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.005 |
ice | +0.005 |
dumps | +0.005 |
Neg logit contributions | |
forward | -0.003 |
lot | -0.003 |
mate | -0.003 |
Wendy | -0.003 |
Monkey | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
pasta | +0.005 |
ice | +0.005 |
puts | +0.005 |
shirts | +0.005 |
sandwich | +0.005 |
Neg logit contributions | |
known | -0.006 |
Bet | -0.005 |
mate | -0.005 |
stretched | -0.005 |
forward | -0.005 |
Token | ac |
Token ID | 936 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
lot | +0.006 |
forward | +0.006 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
dumps | -0.005 |
pasta | -0.005 |
view | -0.004 |
Token | rob |
Token ID | 22609 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.003 |
ice | +0.003 |
view | +0.003 |
Neg logit contributions | |
forward | -0.009 |
lot | -0.009 |
Wendy | -0.009 |
mate | -0.009 |
often | -0.008 |
Token | ats |
Token ID | 1381 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
forward | +0.082 |
Wendy | +0.081 |
lot | +0.081 |
mate | +0.080 |
Monkey | +0.077 |
Neg logit contributions | |
endant | -0.088 |
puts | -0.080 |
pasta | -0.080 |
ice | -0.077 |
view | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Bet | +0.014 |
Wendy | +0.014 |
lot | +0.014 |
June | +0.014 |
Da | +0.014 |
Neg logit contributions | |
ice | -0.013 |
endant | -0.013 |
puts | -0.013 |
view | -0.013 |
pasta | -0.013 |
Token | clown |
Token ID | 25573 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
endant | +0.016 |
puts | +0.016 |
ice | +0.015 |
pasta | +0.015 |
picks | +0.014 |
Neg logit contributions | |
forward | -0.018 |
mate | -0.017 |
lot | -0.017 |
Wendy | -0.016 |
Bet | -0.016 |
Token | s |
Token ID | 82 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
lot | +0.009 |
Bet | +0.009 |
Wendy | +0.009 |
mate | +0.009 |
forward | +0.009 |
Neg logit contributions | |
endant | -0.011 |
ice | -0.010 |
puts | -0.010 |
pasta | -0.010 |
sandwich | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
endant | +0.017 |
ice | +0.017 |
puts | +0.016 |
pasta | +0.016 |
view | +0.016 |
Neg logit contributions | |
Wendy | -0.015 |
mate | -0.015 |
Bet | -0.015 |
forward | -0.015 |
June | -0.014 |
Token | elephants |
Token ID | 25368 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
forward | +0.018 |
mate | +0.018 |
lot | +0.018 |
Wendy | +0.017 |
often | +0.017 |
Neg logit contributions | |
endant | -0.020 |
puts | -0.019 |
pasta | -0.019 |
ice | -0.018 |
picks | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
forward | +0.020 |
mate | +0.020 |
lot | +0.019 |
Wendy | +0.019 |
Bet | +0.018 |
Neg logit contributions | |
endant | -0.031 |
puts | -0.030 |
ice | -0.030 |
picks | -0.030 |
pasta | -0.029 |
Token | lions |
Token ID | 31420 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
lot | +0.003 |
forward | +0.003 |
Wendy | +0.003 |
Monkey | +0.002 |
mate | +0.002 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.003 |
view | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
forward | +0.031 |
mate | +0.029 |
lot | +0.029 |
known | +0.028 |
Wendy | +0.028 |
Neg logit contributions | |
endant | -0.043 |
puts | -0.043 |
ice | -0.043 |
picks | -0.042 |
pasta | -0.041 |
Token | ac |
Token ID | 936 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
endant | +0.021 |
puts | +0.019 |
pasta | +0.018 |
ice | +0.018 |
dumps | +0.018 |
Neg logit contributions | |
forward | -0.022 |
lot | -0.021 |
mate | -0.021 |
Wendy | -0.021 |
often | -0.020 |
Token | rob |
Token ID | 22609 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
pasta | +0.005 |
dumps | +0.005 |
picks | +0.005 |
Neg logit contributions | |
forward | -0.011 |
lot | -0.011 |
mate | -0.011 |
Wendy | -0.011 |
often | -0.010 |
Token | ats |
Token ID | 1381 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
forward | +0.075 |
lot | +0.073 |
mate | +0.072 |
Wendy | +0.071 |
Monkey | +0.069 |
Neg logit contributions | |
endant | -0.093 |
puts | -0.086 |
pasta | -0.083 |
picks | -0.081 |
dumps | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
known | +0.006 |
lot | +0.006 |
rarely | +0.006 |
mate | +0.006 |
forward | +0.006 |
Neg logit contributions | |
ice | -0.005 |
puts | -0.005 |
picks | -0.005 |
frost | -0.005 |
pasta | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
puts | +0.000 |
endant | +0.000 |
dumps | +0.000 |
picks | +0.000 |
pasta | +0.000 |
Neg logit contributions | |
mate | -0.000 |
forward | -0.000 |
lot | -0.000 |
Bet | -0.000 |
often | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | +9.89e-03 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
picks | +0.005 |
dumps | +0.005 |
ice | +0.005 |
Neg logit contributions | |
forward | -0.010 |
mate | -0.009 |
lot | -0.009 |
Wendy | -0.009 |
Bet | -0.009 |
Token | amazed |
Token ID | 24562 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
mate | +0.000 |
forward | +0.000 |
lot | +0.000 |
Wendy | +0.000 |
Bet | +0.000 |
Neg logit contributions | |
endant | -0.000 |
ice | -0.000 |
puts | -0.000 |
pasta | -0.000 |
picks | -0.000 |
Token | velvet |
Token ID | 47750 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
forward | +0.006 |
mate | +0.006 |
lot | +0.006 |
Wendy | +0.006 |
often | +0.005 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
ice | -0.005 |
dumps | -0.004 |
Token | path |
Token ID | 3108 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
forward | +0.021 |
known | +0.020 |
Wendy | +0.019 |
lot | +0.019 |
often | +0.019 |
Neg logit contributions | |
endant | -0.011 |
pasta | -0.009 |
ice | -0.009 |
sandwich | -0.009 |
necklace | -0.009 |
Token | covered |
Token ID | 5017 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
dumps | +0.002 |
picks | +0.002 |
Neg logit contributions | |
lot | -0.002 |
forward | -0.002 |
Wendy | -0.002 |
mate | -0.002 |
Monkey | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
lot | +0.008 |
Monkey | +0.008 |
forward | +0.007 |
Wendy | +0.007 |
mate | +0.007 |
Neg logit contributions | |
endant | -0.006 |
pasta | -0.006 |
ice | -0.006 |
puts | -0.006 |
view | -0.005 |
Token | gl |
Token ID | 1278 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
forward | +0.004 |
mate | +0.004 |
Wendy | +0.003 |
Monkey | +0.003 |
lot | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
ice | -0.003 |
pasta | -0.003 |
picks | -0.003 |
Token | ist |
Token ID | 396 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
pasta | +0.000 |
dumps | +0.000 |
ice | +0.000 |
Neg logit contributions | |
forward | -0.000 |
lot | -0.000 |
mate | -0.000 |
often | -0.000 |
Wendy | -0.000 |
Token | ening |
Token ID | 3101 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
mate | +0.087 |
Monkey | +0.085 |
Bet | +0.084 |
Wendy | +0.084 |
known | +0.083 |
Neg logit contributions | |
endant | -0.065 |
puts | -0.063 |
picks | -0.060 |
ice | -0.058 |
view | -0.057 |
Token | rain |
Token ID | 6290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
mate | +0.008 |
Wendy | +0.008 |
known | +0.008 |
Monkey | +0.008 |
forward | +0.008 |
Neg logit contributions | |
ice | -0.007 |
pasta | -0.007 |
endant | -0.007 |
puts | -0.006 |
frost | -0.006 |
Token | drops |
Token ID | 49253 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
lot | +0.002 |
mate | +0.002 |
forward | +0.002 |
Wendy | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
ice | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
mate | +0.017 |
Wendy | +0.017 |
Monkey | +0.017 |
lot | +0.017 |
Bet | +0.017 |
Neg logit contributions | |
endant | -0.018 |
ice | -0.017 |
puts | -0.017 |
pasta | -0.017 |
frost | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.001 |
picks | +0.001 |
pasta | +0.001 |
ice | +0.001 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
lot | -0.001 |
known | -0.001 |
often | -0.001 |
Token | Inside |
Token ID | 14384 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
puts | +0.007 |
endant | +0.007 |
pasta | +0.007 |
ice | +0.007 |
picks | +0.007 |
Neg logit contributions | |
mate | -0.008 |
forward | -0.008 |
lot | -0.007 |
known | -0.007 |
often | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
pasta | +0.001 |
ice | +0.001 |
puts | +0.001 |
endant | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
mate | -0.001 |
forward | -0.001 |
Bet | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
mate | +0.021 |
forward | +0.021 |
lot | +0.020 |
Wendy | +0.019 |
Bet | +0.019 |
Neg logit contributions | |
pasta | -0.025 |
endant | -0.025 |
ice | -0.025 |
puts | -0.024 |
frost | -0.023 |
Token | kinds |
Token ID | 6982 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
mate | +0.011 |
forward | +0.011 |
lot | +0.011 |
Wendy | +0.010 |
Monkey | +0.010 |
Neg logit contributions | |
endant | -0.013 |
puts | -0.013 |
pasta | -0.013 |
ice | -0.012 |
view | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
mate | +0.000 |
forward | +0.000 |
lot | +0.000 |
Bet | +0.000 |
Wendy | +0.000 |
Neg logit contributions | |
endant | -0.001 |
pasta | -0.001 |
ice | -0.001 |
puts | -0.001 |
frost | -0.001 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
forward | +0.050 |
mate | +0.049 |
lot | +0.049 |
Wendy | +0.048 |
Monkey | +0.047 |
Neg logit contributions | |
endant | -0.042 |
puts | -0.039 |
pasta | -0.038 |
ice | -0.037 |
picks | -0.036 |
Token | animals |
Token ID | 4695 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
forward | +0.086 |
mate | +0.079 |
known | +0.075 |
stretched | +0.074 |
lot | +0.074 |
Neg logit contributions | |
ice | -0.068 |
pasta | -0.067 |
endant | -0.066 |
puts | -0.066 |
picks | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
mate | +0.023 |
lot | +0.022 |
forward | +0.022 |
Bet | +0.021 |
Wendy | +0.021 |
Neg logit contributions | |
endant | -0.023 |
puts | -0.022 |
pasta | -0.022 |
ice | -0.022 |
picks | -0.021 |
Token | games |
Token ID | 1830 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
mate | +0.001 |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
Bet | +0.001 |
Neg logit contributions | |
pasta | -0.001 |
ice | -0.001 |
puts | -0.001 |
endant | -0.001 |
frost | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.007 |
pasta | +0.006 |
ice | +0.006 |
picks | +0.006 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.006 |
mate | -0.006 |
Wendy | -0.006 |
Bet | -0.005 |
Token | humor |
Token ID | 14733 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
mate | +0.003 |
forward | +0.003 |
Wendy | +0.003 |
lot | +0.003 |
Bet | +0.003 |
Neg logit contributions | |
pasta | -0.002 |
puts | -0.002 |
ice | -0.002 |
endant | -0.002 |
frost | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
endant | +0.017 |
puts | +0.016 |
pasta | +0.015 |
ice | +0.015 |
dumps | +0.015 |
Neg logit contributions | |
forward | -0.014 |
mate | -0.013 |
lot | -0.013 |
Wendy | -0.013 |
Monkey | -0.012 |
Token | long |
Token ID | 890 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
endant | +0.009 |
ice | +0.009 |
puts | +0.008 |
sandwich | +0.008 |
pasta | +0.008 |
Neg logit contributions | |
forward | -0.008 |
mate | -0.008 |
Wendy | -0.007 |
Monkey | -0.007 |
Bet | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
endant | +0.020 |
pasta | +0.018 |
puts | +0.018 |
view | +0.017 |
dumps | +0.017 |
Neg logit contributions | |
lot | -0.021 |
forward | -0.019 |
mate | -0.019 |
Wendy | -0.019 |
often | -0.019 |
Token | z |
Token ID | 1976 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
lot | +0.004 |
forward | +0.004 |
Wendy | +0.004 |
often | +0.004 |
mate | +0.004 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.003 |
view | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
Token | ig |
Token ID | 328 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
often | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.001 |
dumps | -0.001 |
picks | -0.001 |
Token | zag |
Token ID | 50183 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
forward | +0.029 |
lot | +0.029 |
Wendy | +0.028 |
mate | +0.028 |
Monkey | +0.026 |
Neg logit contributions | |
endant | -0.046 |
puts | -0.043 |
pasta | -0.041 |
dumps | -0.041 |
picks | -0.041 |
Token | tail |
Token ID | 7894 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
forward | +0.077 |
Wendy | +0.074 |
mate | +0.074 |
lot | +0.073 |
Monkey | +0.072 |
Neg logit contributions | |
endant | -0.070 |
puts | -0.064 |
pasta | -0.061 |
dumps | -0.060 |
ice | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
forward | +0.029 |
mate | +0.029 |
Wendy | +0.029 |
lot | +0.029 |
known | +0.028 |
Neg logit contributions | |
endant | -0.027 |
ice | -0.025 |
puts | -0.024 |
picks | -0.024 |
pasta | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.008 |
dumps | +0.008 |
picks | +0.008 |
Neg logit contributions | |
forward | -0.007 |
lot | -0.007 |
mate | -0.006 |
Wendy | -0.006 |
often | -0.006 |
Token | opened |
Token ID | 4721 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
picks | +0.006 |
ice | +0.006 |
pasta | +0.006 |
Neg logit contributions | |
forward | -0.007 |
mate | -0.007 |
lot | -0.007 |
Wendy | -0.007 |
Monkey | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
mate | +0.024 |
forward | +0.024 |
lot | +0.023 |
Wendy | +0.022 |
Monkey | +0.022 |
Neg logit contributions | |
endant | -0.031 |
puts | -0.029 |
ice | -0.028 |
pasta | -0.028 |
picks | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
lot | +0.007 |
forward | +0.007 |
mate | +0.007 |
Wendy | +0.007 |
often | +0.006 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
pasta | -0.006 |
dumps | -0.006 |
picks | -0.006 |
Token | has |
Token ID | 468 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
lot | +0.000 |
forward | +0.000 |
mate | +0.000 |
Wendy | +0.000 |
often | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
dumps | -0.000 |
view | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
endant | +0.022 |
puts | +0.020 |
pasta | +0.019 |
dumps | +0.019 |
picks | +0.018 |
Neg logit contributions | |
lot | -0.024 |
forward | -0.023 |
mate | -0.022 |
Wendy | -0.022 |
often | -0.022 |
Token | z |
Token ID | 1976 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
endant | +0.011 |
ice | +0.010 |
pasta | +0.010 |
puts | +0.010 |
sandwich | +0.010 |
Neg logit contributions | |
forward | -0.015 |
Wendy | -0.015 |
mate | -0.014 |
Bet | -0.014 |
June | -0.014 |
Token | ig |
Token ID | 328 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
often | +0.004 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
pasta | -0.003 |
dumps | -0.003 |
picks | -0.003 |
Token | zag |
Token ID | 50183 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
forward | +0.028 |
lot | +0.028 |
mate | +0.027 |
Wendy | +0.026 |
often | +0.025 |
Neg logit contributions | |
endant | -0.058 |
puts | -0.054 |
pasta | -0.053 |
dumps | -0.052 |
picks | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
lot | +0.067 |
forward | +0.066 |
mate | +0.064 |
Wendy | +0.062 |
often | +0.062 |
Neg logit contributions | |
endant | -0.078 |
puts | -0.072 |
pasta | -0.069 |
dumps | -0.068 |
picks | -0.067 |
Token | What |
Token ID | 1867 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
lot | +0.001 |
forward | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
dumps | -0.001 |
picks | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
endant | +0.003 |
view | +0.003 |
dumps | +0.003 |
puts | +0.003 |
picks | +0.003 |
Neg logit contributions | |
lot | -0.004 |
forward | -0.004 |
mate | -0.004 |
often | -0.004 |
Monkey | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
endant | +0.010 |
view | +0.009 |
puts | +0.009 |
dumps | +0.009 |
pasta | +0.008 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.005 |
often | -0.005 |
Wendy | -0.005 |
mate | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
endant | +0.015 |
puts | +0.013 |
dumps | +0.013 |
view | +0.012 |
picks | +0.012 |
Neg logit contributions | |
forward | -0.019 |
lot | -0.019 |
mate | -0.018 |
often | -0.018 |
Wendy | -0.018 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
lot | +0.002 |
forward | +0.002 |
Wendy | +0.002 |
mate | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.003 |
view | -0.003 |
puts | -0.003 |
anniversary | -0.003 |
pasta | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Wendy | +0.005 |
lot | +0.005 |
mate | +0.005 |
Monkey | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
ice | -0.006 |
picks | -0.005 |
pasta | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
puts | +0.009 |
endant | +0.009 |
picks | +0.009 |
dumps | +0.009 |
ice | +0.009 |
Neg logit contributions | |
forward | -0.013 |
mate | -0.013 |
lot | -0.012 |
Wendy | -0.012 |
often | -0.012 |
Token | dog |
Token ID | 3290 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
view | +0.007 |
pasta | +0.007 |
dumps | +0.007 |
Neg logit contributions | |
lot | -0.008 |
forward | -0.008 |
Wendy | -0.007 |
mate | -0.007 |
Monkey | -0.007 |
Token | fet |
Token ID | 11351 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
lot | +0.011 |
forward | +0.011 |
mate | +0.011 |
Wendy | +0.011 |
Monkey | +0.010 |
Neg logit contributions | |
endant | -0.014 |
puts | -0.013 |
picks | -0.013 |
dumps | -0.013 |
pasta | -0.013 |
Token | ches |
Token ID | 2052 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Wendy | +0.017 |
forward | +0.016 |
Monkey | +0.016 |
Bet | +0.016 |
known | +0.016 |
Neg logit contributions | |
puts | -0.020 |
endant | -0.020 |
picks | -0.019 |
ws | -0.019 |
dumps | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
known | +0.073 |
Bet | +0.073 |
Monkey | +0.071 |
Wendy | +0.069 |
June | +0.069 |
Neg logit contributions | |
picks | -0.062 |
puts | -0.061 |
ice | -0.060 |
dumps | -0.058 |
ws | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
ice | +0.005 |
picks | +0.005 |
dumps | +0.004 |
Neg logit contributions | |
Bet | -0.006 |
known | -0.006 |
Wendy | -0.006 |
June | -0.005 |
Ally | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.009 |
dumps | +0.008 |
picks | +0.008 |
ice | +0.008 |
Neg logit contributions | |
mate | -0.009 |
forward | -0.009 |
lot | -0.008 |
Wendy | -0.008 |
often | -0.008 |
Token | have |
Token ID | 423 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
picks | +0.000 |
dumps | +0.000 |
ice | +0.000 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
Wendy | -0.001 |
lot | -0.001 |
Bet | -0.001 |
Token | fun |
Token ID | 1257 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
endant | +0.019 |
puts | +0.018 |
pasta | +0.017 |
dumps | +0.017 |
picks | +0.016 |
Neg logit contributions | |
forward | -0.020 |
lot | -0.020 |
mate | -0.019 |
Wendy | -0.019 |
often | -0.019 |
Token | clown |
Token ID | 25573 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
lot | +0.004 |
forward | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
dumps | -0.003 |
pasta | -0.003 |
picks | -0.003 |
Token | s |
Token ID | 82 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.005 |
Wendy | +0.005 |
often | +0.005 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
pasta | -0.006 |
dumps | -0.006 |
picks | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.004 |
pasta | +0.004 |
dumps | +0.004 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.004 |
lot | -0.004 |
mate | -0.003 |
Wendy | -0.003 |
Monkey | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
puts | +0.019 |
endant | +0.019 |
ice | +0.018 |
picks | +0.018 |
pasta | +0.018 |
Neg logit contributions | |
forward | -0.020 |
mate | -0.020 |
lot | -0.019 |
Wendy | -0.018 |
Bet | -0.018 |
Token | ac |
Token ID | 936 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
pasta | +0.006 |
dumps | +0.006 |
picks | +0.006 |
Neg logit contributions | |
forward | -0.008 |
lot | -0.008 |
mate | -0.008 |
Wendy | -0.008 |
often | -0.008 |
Token | rob |
Token ID | 22609 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.012 |
pasta | +0.011 |
ice | +0.011 |
dumps | +0.011 |
Neg logit contributions | |
forward | -0.025 |
lot | -0.025 |
Wendy | -0.025 |
mate | -0.024 |
often | -0.024 |
Token | ats |
Token ID | 1381 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
forward | +0.070 |
Wendy | +0.070 |
lot | +0.068 |
mate | +0.068 |
Monkey | +0.067 |
Neg logit contributions | |
endant | -0.074 |
puts | -0.067 |
pasta | -0.065 |
view | -0.064 |
picks | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Wendy | +0.006 |
mate | +0.006 |
lot | +0.006 |
Bet | +0.006 |
forward | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
ice | -0.006 |
picks | -0.006 |
frost | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
endant | +0.030 |
puts | +0.030 |
ice | +0.028 |
pasta | +0.028 |
picks | +0.028 |
Neg logit contributions | |
forward | -0.027 |
mate | -0.026 |
lot | -0.025 |
Wendy | -0.025 |
often | -0.024 |
Token | lions |
Token ID | 31420 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
pasta | +0.006 |
dumps | +0.005 |
picks | +0.005 |
Neg logit contributions | |
forward | -0.008 |
lot | -0.008 |
mate | -0.008 |
Wendy | -0.008 |
often | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Wendy | +0.031 |
forward | +0.031 |
mate | +0.030 |
lot | +0.030 |
Bet | +0.029 |
Neg logit contributions | |
endant | -0.038 |
puts | -0.036 |
ice | -0.036 |
pasta | -0.035 |
picks | -0.035 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.009 |
mate | +0.009 |
stretched | +0.008 |
Bet | +0.008 |
Neg logit contributions | |
puts | -0.012 |
pasta | -0.012 |
ice | -0.011 |
picks | -0.011 |
endant | -0.011 |
Token | would |
Token ID | 561 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
forward | +0.000 |
Wendy | +0.000 |
mate | +0.000 |
lot | +0.000 |
Monkey | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
picks | -0.000 |
pasta | -0.000 |
ice | -0.000 |
Token | often |
Token ID | 1690 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
ice | +0.001 |
pasta | +0.001 |
picks | +0.001 |
Neg logit contributions | |
forward | -0.000 |
Wendy | -0.000 |
mate | -0.000 |
lot | -0.000 |
Bet | -0.000 |
Token | share |
Token ID | 2648 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.004 |
pasta | +0.004 |
dumps | +0.004 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.006 |
mate | -0.006 |
Wendy | -0.006 |
Monkey | -0.006 |
Token | av |
Token ID | 1196 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
forward | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
lot | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
endant | -0.007 |
pasta | -0.006 |
puts | -0.006 |
ice | -0.006 |
picks | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Wendy | +0.042 |
forward | +0.042 |
mate | +0.041 |
lot | +0.040 |
Misty | +0.037 |
Neg logit contributions | |
endant | -0.049 |
puts | -0.045 |
pasta | -0.043 |
picks | -0.042 |
ice | -0.042 |
Token | ados |
Token ID | 22484 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
lot | +0.092 |
forward | +0.092 |
Wendy | +0.089 |
mate | +0.087 |
often | +0.085 |
Neg logit contributions | |
endant | -0.053 |
puts | -0.047 |
picks | -0.044 |
pasta | -0.044 |
ice | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
endant | +0.002 |
pasta | +0.002 |
puts | +0.002 |
ice | +0.002 |
sandwich | +0.002 |
Neg logit contributions | |
Wendy | -0.001 |
forward | -0.001 |
lot | -0.001 |
mate | -0.001 |
stretched | -0.001 |
Token | other |
Token ID | 584 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
puts | +0.002 |
ice | +0.002 |
endant | +0.002 |
pasta | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.004 |
mate | -0.003 |
Wendy | -0.003 |
Bet | -0.003 |
lot | -0.003 |
Token | y |
Token ID | 331 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Wendy | +0.012 |
mate | +0.012 |
forward | +0.012 |
Bet | +0.011 |
Misty | +0.011 |
Neg logit contributions | |
pasta | -0.009 |
puts | -0.009 |
endant | -0.009 |
ice | -0.009 |
picks | -0.009 |
Token | ummy |
Token ID | 13513 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
ice | -0.003 |
Token | ball |
Token ID | 2613 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
lot | +0.006 |
forward | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
view | -0.004 |
pasta | -0.004 |
dumps | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
Wendy | +0.011 |
lot | +0.011 |
forward | +0.011 |
mate | +0.011 |
Monkey | +0.011 |
Neg logit contributions | |
endant | -0.014 |
puts | -0.013 |
ice | -0.013 |
pasta | -0.013 |
picks | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
endant | +0.018 |
puts | +0.017 |
pasta | +0.016 |
dumps | +0.016 |
picks | +0.016 |
Neg logit contributions | |
forward | -0.025 |
mate | -0.024 |
lot | -0.024 |
Wendy | -0.023 |
often | -0.023 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.007 |
dumps | +0.007 |
view | +0.007 |
Neg logit contributions | |
lot | -0.010 |
forward | -0.009 |
mate | -0.009 |
Wendy | -0.009 |
Monkey | -0.009 |
Token | fet |
Token ID | 11351 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.009 |
mate | +0.009 |
Wendy | +0.009 |
Bet | +0.008 |
Neg logit contributions | |
endant | -0.012 |
puts | -0.011 |
picks | -0.011 |
dumps | -0.011 |
pasta | -0.011 |
Token | ches |
Token ID | 2052 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
Wendy | +0.016 |
forward | +0.016 |
Bet | +0.016 |
Monkey | +0.016 |
known | +0.015 |
Neg logit contributions | |
puts | -0.019 |
endant | -0.019 |
picks | -0.018 |
ws | -0.018 |
dumps | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
known | +0.072 |
Bet | +0.072 |
Wendy | +0.069 |
Monkey | +0.069 |
June | +0.068 |
Neg logit contributions | |
picks | -0.062 |
puts | -0.062 |
ice | -0.061 |
dumps | -0.059 |
ws | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
ice | +0.006 |
picks | +0.006 |
dumps | +0.005 |
Neg logit contributions | |
Wendy | -0.007 |
known | -0.007 |
Bet | -0.007 |
June | -0.006 |
Ally | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
dumps | +0.006 |
pasta | +0.006 |
picks | +0.006 |
Neg logit contributions | |
forward | -0.006 |
mate | -0.006 |
lot | -0.005 |
Wendy | -0.005 |
often | -0.005 |
Token | hug |
Token ID | 16225 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
picks | +0.002 |
dumps | +0.002 |
pasta | +0.002 |
Neg logit contributions | |
forward | -0.004 |
mate | -0.003 |
lot | -0.003 |
Wendy | -0.003 |
Monkey | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
known | +0.015 |
stretched | +0.015 |
forward | +0.014 |
particularly | +0.014 |
mate | +0.013 |
Neg logit contributions | |
ice | -0.010 |
puts | -0.009 |
pasta | -0.008 |
picks | -0.008 |
bread | -0.008 |
Token | flying |
Token ID | 7348 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
forward | +0.008 |
lot | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
known | +0.007 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.009 |
pasta | -0.008 |
ice | -0.008 |
picks | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
mate | +0.023 |
Monkey | +0.023 |
known | +0.023 |
Wendy | +0.022 |
lot | +0.022 |
Neg logit contributions | |
endant | -0.014 |
ice | -0.013 |
picks | -0.013 |
dumps | -0.012 |
puts | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ice | +0.003 |
puts | +0.003 |
pasta | +0.003 |
endant | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.004 |
mate | -0.004 |
Monkey | -0.003 |
rarely | -0.003 |
often | -0.003 |
Token | z |
Token ID | 1976 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
forward | +0.007 |
mate | +0.007 |
known | +0.007 |
Wendy | +0.007 |
Monkey | +0.007 |
Neg logit contributions | |
endant | -0.005 |
ice | -0.005 |
pasta | -0.004 |
envelope | -0.004 |
sandwich | -0.004 |
Token | ig |
Token ID | 328 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
lot | +0.003 |
forward | +0.003 |
Wendy | +0.003 |
often | +0.003 |
mate | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.002 |
pasta | -0.002 |
dumps | -0.002 |
ice | -0.002 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
forward | +0.037 |
Wendy | +0.035 |
lot | +0.035 |
mate | +0.034 |
Monkey | +0.033 |
Neg logit contributions | |
endant | -0.041 |
view | -0.036 |
puts | -0.036 |
ice | -0.035 |
picks | -0.035 |
Token | way |
Token ID | 835 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
forward | +0.086 |
Wendy | +0.082 |
mate | +0.082 |
Monkey | +0.081 |
known | +0.078 |
Neg logit contributions | |
endant | -0.057 |
puts | -0.050 |
ice | -0.050 |
dumps | -0.049 |
pasta | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
mate | +0.020 |
Monkey | +0.020 |
lot | +0.019 |
Bet | +0.019 |
June | +0.018 |
Neg logit contributions | |
endant | -0.015 |
ice | -0.014 |
picks | -0.014 |
view | -0.014 |
puts | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
lot | +0.001 |
forward | +0.001 |
Wendy | +0.001 |
mate | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
view | -0.002 |
dumps | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
forward | +0.006 |
mate | +0.006 |
lot | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
puts | -0.004 |
endant | -0.004 |
picks | -0.004 |
ice | -0.003 |
dumps | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
mate | +0.006 |
forward | +0.006 |
Monkey | +0.005 |
lot | +0.005 |
often | +0.005 |
Neg logit contributions | |
endant | -0.006 |
ice | -0.006 |
puts | -0.005 |
pasta | -0.005 |
picks | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Bet | +0.011 |
Wendy | +0.011 |
June | +0.011 |
lot | +0.010 |
Monkey | +0.010 |
Neg logit contributions | |
endant | -0.010 |
ice | -0.010 |
pasta | -0.010 |
puts | -0.009 |
frost | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
puts | +0.006 |
picks | +0.006 |
endant | +0.006 |
dumps | +0.006 |
address | +0.006 |
Neg logit contributions | |
mate | -0.006 |
forward | -0.005 |
known | -0.005 |
forever | -0.005 |
Bet | -0.005 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.006 |
Wendy | +0.006 |
Monkey | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
pasta | -0.006 |
picks | -0.006 |
dumps | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
endant | +0.015 |
puts | +0.014 |
ice | +0.014 |
pasta | +0.014 |
frost | +0.014 |
Neg logit contributions | |
mate | -0.012 |
Bet | -0.012 |
often | -0.012 |
forward | -0.012 |
lot | -0.012 |
Token | few |
Token ID | 1178 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
lot | +0.005 |
forward | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
view | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
lot | +0.021 |
forward | +0.021 |
mate | +0.020 |
Wendy | +0.019 |
often | +0.019 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.014 |
view | -0.014 |
pasta | -0.014 |
dumps | -0.014 |
Token | animals |
Token ID | 4695 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
forward | +0.064 |
lot | +0.063 |
mate | +0.061 |
Wendy | +0.060 |
often | +0.059 |
Neg logit contributions | |
endant | -0.077 |
puts | -0.072 |
pasta | -0.070 |
ice | -0.068 |
picks | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
lot | +0.023 |
mate | +0.022 |
forward | +0.021 |
Wendy | +0.021 |
Bet | +0.021 |
Neg logit contributions | |
endant | -0.024 |
puts | -0.022 |
pasta | -0.022 |
ice | -0.021 |
picks | -0.021 |
Token | but |
Token ID | 475 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
forward | +0.007 |
mate | +0.007 |
lot | +0.007 |
Wendy | +0.007 |
Monkey | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
pasta | -0.005 |
ice | -0.005 |
picks | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
mate | +0.001 |
lot | +0.001 |
forward | +0.001 |
stretched | +0.001 |
Bet | +0.001 |
Neg logit contributions | |
ice | -0.001 |
puts | -0.001 |
endant | -0.001 |
pasta | -0.001 |
envelope | -0.001 |
Token | favorite |
Token ID | 4004 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
dumps | +0.003 |
picks | +0.003 |
Neg logit contributions | |
lot | -0.003 |
forward | -0.003 |
Wendy | -0.003 |
mate | -0.003 |
often | -0.003 |
Token | truck |
Token ID | 7779 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
lot | +0.012 |
forward | +0.012 |
mate | +0.011 |
Wendy | +0.011 |
Monkey | +0.011 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
pasta | -0.009 |
dumps | -0.008 |
view | -0.008 |
Token | has |
Token ID | 468 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
lot | +0.002 |
forward | +0.002 |
often | +0.002 |
Monkey | +0.002 |
Tiger | +0.002 |
Neg logit contributions | |
endant | -0.002 |
pasta | -0.002 |
Ta | -0.002 |
view | -0.002 |
apr | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.013 |
pasta | +0.013 |
dumps | +0.012 |
picks | +0.012 |
Neg logit contributions | |
lot | -0.011 |
forward | -0.011 |
mate | -0.010 |
Wendy | -0.010 |
often | -0.010 |
Token | z |
Token ID | 1976 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
pasta | +0.007 |
ice | +0.006 |
dumps | +0.006 |
Neg logit contributions | |
forward | -0.010 |
mate | -0.010 |
lot | -0.009 |
Wendy | -0.009 |
often | -0.009 |
Token | ig |
Token ID | 328 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
pasta | -0.004 |
view | -0.004 |
dumps | -0.004 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
lot | +0.023 |
forward | +0.023 |
mate | +0.022 |
often | +0.021 |
Wendy | +0.021 |
Neg logit contributions | |
endant | -0.051 |
puts | -0.048 |
pasta | -0.047 |
dumps | -0.046 |
picks | -0.045 |
Token | on |
Token ID | 319 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
lot | +0.073 |
forward | +0.069 |
mate | +0.067 |
often | +0.066 |
Wendy | +0.062 |
Neg logit contributions | |
endant | -0.070 |
puts | -0.064 |
Ta | -0.062 |
pasta | -0.061 |
picks | -0.059 |
Token | it |
Token ID | 340 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
puts | +0.007 |
ice | +0.007 |
endant | +0.007 |
dumps | +0.006 |
picks | +0.006 |
Neg logit contributions | |
forward | -0.006 |
Bet | -0.005 |
Wendy | -0.005 |
mate | -0.005 |
June | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
endant | +0.012 |
puts | +0.012 |
pasta | +0.011 |
dumps | +0.011 |
picks | +0.011 |
Neg logit contributions | |
forward | -0.007 |
lot | -0.007 |
mate | -0.007 |
Wendy | -0.007 |
often | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
view | +0.006 |
pasta | +0.006 |
dumps | +0.006 |
Neg logit contributions | |
lot | -0.004 |
forward | -0.004 |
Wendy | -0.004 |
mate | -0.004 |
Monkey | -0.004 |
Token | truck |
Token ID | 7779 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
lot | +0.005 |
forward | +0.004 |
mate | +0.004 |
Monkey | +0.004 |
Wendy | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.004 |
view | -0.004 |
pasta | -0.004 |
ws | -0.004 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
lot | +0.002 |
forward | +0.002 |
Wendy | +0.002 |
mate | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.003 |
pasta | -0.002 |
puts | -0.002 |
view | -0.002 |
dumps | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Wendy | +0.006 |
lot | +0.006 |
mate | +0.006 |
forward | +0.006 |
Monkey | +0.006 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
ice | -0.006 |
picks | -0.006 |
pasta | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.008 |
picks | +0.008 |
dumps | +0.008 |
Neg logit contributions | |
forward | -0.010 |
lot | -0.010 |
mate | -0.010 |
Wendy | -0.010 |
often | -0.010 |
Token | dog |
Token ID | 3290 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.007 |
view | +0.007 |
dumps | +0.007 |
Neg logit contributions | |
lot | -0.010 |
forward | -0.010 |
Wendy | -0.009 |
mate | -0.009 |
Monkey | -0.009 |
Token | fet |
Token ID | 11351 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
forward | +0.013 |
mate | +0.013 |
lot | +0.013 |
Wendy | +0.013 |
Monkey | +0.012 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.014 |
picks | -0.013 |
dumps | -0.013 |
pasta | -0.013 |
Token | ches |
Token ID | 2052 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Wendy | +0.018 |
Monkey | +0.018 |
Bet | +0.017 |
forward | +0.017 |
known | +0.017 |
Neg logit contributions | |
puts | -0.020 |
endant | -0.019 |
picks | -0.019 |
ws | -0.019 |
dumps | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
known | +0.074 |
Bet | +0.071 |
Monkey | +0.070 |
Wendy | +0.069 |
rarely | +0.069 |
Neg logit contributions | |
picks | -0.059 |
puts | -0.057 |
ice | -0.057 |
dumps | -0.054 |
ws | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
ice | +0.006 |
picks | +0.006 |
pasta | +0.005 |
Neg logit contributions | |
known | -0.007 |
Wendy | -0.007 |
Bet | -0.007 |
June | -0.007 |
Ally | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.007 |
picks | +0.006 |
ice | +0.006 |
dumps | +0.006 |
Neg logit contributions | |
mate | -0.008 |
forward | -0.008 |
June | -0.007 |
Bet | -0.007 |
lot | -0.007 |
Token | push |
Token ID | 4574 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
picks | +0.002 |
dumps | +0.002 |
ice | +0.002 |
Neg logit contributions | |
forward | -0.003 |
mate | -0.003 |
lot | -0.003 |
Wendy | -0.003 |
Monkey | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
known | +0.010 |
mate | +0.010 |
often | +0.010 |
Bet | +0.010 |
Wendy | +0.010 |
Neg logit contributions | |
puts | -0.011 |
picks | -0.010 |
ice | -0.010 |
dumps | -0.010 |
endant | -0.010 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.009 |
mate | +0.008 |
Wendy | +0.008 |
often | +0.008 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
pasta | -0.009 |
dumps | -0.009 |
view | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.014 |
pasta | +0.014 |
ice | +0.013 |
dumps | +0.013 |
Neg logit contributions | |
forward | -0.012 |
mate | -0.012 |
Wendy | -0.012 |
lot | -0.012 |
often | -0.012 |
Token | few |
Token ID | 1178 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
lot | +0.009 |
forward | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
Monkey | +0.008 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
pasta | -0.006 |
view | -0.006 |
dumps | -0.006 |
Token | treats |
Token ID | 18432 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
lot | +0.024 |
forward | +0.024 |
mate | +0.023 |
Wendy | +0.023 |
often | +0.023 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.013 |
pasta | -0.013 |
dumps | -0.012 |
view | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
lot | +0.013 |
forward | +0.013 |
mate | +0.013 |
Wendy | +0.013 |
Monkey | +0.012 |
Neg logit contributions | |
endant | -0.016 |
puts | -0.015 |
pasta | -0.015 |
ice | -0.014 |
dumps | -0.014 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
puts | +0.005 |
endant | +0.005 |
ice | +0.005 |
pasta | +0.005 |
dumps | +0.005 |
Neg logit contributions | |
forward | -0.007 |
mate | -0.007 |
lot | -0.007 |
Wendy | -0.007 |
stretched | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
forward | +0.078 |
stretched | +0.067 |
mate | +0.067 |
known | +0.066 |
Wendy | +0.065 |
Neg logit contributions | |
ice | -0.067 |
puts | -0.065 |
pasta | -0.061 |
endant | -0.061 |
picks | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
endant | +0.012 |
puts | +0.011 |
pasta | +0.011 |
ice | +0.011 |
picks | +0.011 |
Neg logit contributions | |
forward | -0.010 |
lot | -0.010 |
mate | -0.010 |
Wendy | -0.010 |
Bet | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
puts | +0.003 |
ice | +0.003 |
pasta | +0.003 |
frost | +0.003 |
envelope | +0.003 |
Neg logit contributions | |
forward | -0.004 |
Wendy | -0.003 |
Bet | -0.003 |
mate | -0.003 |
June | -0.003 |
Token | bag |
Token ID | 6131 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.003 |
pasta | +0.003 |
ice | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.007 |
mate | -0.007 |
Wendy | -0.007 |
lot | -0.007 |
often | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
endant | +0.012 |
pasta | +0.011 |
ice | +0.011 |
sandwich | +0.010 |
view | +0.010 |
Neg logit contributions | |
lot | -0.011 |
Wendy | -0.011 |
forward | -0.011 |
mate | -0.011 |
Monkey | -0.010 |
Token | bag |
Token ID | 6131 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
lot | +0.021 |
forward | +0.020 |
Wendy | +0.018 |
mate | +0.018 |
Monkey | +0.018 |
Neg logit contributions | |
endant | -0.013 |
puts | -0.012 |
view | -0.012 |
ws | -0.011 |
Ta | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
lot | +0.003 |
forward | +0.003 |
Wendy | +0.003 |
mate | +0.003 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
pasta | -0.003 |
picks | -0.003 |
ice | -0.003 |
Token | took |
Token ID | 1718 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.009 |
Wendy | +0.009 |
mate | +0.009 |
often | +0.008 |
Neg logit contributions | |
endant | -0.009 |
view | -0.008 |
puts | -0.008 |
pasta | -0.008 |
dumps | -0.008 |
Token | out |
Token ID | 503 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
puts | +0.024 |
endant | +0.024 |
ice | +0.023 |
pasta | +0.023 |
picks | +0.023 |
Neg logit contributions | |
Bet | -0.019 |
often | -0.019 |
mate | -0.019 |
Monkey | -0.019 |
forward | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
mate | +0.002 |
forward | +0.002 |
Bet | +0.002 |
Monkey | +0.002 |
rarely | +0.002 |
Neg logit contributions | |
endant | -0.002 |
pasta | -0.002 |
ice | -0.002 |
puts | -0.002 |
frost | -0.001 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
view | +0.008 |
dumps | +0.008 |
picks | +0.007 |
Neg logit contributions | |
lot | -0.011 |
forward | -0.010 |
Wendy | -0.009 |
mate | -0.009 |
often | -0.009 |
Token | animals |
Token ID | 4695 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
forward | +0.075 |
stretched | +0.069 |
often | +0.069 |
rarely | +0.068 |
known | +0.068 |
Neg logit contributions | |
puts | -0.066 |
ice | -0.065 |
pasta | -0.064 |
endant | -0.063 |
picks | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
lot | +0.019 |
forward | +0.019 |
mate | +0.018 |
Wendy | +0.018 |
Monkey | +0.017 |
Neg logit contributions | |
endant | -0.029 |
puts | -0.027 |
pasta | -0.026 |
ice | -0.025 |
picks | -0.025 |
Token | There |
Token ID | 1318 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
picks | +0.003 |
pasta | +0.003 |
dumps | +0.003 |
Neg logit contributions | |
mate | -0.003 |
forward | -0.003 |
forever | -0.002 |
lot | -0.002 |
often | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
forward | +0.005 |
lot | +0.005 |
mate | +0.005 |
Wendy | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
ice | -0.005 |
picks | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
endant | +0.004 |
ice | +0.004 |
pasta | +0.004 |
puts | +0.004 |
frost | +0.004 |
Neg logit contributions | |
mate | -0.006 |
forward | -0.006 |
Wendy | -0.005 |
Monkey | -0.005 |
Bet | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
pasta | +0.007 |
view | +0.007 |
dumps | +0.007 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.005 |
Wendy | -0.005 |
mate | -0.005 |
Monkey | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
pasta | +0.008 |
ice | +0.008 |
endant | +0.008 |
puts | +0.007 |
frost | +0.007 |
Neg logit contributions | |
forward | -0.010 |
mate | -0.009 |
often | -0.009 |
June | -0.008 |
Bet | -0.008 |
Token | blue |
Token ID | 4171 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.003 |
Wendy | +0.003 |
often | +0.003 |
June | +0.003 |
Neg logit contributions | |
endant | -0.002 |
pasta | -0.002 |
ice | -0.002 |
sandwich | -0.002 |
envelope | -0.002 |
Token | z |
Token ID | 1976 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
forward | +0.010 |
Wendy | +0.009 |
mate | +0.009 |
June | +0.009 |
often | +0.009 |
Neg logit contributions | |
endant | -0.005 |
pasta | -0.005 |
ice | -0.005 |
puts | -0.005 |
frost | -0.005 |
Token | ig |
Token ID | 328 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
mate | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
dumps | -0.001 |
ice | -0.001 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
forward | +0.036 |
lot | +0.035 |
Wendy | +0.034 |
mate | +0.034 |
Monkey | +0.032 |
Neg logit contributions | |
endant | -0.047 |
puts | -0.042 |
pasta | -0.042 |
ice | -0.041 |
dumps | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
forward | +0.078 |
lot | +0.076 |
Wendy | +0.075 |
mate | +0.075 |
Monkey | +0.072 |
Neg logit contributions | |
endant | -0.063 |
puts | -0.056 |
pasta | -0.055 |
ice | -0.053 |
dumps | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
puts | +0.004 |
picks | +0.004 |
endant | +0.003 |
dumps | +0.003 |
fills | +0.003 |
Neg logit contributions | |
mate | -0.004 |
often | -0.004 |
forward | -0.004 |
known | -0.003 |
forever | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
forward | +0.008 |
mate | +0.007 |
lot | +0.007 |
Wendy | +0.007 |
Monkey | +0.007 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
pasta | -0.006 |
picks | -0.006 |
ice | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
lot | +0.013 |
forward | +0.013 |
mate | +0.013 |
Bet | +0.013 |
Wendy | +0.012 |
Neg logit contributions | |
endant | -0.023 |
puts | -0.022 |
pasta | -0.022 |
ice | -0.022 |
picks | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
picks | +0.000 |
ice | +0.000 |
pasta | +0.000 |
Neg logit contributions | |
mate | -0.000 |
forward | -0.000 |
lot | -0.000 |
Wendy | -0.000 |
June | -0.000 |
Token | When |
Token ID | 1649 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
picks | +0.001 |
pasta | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
lot | -0.001 |
forward | -0.001 |
mate | -0.001 |
known | -0.001 |
often | -0.001 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
pasta | +0.002 |
puts | +0.002 |
ice | +0.002 |
endant | +0.002 |
sandwich | +0.002 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
lot | -0.002 |
Bet | -0.002 |
stretched | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
forward | +0.015 |
lot | +0.015 |
mate | +0.015 |
Wendy | +0.014 |
often | +0.014 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.014 |
pasta | -0.013 |
picks | -0.013 |
dumps | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
endant | +0.013 |
ice | +0.012 |
puts | +0.012 |
pasta | +0.012 |
frost | +0.012 |
Neg logit contributions | |
Bet | -0.013 |
often | -0.013 |
rarely | -0.013 |
known | -0.013 |
mate | -0.013 |
Token | magn |
Token ID | 7842 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
lot | +0.005 |
forward | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
dumps | -0.003 |
view | -0.003 |
picks | -0.003 |
Token | ifying |
Token ID | 4035 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.010 |
pasta | +0.010 |
dumps | +0.010 |
picks | +0.010 |
Neg logit contributions | |
lot | -0.007 |
Wendy | -0.006 |
mate | -0.006 |
forward | -0.006 |
often | -0.006 |
Token | glass |
Token ID | 5405 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
endant | +0.068 |
puts | +0.060 |
pasta | +0.054 |
picks | +0.054 |
dumps | +0.053 |
Neg logit contributions | |
lot | -0.136 |
forward | -0.134 |
Wendy | -0.130 |
mate | -0.130 |
Monkey | -0.126 |
Token | down |
Token ID | 866 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
ice | +0.003 |
dumps | +0.003 |
Neg logit contributions | |
forward | -0.002 |
lot | -0.002 |
mate | -0.002 |
Wendy | -0.002 |
Monkey | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
endant | +0.011 |
ice | +0.011 |
puts | +0.011 |
pasta | +0.011 |
picks | +0.010 |
Neg logit contributions | |
known | -0.009 |
Monkey | -0.009 |
mate | -0.009 |
June | -0.009 |
forward | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
mate | +0.024 |
forward | +0.023 |
stretched | +0.023 |
lot | +0.021 |
un | +0.021 |
Neg logit contributions | |
puts | -0.027 |
pasta | -0.026 |
ice | -0.025 |
picks | -0.024 |
finds | -0.024 |
Token | cater |
Token ID | 20825 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
forward | +0.000 |
lot | +0.000 |
mate | +0.000 |
Wendy | +0.000 |
often | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
ice | -0.000 |
picks | -0.000 |
Token | people |
Token ID | 661 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
forward | +0.009 |
mate | +0.009 |
Wendy | +0.009 |
lot | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.008 |
pasta | -0.008 |
ice | -0.007 |
picks | -0.007 |
Token | did |
Token ID | 750 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
endant | +0.015 |
puts | +0.013 |
pasta | +0.013 |
dumps | +0.012 |
view | +0.012 |
Neg logit contributions | |
forward | -0.019 |
lot | -0.019 |
mate | -0.018 |
Wendy | -0.018 |
often | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.009 |
pasta | +0.008 |
dumps | +0.008 |
picks | +0.008 |
Neg logit contributions | |
forward | -0.008 |
lot | -0.008 |
Wendy | -0.007 |
mate | -0.007 |
Monkey | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Wendy | +0.004 |
forward | +0.004 |
mate | +0.004 |
Bet | +0.004 |
stretched | +0.004 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.003 |
pasta | -0.003 |
ice | -0.003 |
picks | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
endant | +0.013 |
puts | +0.012 |
pasta | +0.012 |
dumps | +0.011 |
picks | +0.011 |
Neg logit contributions | |
forward | -0.012 |
lot | -0.012 |
Wendy | -0.012 |
mate | -0.012 |
often | -0.011 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
endant | +0.018 |
puts | +0.017 |
pasta | +0.016 |
dumps | +0.016 |
picks | +0.016 |
Neg logit contributions | |
forward | -0.017 |
lot | -0.017 |
mate | -0.017 |
Wendy | -0.017 |
Monkey | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
endant | +0.118 |
puts | +0.105 |
Ta | +0.103 |
dumps | +0.103 |
pasta | +0.103 |
Neg logit contributions | |
lot | -0.073 |
forward | -0.072 |
mate | -0.070 |
often | -0.069 |
Wendy | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
picks | +0.003 |
dumps | +0.003 |
Neg logit contributions | |
forward | -0.003 |
lot | -0.003 |
mate | -0.003 |
Wendy | -0.003 |
often | -0.003 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
pasta | +0.000 |
dumps | +0.000 |
picks | +0.000 |
Neg logit contributions | |
forward | -0.000 |
lot | -0.000 |
mate | -0.000 |
Wendy | -0.000 |
Monkey | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Wendy | +0.025 |
lot | +0.024 |
mate | +0.023 |
Monkey | +0.023 |
Bet | +0.023 |
Neg logit contributions | |
endant | -0.020 |
pasta | -0.019 |
puts | -0.018 |
ice | -0.018 |
picks | -0.018 |
Token | castles |
Token ID | 49203 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
forward | +0.013 |
mate | +0.012 |
Wendy | +0.012 |
Bet | +0.012 |
often | +0.012 |
Neg logit contributions | |
puts | -0.010 |
endant | -0.010 |
pasta | -0.010 |
ice | -0.010 |
frost | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Bet | +0.006 |
June | +0.005 |
lot | +0.005 |
Wendy | +0.005 |
Pat | +0.005 |
Neg logit contributions | |
puts | -0.005 |
picks | -0.005 |
endant | -0.005 |
ice | -0.005 |
pasta | -0.005 |
Token | handing |
Token ID | 22786 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
lot | +0.004 |
mate | +0.004 |
forward | +0.004 |
Wendy | +0.004 |
June | +0.004 |
Neg logit contributions | |
picks | -0.005 |
puts | -0.005 |
ice | -0.005 |
endant | -0.004 |
pasta | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
ice | +0.009 |
pasta | +0.008 |
puts | +0.008 |
frost | +0.008 |
envelope | +0.008 |
Neg logit contributions | |
stretched | -0.010 |
rarely | -0.010 |
often | -0.009 |
lot | -0.009 |
forward | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
lot | -0.001 |
forward | -0.001 |
mate | -0.001 |
often | -0.001 |
Wendy | -0.001 |
Token | magn |
Token ID | 7842 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
dumps | +0.001 |
pasta | +0.001 |
view | +0.001 |
Neg logit contributions | |
lot | -0.002 |
forward | -0.002 |
mate | -0.002 |
Wendy | -0.002 |
Monkey | -0.002 |
Token | ifying |
Token ID | 4035 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
endant | +0.013 |
pasta | +0.012 |
puts | +0.011 |
dumps | +0.011 |
frost | +0.011 |
Neg logit contributions | |
lot | -0.008 |
Wendy | -0.008 |
Bet | -0.007 |
known | -0.007 |
often | -0.007 |
Token | glass |
Token ID | 5405 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
endant | +0.046 |
puts | +0.037 |
pasta | +0.035 |
dumps | +0.033 |
ice | +0.032 |
Neg logit contributions | |
forward | -0.144 |
lot | -0.143 |
mate | -0.140 |
Wendy | -0.139 |
often | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.004 |
ice | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.003 |
lot | -0.003 |
Wendy | -0.003 |
mate | -0.003 |
Monkey | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
endant | +0.004 |
picks | +0.004 |
puts | +0.004 |
says | +0.003 |
pasta | +0.003 |
Neg logit contributions | |
forward | -0.005 |
mate | -0.005 |
known | -0.005 |
lot | -0.005 |
often | -0.004 |
Token | looked |
Token ID | 3114 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
pasta | -0.002 |
dumps | -0.002 |
picks | -0.002 |
Token | around |
Token ID | 1088 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
endant | +0.019 |
puts | +0.017 |
pasta | +0.017 |
dumps | +0.017 |
picks | +0.016 |
Neg logit contributions | |
forward | -0.016 |
lot | -0.016 |
mate | -0.016 |
Wendy | -0.015 |
often | -0.015 |
Token | velvet |
Token ID | 47750 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
lot | +0.003 |
forward | +0.003 |
often | +0.003 |
forever | +0.003 |
mate | +0.003 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
dumps | -0.002 |
ws | -0.002 |
pasta | -0.002 |
Token | box |
Token ID | 3091 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
forward | +0.012 |
known | +0.012 |
Wendy | +0.012 |
Bet | +0.011 |
lot | +0.011 |
Neg logit contributions | |
endant | -0.008 |
necklace | -0.007 |
ice | -0.007 |
puts | -0.007 |
pasta | -0.007 |
Token | all |
Token ID | 477 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
lot | +0.011 |
Wendy | +0.011 |
Bet | +0.010 |
mate | +0.010 |
Monkey | +0.010 |
Neg logit contributions | |
endant | -0.014 |
puts | -0.013 |
pasta | -0.012 |
ice | -0.012 |
picks | -0.012 |
Token | those |
Token ID | 883 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.002 |
pasta | +0.002 |
dumps | +0.002 |
ice | +0.002 |
Neg logit contributions | |
lot | -0.002 |
forward | -0.002 |
mate | -0.002 |
Wendy | -0.002 |
Monkey | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.008 |
dumps | +0.008 |
picks | +0.008 |
Neg logit contributions | |
forward | -0.010 |
lot | -0.010 |
mate | -0.009 |
Wendy | -0.009 |
often | -0.009 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
endant | +0.040 |
puts | +0.036 |
pasta | +0.035 |
ice | +0.034 |
picks | +0.034 |
Neg logit contributions | |
mate | -0.037 |
lot | -0.037 |
forward | -0.037 |
Wendy | -0.036 |
Monkey | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
endant | +0.108 |
puts | +0.101 |
pasta | +0.098 |
picks | +0.096 |
ice | +0.095 |
Neg logit contributions | |
forward | -0.073 |
lot | -0.072 |
Wendy | -0.070 |
mate | -0.069 |
Monkey | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.008 |
picks | +0.008 |
pasta | +0.008 |
dumps | +0.008 |
Neg logit contributions | |
mate | -0.008 |
lot | -0.008 |
forward | -0.008 |
often | -0.007 |
June | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
picks | +0.003 |
ice | +0.003 |
finds | +0.003 |
Neg logit contributions | |
mate | -0.004 |
forward | -0.004 |
lot | -0.004 |
Wendy | -0.004 |
Monkey | -0.004 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
puts | +0.002 |
endant | +0.002 |
ice | +0.002 |
picks | +0.002 |
pasta | +0.002 |
Neg logit contributions | |
mate | -0.002 |
Monkey | -0.002 |
lot | -0.002 |
Bet | -0.002 |
Wendy | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
mate | +0.005 |
June | +0.004 |
forward | +0.004 |
Bet | +0.004 |
lot | +0.004 |
Neg logit contributions | |
ice | -0.004 |
pasta | -0.004 |
puts | -0.004 |
endant | -0.004 |
oy | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
stretched | +0.016 |
ways | +0.015 |
Bet | +0.015 |
forward | +0.014 |
� | +0.014 |
Neg logit contributions | |
puts | -0.014 |
ice | -0.013 |
wraps | -0.013 |
happen | -0.012 |
oy | -0.012 |
Token | pigeon |
Token ID | 46387 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
forward | +0.009 |
mate | +0.009 |
lot | +0.008 |
Bet | +0.008 |
Wendy | +0.008 |
Neg logit contributions | |
endant | -0.008 |
ice | -0.008 |
puts | -0.008 |
pasta | -0.008 |
picks | -0.007 |
Token | all |
Token ID | 477 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
ice | +0.003 |
finds | +0.003 |
picks | +0.003 |
Neg logit contributions | |
lot | -0.003 |
mate | -0.003 |
Wendy | -0.003 |
forward | -0.003 |
Bet | -0.003 |
Token | those |
Token ID | 883 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
forward | +0.007 |
lot | +0.007 |
mate | +0.007 |
Wendy | +0.007 |
Monkey | +0.007 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.008 |
pasta | -0.008 |
picks | -0.008 |
ice | -0.008 |
Token | weeks |
Token ID | 2745 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.008 |
pasta | +0.008 |
ice | +0.008 |
picks | +0.007 |
Neg logit contributions | |
mate | -0.009 |
lot | -0.009 |
Wendy | -0.009 |
forward | -0.009 |
Bet | -0.009 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
endant | +0.022 |
puts | +0.022 |
picks | +0.020 |
ice | +0.020 |
view | +0.019 |
Neg logit contributions | |
lot | -0.019 |
Wendy | -0.018 |
forward | -0.018 |
mate | -0.018 |
Monkey | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
endant | +0.097 |
puts | +0.095 |
pasta | +0.090 |
ice | +0.089 |
picks | +0.089 |
Neg logit contributions | |
forward | -0.081 |
lot | -0.079 |
Wendy | -0.078 |
Bet | -0.076 |
Monkey | -0.075 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
puts | +0.004 |
endant | +0.004 |
picks | +0.004 |
says | +0.003 |
dumps | +0.003 |
Neg logit contributions | |
mate | -0.005 |
forward | -0.005 |
lot | -0.005 |
stretched | -0.004 |
often | -0.004 |
Token | Mike |
Token ID | 16073 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
often | +0.004 |
Wendy | +0.004 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
pasta | -0.003 |
picks | -0.003 |
ice | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
endant | +0.012 |
puts | +0.011 |
pasta | +0.011 |
picks | +0.011 |
dumps | +0.011 |
Neg logit contributions | |
forward | -0.009 |
lot | -0.009 |
mate | -0.009 |
Wendy | -0.009 |
Monkey | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
forward | +0.016 |
lot | +0.016 |
mate | +0.016 |
Wendy | +0.015 |
often | +0.014 |
Neg logit contributions | |
endant | -0.020 |
puts | -0.020 |
ice | -0.019 |
pasta | -0.019 |
picks | -0.018 |
Token | our |
Token ID | 674 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
Bet | +0.004 |
Wendy | +0.004 |
forward | +0.003 |
June | +0.003 |
mate | +0.003 |
Neg logit contributions | |
ice | -0.003 |
puts | -0.003 |
pasta | -0.003 |
picks | -0.002 |
oy | -0.002 |
Token | country |
Token ID | 1499 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
mate | +0.000 |
forward | +0.000 |
Wendy | +0.000 |
Bet | +0.000 |
lot | +0.000 |
Neg logit contributions | |
endant | -0.000 |
ice | -0.000 |
puts | -0.000 |
pasta | -0.000 |
picks | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
endant | +0.036 |
puts | +0.034 |
ice | +0.034 |
pasta | +0.033 |
picks | +0.032 |
Neg logit contributions | |
Wendy | -0.037 |
Bet | -0.036 |
lot | -0.035 |
forward | -0.035 |
mate | -0.035 |
Token | long |
Token ID | 890 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
ice | +0.006 |
sandwich | +0.005 |
necklace | +0.005 |
card | +0.005 |
coin | +0.005 |
Neg logit contributions | |
Wendy | -0.008 |
stretched | -0.008 |
Bet | -0.008 |
mate | -0.008 |
June | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
puts | +0.018 |
endant | +0.018 |
picks | +0.018 |
ice | +0.018 |
envelope | +0.017 |
Neg logit contributions | |
forward | -0.023 |
Wendy | -0.022 |
Bet | -0.021 |
mate | -0.021 |
Mitt | -0.021 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.011 |
ice | +0.010 |
pasta | +0.010 |
picks | +0.010 |
Neg logit contributions | |
Wendy | -0.012 |
mate | -0.012 |
Bet | -0.012 |
lot | -0.012 |
June | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
endant | +0.106 |
puts | +0.101 |
pasta | +0.099 |
ice | +0.097 |
picks | +0.096 |
Neg logit contributions | |
forward | -0.073 |
lot | -0.072 |
Wendy | -0.071 |
mate | -0.068 |
Bet | -0.066 |
Token | He |
Token ID | 679 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
mate | +0.000 |
lot | +0.000 |
forward | +0.000 |
stretched | +0.000 |
often | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
ice | -0.000 |
dumps | -0.000 |
Token | helped |
Token ID | 4193 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
forward | +0.010 |
mate | +0.010 |
Wendy | +0.009 |
lot | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
puts | -0.007 |
endant | -0.007 |
picks | -0.006 |
ice | -0.006 |
finds | -0.006 |
Token | many |
Token ID | 867 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
forward | +0.019 |
stretched | +0.018 |
lot | +0.018 |
mate | +0.018 |
Wendy | +0.018 |
Neg logit contributions | |
puts | -0.019 |
ice | -0.019 |
pasta | -0.018 |
address | -0.017 |
picks | -0.017 |
Token | people |
Token ID | 661 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Bet | +0.025 |
mate | +0.025 |
Wendy | +0.025 |
forward | +0.024 |
� | +0.024 |
Neg logit contributions | |
puts | -0.018 |
ice | -0.017 |
pasta | -0.016 |
picks | -0.016 |
shirts | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
lot | +0.001 |
forward | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
picks | -0.001 |
pasta | -0.001 |
ice | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
lot | +0.008 |
forward | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
Bet | +0.007 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
picks | -0.006 |
pasta | -0.006 |
ice | -0.006 |
Token | told |
Token ID | 1297 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
endant | +0.017 |
puts | +0.015 |
pasta | +0.015 |
dumps | +0.014 |
picks | +0.014 |
Neg logit contributions | |
forward | -0.022 |
lot | -0.022 |
mate | -0.021 |
Wendy | -0.021 |
often | -0.020 |
Token | him |
Token ID | 683 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
lot | +0.019 |
Wendy | +0.018 |
forward | +0.018 |
Monkey | +0.017 |
Bet | +0.017 |
Neg logit contributions | |
pasta | -0.017 |
ice | -0.017 |
puts | -0.017 |
endant | -0.016 |
picks | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
lot | +0.006 |
Bet | +0.006 |
mate | +0.006 |
forward | +0.006 |
Wendy | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
pasta | -0.006 |
ice | -0.006 |
picks | -0.006 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.013 |
pasta | +0.013 |
picks | +0.012 |
ice | +0.012 |
Neg logit contributions | |
forward | -0.018 |
lot | -0.017 |
mate | -0.017 |
Wendy | -0.017 |
Monkey | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
endant | +0.099 |
puts | +0.095 |
pasta | +0.093 |
ice | +0.090 |
picks | +0.090 |
Neg logit contributions | |
forward | -0.076 |
lot | -0.074 |
Wendy | -0.074 |
mate | -0.071 |
Bet | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
endant | +0.003 |
pasta | +0.002 |
puts | +0.002 |
picks | +0.002 |
ice | +0.002 |
Neg logit contributions | |
forward | -0.003 |
mate | -0.003 |
lot | -0.003 |
stretched | -0.002 |
often | -0.002 |
Token | bird |
Token ID | 6512 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
endant | +0.002 |
pasta | +0.002 |
puts | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
Wendy | -0.002 |
lot | -0.002 |
Bet | -0.002 |
Token | spread |
Token ID | 4104 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
forward | +0.018 |
lot | +0.018 |
mate | +0.017 |
Wendy | +0.017 |
Monkey | +0.016 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.016 |
picks | -0.015 |
ice | -0.015 |
pasta | -0.014 |
Token | out |
Token ID | 503 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
ice | +0.011 |
puts | +0.011 |
pasta | +0.011 |
endant | +0.011 |
picks | +0.011 |
Neg logit contributions | |
mate | -0.011 |
lot | -0.011 |
Monkey | -0.011 |
Wendy | -0.011 |
often | -0.011 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.010 |
Wendy | +0.010 |
mate | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.008 |
picks | -0.007 |
dumps | -0.007 |
ice | -0.007 |
Token | here |
Token ID | 994 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Wendy | +0.034 |
lot | +0.034 |
Monkey | +0.033 |
Bet | +0.032 |
June | +0.032 |
Neg logit contributions | |
endant | -0.019 |
pasta | -0.019 |
puts | -0.018 |
ice | -0.018 |
picks | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Wendy | +0.009 |
lot | +0.009 |
Bet | +0.009 |
Monkey | +0.009 |
mate | +0.008 |
Neg logit contributions | |
endant | -0.009 |
pasta | -0.009 |
ice | -0.008 |
puts | -0.008 |
sandwich | -0.008 |
Token | long |
Token ID | 890 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ice | +0.001 |
pasta | +0.001 |
sandwich | +0.000 |
oy | +0.000 |
endant | +0.000 |
Neg logit contributions | |
Bet | -0.001 |
stretched | -0.001 |
Wendy | -0.001 |
June | -0.001 |
forward | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
endant | +0.022 |
puts | +0.021 |
pasta | +0.021 |
ice | +0.020 |
dumps | +0.020 |
Neg logit contributions | |
forward | -0.024 |
Wendy | -0.023 |
mate | -0.023 |
Bet | -0.023 |
lot | -0.023 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
pasta | +0.006 |
ice | +0.005 |
picks | +0.005 |
Neg logit contributions | |
lot | -0.007 |
Wendy | -0.007 |
forward | -0.007 |
mate | -0.007 |
Bet | -0.007 |
Token | ." |
Token ID | 526 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
endant | +0.111 |
puts | +0.104 |
pasta | +0.102 |
dumps | +0.099 |
picks | +0.099 |
Neg logit contributions | |
forward | -0.064 |
lot | -0.063 |
Wendy | -0.060 |
mate | -0.060 |
Monkey | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
forward | +0.000 |
lot | +0.000 |
mate | +0.000 |
often | +0.000 |
stretched | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
picks | -0.000 |
ice | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
picks | -0.002 |
ice | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
view | -0.004 |
pasta | -0.004 |
ice | -0.004 |
Token | Can |
Token ID | 6090 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.004 |
ice | +0.004 |
dumps | +0.004 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.004 |
Wendy | -0.004 |
mate | -0.004 |
often | -0.004 |
Token | flashlight |
Token ID | 38371 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
endant | +0.009 |
pasta | +0.009 |
ice | +0.009 |
sandwich | +0.009 |
puts | +0.008 |
Neg logit contributions | |
forward | -0.016 |
mate | -0.015 |
Wendy | -0.015 |
often | -0.015 |
Bet | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
forward | +0.008 |
lot | +0.008 |
Wendy | +0.008 |
mate | +0.008 |
Bet | +0.007 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
pasta | -0.009 |
ice | -0.009 |
dumps | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
forward | +0.016 |
mate | +0.016 |
lot | +0.016 |
Wendy | +0.015 |
Monkey | +0.015 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.016 |
pasta | -0.015 |
ice | -0.015 |
picks | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
puts | +0.002 |
endant | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
lot | -0.002 |
Wendy | -0.002 |
Bet | -0.002 |
Token | magn |
Token ID | 7842 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
endant | +0.011 |
pasta | +0.010 |
ice | +0.010 |
sandwich | +0.010 |
necklace | +0.009 |
Neg logit contributions | |
forward | -0.018 |
mate | -0.018 |
Wendy | -0.017 |
Bet | -0.017 |
often | -0.017 |
Token | ifying |
Token ID | 4035 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
pasta | +0.009 |
dumps | +0.009 |
picks | +0.009 |
Neg logit contributions | |
lot | -0.006 |
Wendy | -0.006 |
forward | -0.006 |
mate | -0.006 |
Monkey | -0.006 |
Token | glass |
Token ID | 5405 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
endant | +0.055 |
puts | +0.047 |
pasta | +0.044 |
dumps | +0.042 |
picks | +0.042 |
Neg logit contributions | |
forward | -0.119 |
lot | -0.118 |
mate | -0.115 |
Wendy | -0.115 |
often | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
endant | +0.010 |
pasta | +0.009 |
puts | +0.009 |
ice | +0.008 |
dumps | +0.008 |
Neg logit contributions | |
forward | -0.008 |
lot | -0.008 |
Wendy | -0.008 |
mate | -0.008 |
Monkey | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
mate | +0.002 |
forward | +0.002 |
lot | +0.002 |
often | +0.002 |
known | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
picks | -0.002 |
pasta | -0.002 |
dumps | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
forward | +0.008 |
mate | +0.008 |
lot | +0.008 |
Monkey | +0.008 |
Wendy | +0.007 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.007 |
picks | -0.007 |
pasta | -0.007 |
dumps | -0.007 |
Token | As |
Token ID | 1722 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.008 |
Monkey | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
Neg logit contributions | |
endant | -0.011 |
puts | -0.010 |
picks | -0.010 |
Ta | -0.010 |
view | -0.010 |
Token | born |
Token ID | 4642 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
lot | +0.023 |
mate | +0.023 |
Wendy | +0.022 |
Bet | +0.022 |
Monkey | +0.022 |
Neg logit contributions | |
puts | -0.024 |
endant | -0.024 |
ice | -0.023 |
picks | -0.023 |
pasta | -0.023 |
Token | only |
Token ID | 691 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
Bet | +0.023 |
June | +0.023 |
Wendy | +0.022 |
mate | +0.022 |
lot | +0.022 |
Neg logit contributions | |
ice | -0.024 |
puts | -0.023 |
endant | -0.023 |
pasta | -0.023 |
oy | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
Bet | +0.019 |
Wendy | +0.019 |
mate | +0.019 |
lot | +0.019 |
forward | +0.018 |
Neg logit contributions | |
puts | -0.021 |
endant | -0.020 |
picks | -0.020 |
ice | -0.020 |
finds | -0.019 |
Token | few |
Token ID | 1178 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ice | +0.001 |
necklace | +0.001 |
sandwich | +0.001 |
coin | +0.001 |
endant | +0.001 |
Neg logit contributions | |
Wendy | -0.001 |
Bet | -0.001 |
June | -0.001 |
forward | -0.001 |
mate | -0.001 |
Token | days |
Token ID | 1528 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Bet | +0.014 |
Wendy | +0.014 |
mate | +0.013 |
Monkey | +0.013 |
June | +0.013 |
Neg logit contributions | |
puts | -0.011 |
picks | -0.011 |
ice | -0.011 |
finds | -0.011 |
pasta | -0.010 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
endant | +0.013 |
puts | +0.013 |
ice | +0.013 |
pasta | +0.012 |
picks | +0.012 |
Neg logit contributions | |
lot | -0.010 |
mate | -0.010 |
Wendy | -0.010 |
forward | -0.009 |
Bet | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
endant | +0.104 |
puts | +0.099 |
pasta | +0.097 |
ice | +0.096 |
picks | +0.094 |
Neg logit contributions | |
forward | -0.068 |
lot | -0.067 |
Wendy | -0.065 |
mate | -0.062 |
Bet | -0.062 |
Token | The |
Token ID | 383 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
endant | +0.004 |
pasta | +0.004 |
puts | +0.004 |
ice | +0.004 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.004 |
lot | -0.004 |
mate | -0.004 |
Wendy | -0.004 |
stretched | -0.004 |
Token | deer |
Token ID | 20096 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.003 |
Wendy | +0.003 |
Bet | +0.002 |
lot | +0.002 |
Neg logit contributions | |
endant | -0.002 |
pasta | -0.002 |
ice | -0.002 |
puts | -0.002 |
picks | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
forward | +0.023 |
mate | +0.022 |
lot | +0.022 |
Wendy | +0.021 |
Bet | +0.020 |
Neg logit contributions | |
endant | -0.018 |
puts | -0.017 |
picks | -0.016 |
ice | -0.016 |
finds | -0.015 |
Token | sorry |
Token ID | 7926 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
mate | +0.014 |
Bet | +0.013 |
Monkey | +0.013 |
Wendy | +0.013 |
June | +0.013 |
Neg logit contributions | |
ice | -0.013 |
puts | -0.013 |
endant | -0.013 |
pasta | -0.013 |
picks | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
mate | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
ice | -0.001 |
dumps | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
endant | +0.024 |
puts | +0.022 |
pasta | +0.021 |
dumps | +0.021 |
picks | +0.021 |
Neg logit contributions | |
forward | -0.018 |
lot | -0.017 |
mate | -0.017 |
Wendy | -0.017 |
often | -0.016 |
Token | crabs |
Token ID | 49172 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
pasta | +0.005 |
dumps | +0.005 |
picks | +0.005 |
Neg logit contributions | |
lot | -0.009 |
forward | -0.009 |
mate | -0.008 |
Wendy | -0.008 |
often | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
endant | +0.028 |
puts | +0.026 |
pasta | +0.025 |
dumps | +0.025 |
picks | +0.025 |
Neg logit contributions | |
forward | -0.019 |
lot | -0.019 |
mate | -0.018 |
Wendy | -0.018 |
often | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
endant | +0.028 |
puts | +0.026 |
pasta | +0.025 |
dumps | +0.025 |
ice | +0.025 |
Neg logit contributions | |
forward | -0.020 |
lot | -0.020 |
mate | -0.019 |
Wendy | -0.019 |
often | -0.018 |
Token | seaw |
Token ID | 32085 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
pasta | +0.008 |
dumps | +0.008 |
view | +0.008 |
Neg logit contributions | |
lot | -0.015 |
forward | -0.015 |
mate | -0.014 |
Wendy | -0.014 |
often | -0.014 |
Token | eed |
Token ID | 2308 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
endant | +0.059 |
puts | +0.056 |
view | +0.051 |
Ta | +0.049 |
pasta | +0.049 |
Neg logit contributions | |
lot | -0.112 |
forward | -0.107 |
mate | -0.104 |
often | -0.102 |
Wendy | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
endant | +0.044 |
puts | +0.041 |
pasta | +0.040 |
ice | +0.040 |
dumps | +0.039 |
Neg logit contributions | |
forward | -0.031 |
lot | -0.031 |
Wendy | -0.031 |
mate | -0.030 |
Bet | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.004 |
picks | +0.004 |
dumps | +0.004 |
Neg logit contributions | |
forward | -0.004 |
mate | -0.004 |
lot | -0.004 |
often | -0.004 |
Monkey | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.005 |
dumps | +0.004 |
view | +0.004 |
Neg logit contributions | |
lot | -0.003 |
forward | -0.003 |
Wendy | -0.003 |
mate | -0.003 |
often | -0.002 |
Token | Sam |
Token ID | 16305 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
picks | +0.002 |
dumps | +0.002 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
lot | -0.001 |
Monkey | -0.001 |
Wendy | -0.001 |
Token | are |
Token ID | 389 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
pasta | +0.009 |
dumps | +0.008 |
picks | +0.008 |
Neg logit contributions | |
forward | -0.014 |
lot | -0.014 |
mate | -0.014 |
Wendy | -0.014 |
often | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
mate | +0.001 |
Wendy | +0.001 |
forward | +0.001 |
Bet | +0.001 |
June | +0.001 |
Neg logit contributions | |
puts | -0.001 |
endant | -0.001 |
pasta | -0.001 |
ice | -0.001 |
picks | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
pasta | +0.007 |
ice | +0.007 |
puts | +0.007 |
endant | +0.007 |
picks | +0.006 |
Neg logit contributions | |
Wendy | -0.008 |
forward | -0.007 |
Bet | -0.007 |
mate | -0.007 |
June | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ice | +0.003 |
pasta | +0.003 |
sandwich | +0.003 |
oy | +0.003 |
mess | +0.003 |
Neg logit contributions | |
Wendy | -0.004 |
Bet | -0.004 |
June | -0.004 |
stretched | -0.004 |
Pat | -0.004 |
Token | time |
Token ID | 640 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
puts | +0.017 |
endant | +0.016 |
pasta | +0.016 |
picks | +0.016 |
ice | +0.016 |
Neg logit contributions | |
forward | -0.019 |
Wendy | -0.019 |
Bet | -0.018 |
mate | -0.018 |
June | -0.018 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
endant | +0.016 |
puts | +0.016 |
pasta | +0.015 |
picks | +0.015 |
ice | +0.014 |
Neg logit contributions | |
Wendy | -0.021 |
mate | -0.020 |
lot | -0.020 |
Bet | -0.020 |
forward | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
endant | +0.102 |
puts | +0.097 |
pasta | +0.094 |
picks | +0.093 |
ice | +0.092 |
Neg logit contributions | |
forward | -0.069 |
lot | -0.067 |
Wendy | -0.066 |
mate | -0.064 |
Monkey | -0.062 |
Token | before |
Token ID | 878 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
puts | +0.002 |
endant | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
mate | -0.002 |
forward | -0.002 |
lot | -0.002 |
Wendy | -0.002 |
Monkey | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
puts | +0.008 |
pasta | +0.008 |
ice | +0.008 |
endant | +0.008 |
picks | +0.007 |
Neg logit contributions | |
forward | -0.011 |
mate | -0.011 |
June | -0.010 |
Bet | -0.010 |
Wendy | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
pasta | +0.001 |
ice | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
Wendy | -0.002 |
forward | -0.002 |
lot | -0.002 |
mate | -0.002 |
Bet | -0.002 |
Token | born |
Token ID | 4642 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
mate | +0.024 |
Wendy | +0.024 |
Bet | +0.023 |
lot | +0.023 |
forward | +0.022 |
Neg logit contributions | |
endant | -0.022 |
puts | -0.022 |
pasta | -0.022 |
ice | -0.021 |
picks | -0.021 |
Token | story |
Token ID | 1621 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
forward | +0.006 |
Wendy | +0.005 |
mate | +0.005 |
Bet | +0.005 |
stretched | +0.005 |
Neg logit contributions | |
endant | -0.004 |
ice | -0.004 |
puts | -0.004 |
pasta | -0.004 |
sandwich | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
ice | +0.003 |
picks | +0.003 |
Neg logit contributions | |
Wendy | -0.004 |
lot | -0.004 |
Bet | -0.004 |
forward | -0.004 |
Mitt | -0.004 |
Token | A |
Token ID | 317 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
lot | +0.006 |
forward | +0.006 |
mate | +0.006 |
often | +0.006 |
Wendy | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.005 |
picks | -0.005 |
pasta | -0.005 |
dumps | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
forward | +0.001 |
Wendy | +0.001 |
mate | +0.001 |
stretched | +0.001 |
Bet | +0.001 |
Neg logit contributions | |
endant | -0.000 |
sandwich | -0.000 |
pasta | -0.000 |
necklace | -0.000 |
ice | -0.000 |
Token | time |
Token ID | 640 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
endant | +0.026 |
puts | +0.024 |
pasta | +0.024 |
picks | +0.023 |
ice | +0.023 |
Neg logit contributions | |
forward | -0.030 |
Wendy | -0.028 |
lot | -0.028 |
mate | -0.027 |
Monkey | -0.026 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.014 |
picks | +0.014 |
pasta | +0.013 |
finds | +0.013 |
Neg logit contributions | |
forward | -0.012 |
mate | -0.012 |
Wendy | -0.011 |
Bet | -0.011 |
lot | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
endant | +0.115 |
puts | +0.108 |
pasta | +0.105 |
dumps | +0.103 |
picks | +0.103 |
Neg logit contributions | |
forward | -0.056 |
lot | -0.055 |
Wendy | -0.052 |
mate | -0.052 |
Monkey | -0.049 |
Token | there |
Token ID | 612 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
forward | +0.021 |
mate | +0.020 |
lot | +0.020 |
Wendy | +0.019 |
stretched | +0.019 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.016 |
pasta | -0.015 |
ice | -0.015 |
picks | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.006 |
Wendy | +0.006 |
Monkey | +0.006 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
picks | -0.003 |
pasta | -0.003 |
ice | -0.003 |
Token | an |
Token ID | 281 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
forward | +0.004 |
stretched | +0.003 |
mate | +0.003 |
un | +0.003 |
onward | +0.003 |
Neg logit contributions | |
ice | -0.002 |
pasta | -0.002 |
puts | -0.002 |
frost | -0.001 |
bread | -0.001 |
Token | adventurous |
Token ID | 39770 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
endant | +0.020 |
puts | +0.019 |
dumps | +0.019 |
picks | +0.018 |
finds | +0.017 |
Neg logit contributions | |
often | -0.023 |
forward | -0.022 |
lot | -0.022 |
Monkey | -0.021 |
forever | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
lot | +0.020 |
forward | +0.020 |
Wendy | +0.019 |
Bet | +0.019 |
mate | +0.019 |
Neg logit contributions | |
endant | -0.023 |
puts | -0.022 |
pasta | -0.022 |
ice | -0.021 |
picks | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
forward | +0.005 |
lot | +0.005 |
Wendy | +0.005 |
mate | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
picks | -0.003 |
pasta | -0.003 |
ice | -0.003 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
picks | +0.003 |
pasta | +0.003 |
ice | +0.003 |
Neg logit contributions | |
Wendy | -0.004 |
forward | -0.004 |
lot | -0.004 |
Monkey | -0.004 |
mate | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Wendy | +0.004 |
Bet | +0.004 |
lot | +0.004 |
June | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
pasta | -0.004 |
ice | -0.004 |
endant | -0.004 |
puts | -0.003 |
view | -0.003 |
Token | year |
Token ID | 614 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
mess | +0.004 |
necklace | +0.004 |
ice | +0.004 |
card | +0.004 |
envelope | +0.004 |
Neg logit contributions | |
Bet | -0.007 |
Pat | -0.007 |
Wendy | -0.006 |
stretched | -0.006 |
Da | -0.006 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
pasta | +0.009 |
dumps | +0.009 |
picks | +0.008 |
Neg logit contributions | |
forward | -0.008 |
lot | -0.008 |
mate | -0.007 |
Wendy | -0.007 |
often | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
endant | +0.099 |
puts | +0.092 |
pasta | +0.091 |
ice | +0.089 |
picks | +0.088 |
Neg logit contributions | |
forward | -0.069 |
lot | -0.068 |
Wendy | -0.067 |
mate | -0.065 |
Monkey | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
pasta | +0.001 |
picks | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
mate | -0.001 |
forward | -0.001 |
lot | -0.001 |
often | -0.001 |
stretched | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
forward | +0.007 |
mate | +0.007 |
lot | +0.006 |
Wendy | +0.006 |
Bet | +0.006 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
picks | -0.005 |
ice | -0.005 |
dumps | -0.004 |
Token | home |
Token ID | 1363 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ice | +0.003 |
endant | +0.003 |
picks | +0.003 |
puts | +0.003 |
pasta | +0.003 |
Neg logit contributions | |
lot | -0.004 |
rarely | -0.004 |
Bet | -0.004 |
mate | -0.004 |
stretched | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
mate | +0.008 |
lot | +0.008 |
forward | +0.007 |
Bet | +0.007 |
Wendy | +0.007 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
ice | -0.006 |
picks | -0.006 |
pasta | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
endant | +0.003 |
pasta | +0.003 |
puts | +0.003 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
mate | -0.002 |
forward | -0.002 |
Wendy | -0.002 |
Bet | -0.002 |
Monkey | -0.002 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.003 |
Wendy | -0.003 |
mate | -0.003 |
lot | -0.003 |
Bet | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Wendy | +0.025 |
lot | +0.025 |
Bet | +0.024 |
Monkey | +0.024 |
June | +0.023 |
Neg logit contributions | |
endant | -0.020 |
pasta | -0.020 |
ice | -0.019 |
puts | -0.019 |
picks | -0.018 |
Token | long |
Token ID | 890 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
pasta | +0.005 |
sandwich | +0.005 |
ice | +0.005 |
necklace | +0.004 |
card | +0.004 |
Neg logit contributions | |
Wendy | -0.007 |
stretched | -0.007 |
Bet | -0.007 |
June | -0.007 |
forward | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
endant | +0.021 |
puts | +0.020 |
pasta | +0.020 |
ice | +0.019 |
picks | +0.019 |
Neg logit contributions | |
forward | -0.026 |
Wendy | -0.025 |
mate | -0.025 |
Bet | -0.025 |
lot | -0.024 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.014 |
pasta | +0.014 |
ice | +0.013 |
picks | +0.013 |
Neg logit contributions | |
Wendy | -0.015 |
Bet | -0.015 |
lot | -0.015 |
mate | -0.015 |
June | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
endant | +0.095 |
puts | +0.091 |
pasta | +0.090 |
ice | +0.087 |
picks | +0.086 |
Neg logit contributions | |
forward | -0.072 |
lot | -0.070 |
Wendy | -0.070 |
mate | -0.067 |
Bet | -0.066 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
picks | +0.003 |
dumps | +0.003 |
pasta | +0.003 |
Neg logit contributions | |
mate | -0.003 |
forward | -0.003 |
lot | -0.003 |
stretched | -0.003 |
often | -0.003 |
Token | listened |
Token ID | 16399 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
picks | -0.002 |
dumps | -0.002 |
Token | carefully |
Token ID | 7773 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
puts | +0.000 |
picks | +0.000 |
endant | +0.000 |
pasta | +0.000 |
ice | +0.000 |
Neg logit contributions | |
mate | -0.000 |
Bet | -0.000 |
Wendy | -0.000 |
Monkey | -0.000 |
June | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Wendy | +0.012 |
mate | +0.011 |
lot | +0.011 |
Bet | +0.011 |
forward | +0.011 |
Neg logit contributions | |
puts | -0.010 |
endant | -0.010 |
ice | -0.010 |
picks | -0.010 |
pasta | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
pasta | +0.005 |
ice | +0.005 |
endant | +0.005 |
frost | +0.005 |
puts | +0.005 |
Neg logit contributions | |
Bet | -0.006 |
June | -0.006 |
forward | -0.006 |
Wendy | -0.006 |
mate | -0.006 |
Token | scale |
Token ID | 5046 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.003 |
view | +0.003 |
dumps | +0.003 |
picks | +0.003 |
Neg logit contributions | |
lot | -0.006 |
forward | -0.006 |
mate | -0.006 |
often | -0.005 |
Monkey | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Wendy | +0.001 |
lot | +0.001 |
Bet | +0.001 |
mate | +0.001 |
June | +0.001 |
Neg logit contributions | |
endant | -0.001 |
pasta | -0.001 |
ice | -0.001 |
puts | -0.001 |
sandwich | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
ice | +0.008 |
pasta | +0.008 |
sandwich | +0.008 |
necklace | +0.008 |
endant | +0.008 |
Neg logit contributions | |
Wendy | -0.010 |
forward | -0.010 |
Bet | -0.010 |
June | -0.010 |
June | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
endant | +0.023 |
puts | +0.021 |
pasta | +0.020 |
dumps | +0.020 |
picks | +0.020 |
Neg logit contributions | |
forward | -0.020 |
lot | -0.019 |
Wendy | -0.019 |
mate | -0.019 |
Monkey | -0.018 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.013 |
pasta | +0.013 |
ice | +0.012 |
picks | +0.012 |
Neg logit contributions | |
lot | -0.013 |
Wendy | -0.012 |
forward | -0.012 |
mate | -0.012 |
Bet | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
endant | +0.096 |
puts | +0.090 |
pasta | +0.089 |
ice | +0.087 |
picks | +0.085 |
Neg logit contributions | |
forward | -0.071 |
lot | -0.070 |
Wendy | -0.070 |
mate | -0.067 |
Monkey | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.001 |
pasta | +0.001 |
picks | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
often | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.003 |
pasta | +0.003 |
dumps | +0.003 |
frost | +0.003 |
Neg logit contributions | |
lot | -0.002 |
forward | -0.002 |
Wendy | -0.002 |
mate | -0.002 |
often | -0.002 |
Token | As |
Token ID | 1722 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
ice | +0.002 |
view | +0.002 |
Neg logit contributions | |
forward | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
mate | -0.001 |
Monkey | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
mate | +0.006 |
forward | +0.006 |
June | +0.006 |
stretched | +0.006 |
Charl | +0.006 |
Neg logit contributions | |
ice | -0.004 |
pasta | -0.003 |
oy | -0.003 |
buried | -0.003 |
sand | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.010 |
mate | +0.009 |
Wendy | +0.009 |
often | +0.009 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
pasta | -0.009 |
dumps | -0.009 |
picks | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
forward | +0.014 |
lot | +0.014 |
mate | +0.013 |
Wendy | +0.013 |
often | +0.013 |
Neg logit contributions | |
endant | -0.012 |
puts | -0.010 |
pasta | -0.010 |
dumps | -0.010 |
picks | -0.010 |
Token | here |
Token ID | 994 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
mate | +0.004 |
forward | +0.004 |
lot | +0.004 |
Wendy | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
ice | -0.004 |
frost | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Wendy | +0.009 |
mate | +0.009 |
Bet | +0.009 |
Monkey | +0.008 |
June | +0.008 |
Neg logit contributions | |
pasta | -0.009 |
ice | -0.009 |
puts | -0.009 |
endant | -0.009 |
picks | -0.008 |
Token | minute |
Token ID | 5664 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
forward | +0.000 |
Wendy | +0.000 |
stretched | +0.000 |
June | +0.000 |
mate | +0.000 |
Neg logit contributions | |
ice | -0.000 |
pasta | -0.000 |
sandwich | -0.000 |
endant | -0.000 |
envelope | -0.000 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
mate | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
ice | -0.002 |
picks | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
endant | +0.106 |
puts | +0.100 |
pasta | +0.097 |
dumps | +0.095 |
picks | +0.095 |
Neg logit contributions | |
forward | -0.061 |
lot | -0.060 |
Wendy | -0.057 |
mate | -0.057 |
Monkey | -0.054 |
Token | He |
Token ID | 679 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
forward | +0.005 |
lot | +0.005 |
mate | +0.004 |
Wendy | +0.004 |
often | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
dumps | -0.005 |
picks | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
forward | +0.008 |
lot | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
Monkey | +0.008 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.007 |
pasta | -0.007 |
dumps | -0.007 |
picks | -0.007 |
Token | chasing |
Token ID | 20023 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
mate | +0.003 |
lot | +0.003 |
Bet | +0.003 |
Wendy | +0.003 |
forward | +0.003 |
Neg logit contributions | |
puts | -0.003 |
ice | -0.003 |
pasta | -0.003 |
endant | -0.003 |
picks | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
pasta | +0.001 |
ice | +0.001 |
picks | +0.001 |
Neg logit contributions | |
forward | -0.001 |
lot | -0.001 |
known | -0.001 |
mate | -0.001 |
Wendy | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
forward | +0.010 |
mate | +0.009 |
lot | +0.009 |
Wendy | +0.009 |
Bet | +0.008 |
Neg logit contributions | |
puts | -0.013 |
endant | -0.012 |
pasta | -0.012 |
ice | -0.012 |
picks | -0.011 |
Token | ship |
Token ID | 4074 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
endant | +0.002 |
pasta | +0.002 |
ice | +0.002 |
puts | +0.002 |
envelope | +0.002 |
Neg logit contributions | |
Wendy | -0.003 |
forward | -0.003 |
mate | -0.003 |
Bet | -0.003 |
June | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
pasta | +0.007 |
dumps | +0.007 |
picks | +0.007 |
Neg logit contributions | |
forward | -0.007 |
lot | -0.006 |
mate | -0.006 |
Wendy | -0.006 |
often | -0.006 |
Token | wrecked |
Token ID | 44770 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
endant | +0.013 |
puts | +0.012 |
pasta | +0.011 |
ice | +0.011 |
dumps | +0.011 |
Neg logit contributions | |
forward | -0.014 |
lot | -0.014 |
Wendy | -0.014 |
mate | -0.014 |
Monkey | -0.013 |
Token | long |
Token ID | 890 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
Wendy | +0.010 |
forward | +0.010 |
lot | +0.010 |
mate | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
endant | -0.009 |
pasta | -0.008 |
puts | -0.008 |
ice | -0.008 |
dumps | -0.008 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.010 |
pasta | +0.010 |
dumps | +0.009 |
picks | +0.009 |
Neg logit contributions | |
lot | -0.016 |
forward | -0.016 |
mate | -0.016 |
Wendy | -0.016 |
often | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
endant | +0.101 |
puts | +0.094 |
pasta | +0.092 |
ice | +0.089 |
dumps | +0.089 |
Neg logit contributions | |
forward | -0.066 |
lot | -0.065 |
Wendy | -0.063 |
mate | -0.062 |
Monkey | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
forward | +0.015 |
mate | +0.015 |
Wendy | +0.014 |
lot | +0.014 |
Monkey | +0.013 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.015 |
pasta | -0.014 |
ice | -0.014 |
picks | -0.014 |
Token | now |
Token ID | 783 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
forward | +0.004 |
mate | +0.004 |
Bet | +0.004 |
lot | +0.004 |
Wendy | +0.004 |
Neg logit contributions | |
puts | -0.004 |
ice | -0.004 |
pasta | -0.004 |
endant | -0.004 |
picks | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
forward | +0.008 |
Bet | +0.008 |
mate | +0.008 |
lot | +0.008 |
Wendy | +0.008 |
Neg logit contributions | |
puts | -0.010 |
ice | -0.009 |
endant | -0.009 |
pasta | -0.009 |
picks | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
endant | +0.017 |
puts | +0.016 |
pasta | +0.015 |
dumps | +0.015 |
picks | +0.015 |
Neg logit contributions | |
forward | -0.014 |
lot | -0.014 |
mate | -0.014 |
Wendy | -0.014 |
Monkey | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
puts | +0.013 |
ice | +0.013 |
endant | +0.013 |
picks | +0.013 |
pasta | +0.013 |
Neg logit contributions | |
known | -0.014 |
Bet | -0.013 |
June | -0.013 |
lot | -0.012 |
Monkey | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ice | +0.014 |
puts | +0.013 |
pasta | +0.012 |
endant | +0.012 |
oy | +0.012 |
Neg logit contributions | |
forward | -0.014 |
Bet | -0.013 |
mate | -0.013 |
June | -0.013 |
lot | -0.013 |
Token | rocks |
Token ID | 12586 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
forward | +0.012 |
Wendy | +0.012 |
mate | +0.012 |
Bet | +0.012 |
often | +0.012 |
Neg logit contributions | |
endant | -0.008 |
pasta | -0.007 |
ice | -0.007 |
puts | -0.007 |
dumps | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
endant | +0.009 |
ice | +0.009 |
puts | +0.009 |
pasta | +0.008 |
picks | +0.008 |
Neg logit contributions | |
lot | -0.008 |
known | -0.008 |
June | -0.008 |
Monkey | -0.008 |
Bet | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
ice | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.004 |
lot | -0.004 |
mate | -0.004 |
Wendy | -0.004 |
often | -0.004 |
Token | seaw |
Token ID | 32085 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
forward | +0.002 |
Wendy | +0.002 |
mate | +0.002 |
lot | +0.002 |
often | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.001 |
pasta | -0.001 |
ice | -0.001 |
dumps | -0.001 |
Token | eed |
Token ID | 2308 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
endant | +0.050 |
puts | +0.043 |
pasta | +0.040 |
dumps | +0.039 |
view | +0.038 |
Neg logit contributions | |
lot | -0.117 |
forward | -0.116 |
mate | -0.114 |
Wendy | -0.112 |
often | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
endant | +0.042 |
puts | +0.039 |
pasta | +0.039 |
ice | +0.038 |
picks | +0.038 |
Neg logit contributions | |
lot | -0.034 |
forward | -0.034 |
Wendy | -0.033 |
Monkey | -0.032 |
Bet | -0.032 |
Token | but |
Token ID | 475 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
mate | +0.005 |
lot | +0.005 |
forward | +0.005 |
Monkey | +0.005 |
Wendy | +0.005 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
picks | -0.005 |
pasta | -0.005 |
ice | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
June | +0.002 |
mate | +0.002 |
Bet | +0.002 |
Monkey | +0.002 |
stretched | +0.002 |
Neg logit contributions | |
ice | -0.003 |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
picks | -0.002 |
Token | net |
Token ID | 2010 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
lot | +0.001 |
forward | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
view | -0.000 |
dumps | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Wendy | +0.035 |
Bet | +0.034 |
June | +0.034 |
lot | +0.034 |
mate | +0.033 |
Neg logit contributions | |
ice | -0.031 |
endant | -0.031 |
puts | -0.030 |
pasta | -0.030 |
picks | -0.029 |
Token | died |
Token ID | 3724 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
forward | +0.007 |
Wendy | +0.007 |
lot | +0.007 |
mate | +0.007 |
Bet | +0.007 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
picks | -0.006 |
ice | -0.006 |
pasta | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -2.33e-04 |
Pos logit contributions | |
Wendy | +0.016 |
lot | +0.016 |
June | +0.015 |
Bet | +0.015 |
forward | +0.015 |
Neg logit contributions | |
endant | -0.013 |
ice | -0.013 |
puts | -0.012 |
pasta | -0.012 |
finds | -0.011 |
Token | long |
Token ID | 890 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
ice | +0.000 |
sandwich | +0.000 |
necklace | +0.000 |
endant | +0.000 |
pasta | +0.000 |
Neg logit contributions | |
Wendy | -0.000 |
forward | -0.000 |
June | -0.000 |
June | -0.000 |
Bet | -0.000 |
Token | time |
Token ID | 640 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
endant | +0.021 |
puts | +0.020 |
ice | +0.019 |
pasta | +0.019 |
picks | +0.019 |
Neg logit contributions | |
forward | -0.024 |
Wendy | -0.023 |
mate | -0.022 |
lot | -0.022 |
Bet | -0.022 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.007 |
pasta | +0.006 |
picks | +0.006 |
ice | +0.006 |
Neg logit contributions | |
Wendy | -0.007 |
lot | -0.007 |
mate | -0.007 |
forward | -0.007 |
Monkey | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
endant | +0.099 |
puts | +0.093 |
pasta | +0.091 |
ice | +0.089 |
picks | +0.089 |
Neg logit contributions | |
forward | -0.068 |
lot | -0.066 |
Wendy | -0.065 |
mate | -0.063 |
Monkey | -0.061 |
Token | It |
Token ID | 632 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
pasta | +0.003 |
ice | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.003 |
mate | -0.003 |
lot | -0.003 |
often | -0.003 |
stretched | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
picks | -0.004 |
dumps | -0.004 |
pasta | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
mate | +0.002 |
forward | +0.002 |
Wendy | +0.002 |
lot | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.002 |
ice | -0.001 |
puts | -0.001 |
pasta | -0.001 |
frost | -0.001 |
Token | alive |
Token ID | 6776 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.011 |
ice | +0.010 |
pasta | +0.010 |
picks | +0.010 |
Neg logit contributions | |
mate | -0.011 |
forward | -0.011 |
Wendy | -0.011 |
lot | -0.011 |
Bet | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
mate | +0.006 |
June | +0.006 |
June | +0.006 |
forward | +0.006 |
Bet | +0.005 |
Neg logit contributions | |
ice | -0.006 |
pasta | -0.006 |
oy | -0.005 |
endant | -0.005 |
puts | -0.005 |
Token | arrived |
Token ID | 5284 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.009 |
mate | +0.008 |
Wendy | +0.008 |
Monkey | +0.008 |
Neg logit contributions | |
endant | -0.011 |
puts | -0.010 |
pasta | -0.010 |
dumps | -0.009 |
picks | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
lot | +0.009 |
mate | +0.009 |
Monkey | +0.009 |
Bet | +0.008 |
forward | +0.008 |
Neg logit contributions | |
endant | -0.014 |
puts | -0.013 |
pasta | -0.013 |
ice | -0.013 |
picks | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
pasta | +0.007 |
ice | +0.007 |
picks | +0.007 |
Neg logit contributions | |
mate | -0.012 |
lot | -0.012 |
Wendy | -0.012 |
forward | -0.012 |
Monkey | -0.012 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
endant | +0.008 |
ice | +0.008 |
pasta | +0.008 |
puts | +0.008 |
frost | +0.008 |
Neg logit contributions | |
forward | -0.008 |
mate | -0.008 |
lot | -0.007 |
often | -0.007 |
Wendy | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
forward | +0.005 |
lot | +0.005 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.011 |
puts | -0.010 |
pasta | -0.010 |
ice | -0.010 |
dumps | -0.010 |
Token | other |
Token ID | 584 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
lot | +0.050 |
forward | +0.049 |
Wendy | +0.047 |
mate | +0.047 |
often | +0.046 |
Neg logit contributions | |
endant | -0.044 |
puts | -0.040 |
pasta | -0.038 |
dumps | -0.038 |
picks | -0.037 |
Token | children |
Token ID | 1751 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
lot | +0.030 |
forward | +0.030 |
Wendy | +0.029 |
mate | +0.028 |
often | +0.028 |
Neg logit contributions | |
endant | -0.019 |
puts | -0.017 |
pasta | -0.016 |
dumps | -0.016 |
view | -0.015 |
Token | sliding |
Token ID | 22292 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.007 |
pasta | +0.007 |
dumps | +0.007 |
view | +0.007 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.005 |
Wendy | -0.005 |
mate | -0.005 |
often | -0.005 |
Token | down |
Token ID | 866 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
endant | +0.002 |
ice | +0.002 |
puts | +0.002 |
dumps | +0.002 |
pasta | +0.002 |
Neg logit contributions | |
mate | -0.002 |
Bet | -0.002 |
lot | -0.002 |
Monkey | -0.002 |
forward | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ice | +0.008 |
pasta | +0.006 |
puts | +0.006 |
picks | +0.006 |
dumps | +0.006 |
Neg logit contributions | |
June | -0.012 |
mate | -0.012 |
rarely | -0.012 |
Monkey | -0.012 |
Bet | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
forward | +0.014 |
Bet | +0.014 |
lot | +0.014 |
June | +0.013 |
stretched | +0.013 |
Neg logit contributions | |
puts | -0.012 |
ice | -0.011 |
pasta | -0.011 |
picks | -0.010 |
endant | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
puts | +0.004 |
picks | +0.004 |
pasta | +0.004 |
ice | +0.004 |
endant | +0.004 |
Neg logit contributions | |
mate | -0.004 |
Monkey | -0.004 |
Bet | -0.004 |
June | -0.004 |
forward | -0.004 |
Token | don |
Token ID | 836 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
mate | +0.006 |
forward | +0.006 |
June | +0.006 |
Bet | +0.006 |
Wendy | +0.005 |
Neg logit contributions | |
puts | -0.004 |
endant | -0.004 |
picks | -0.004 |
says | -0.004 |
finds | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.006 |
Wendy | +0.005 |
known | +0.005 |
Neg logit contributions | |
puts | -0.018 |
endant | -0.018 |
picks | -0.018 |
ice | -0.018 |
dumps | -0.017 |
Token | € |
Token ID | 26391 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.002 |
lot | +0.002 |
Wendy | +0.002 |
often | +0.002 |
Neg logit contributions | |
endant | -0.002 |
pasta | -0.002 |
puts | -0.002 |
dumps | -0.002 |
frost | -0.002 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
lot | +0.004 |
mate | +0.004 |
forward | +0.004 |
stretched | +0.004 |
often | +0.004 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
aj | -0.003 |
picks | -0.003 |
sandwich | -0.003 |
Token | t |
Token ID | 83 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
lot | +0.044 |
Ally | +0.043 |
rarely | +0.042 |
June | +0.042 |
June | +0.042 |
Neg logit contributions | |
endant | -0.043 |
emon | -0.040 |
view | -0.040 |
izza | -0.040 |
v | -0.039 |
Token | have |
Token ID | 423 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.003 |
lot | +0.003 |
Wendy | +0.003 |
Bet | +0.003 |
Neg logit contributions | |
puts | -0.001 |
endant | -0.001 |
picks | -0.001 |
ice | -0.001 |
view | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
ice | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
lot | -0.002 |
Wendy | -0.002 |
Bet | -0.002 |
Token | be |
Token ID | 307 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
puts | +0.007 |
endant | +0.007 |
ice | +0.006 |
picks | +0.006 |
pasta | +0.006 |
Neg logit contributions | |
forward | -0.012 |
lot | -0.012 |
mate | -0.012 |
Wendy | -0.012 |
Monkey | -0.011 |
Token | scared |
Token ID | 12008 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
puts | +0.008 |
picks | +0.007 |
finds | +0.007 |
ice | +0.007 |
endant | +0.006 |
Neg logit contributions | |
mate | -0.009 |
lot | -0.009 |
Monkey | -0.009 |
Bet | -0.008 |
� | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
endant | +0.018 |
puts | +0.017 |
pasta | +0.016 |
dumps | +0.016 |
picks | +0.016 |
Neg logit contributions | |
forward | -0.015 |
lot | -0.014 |
mate | -0.014 |
Wendy | -0.014 |
often | -0.013 |
Token | tree |
Token ID | 5509 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
lot | +0.005 |
forward | +0.004 |
often | +0.004 |
Wendy | +0.004 |
mate | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
dumps | -0.005 |
view | -0.005 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
picks | +0.001 |
ice | +0.001 |
pasta | +0.001 |
Neg logit contributions | |
forward | -0.001 |
lot | -0.001 |
mate | -0.001 |
Wendy | -0.001 |
Bet | -0.001 |
Token | â |
Token ID | 22940 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
forward | +0.011 |
lot | +0.010 |
mate | +0.010 |
Wendy | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
endant | -0.039 |
puts | -0.038 |
ice | -0.037 |
picks | -0.036 |
pasta | -0.036 |
Token | € |
Token ID | 26391 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
endant | +0.003 |
pasta | +0.003 |
forks | +0.002 |
dumps | +0.002 |
puts | +0.002 |
Neg logit contributions | |
forward | -0.003 |
mate | -0.003 |
Wendy | -0.003 |
lot | -0.003 |
Monkey | -0.002 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
forward | +0.004 |
mate | +0.004 |
lot | +0.004 |
stretched | +0.004 |
Wendy | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
picks | -0.004 |
pasta | -0.004 |
sandwich | -0.004 |
Token | t |
Token ID | 83 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
lot | +0.044 |
rarely | +0.042 |
Ally | +0.042 |
June | +0.041 |
Misty | +0.041 |
Neg logit contributions | |
endant | -0.045 |
view | -0.042 |
emon | -0.040 |
ice | -0.040 |
inner | -0.040 |
Token | respond |
Token ID | 3031 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
picks | -0.001 |
ice | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Bet | +0.012 |
lot | +0.011 |
June | +0.011 |
Monkey | +0.011 |
known | +0.011 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.009 |
ice | -0.008 |
picks | -0.008 |
pasta | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
mate | +0.001 |
lot | +0.001 |
forward | +0.001 |
Bet | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
ice | -0.001 |
picks | -0.001 |
pasta | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ice | +0.013 |
puts | +0.013 |
says | +0.012 |
oy | +0.012 |
pasta | +0.011 |
Neg logit contributions | |
mate | -0.017 |
forward | -0.016 |
June | -0.016 |
Bet | -0.015 |
Monkey | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
puts | +0.000 |
ice | +0.000 |
endant | +0.000 |
pasta | +0.000 |
picks | +0.000 |
Neg logit contributions | |
Bet | -0.000 |
lot | -0.000 |
mate | -0.000 |
June | -0.000 |
Monkey | -0.000 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
puts | +0.001 |
endant | +0.001 |
ice | +0.001 |
picks | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
Bet | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
forward | +0.014 |
lot | +0.014 |
mate | +0.014 |
Wendy | +0.013 |
often | +0.012 |
Neg logit contributions | |
endant | -0.055 |
puts | -0.053 |
ice | -0.051 |
dumps | -0.051 |
pasta | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
ice | -0.001 |
picks | -0.001 |
Token | scary |
Token ID | 14343 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Bet | +0.023 |
forward | +0.022 |
known | +0.022 |
stretched | +0.022 |
June | +0.021 |
Neg logit contributions | |
ice | -0.020 |
mess | -0.018 |
puts | -0.018 |
boo | -0.018 |
necklace | -0.018 |
Token | ghost |
Token ID | 10905 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
forward | +0.014 |
Bet | +0.013 |
known | +0.013 |
lot | +0.013 |
Wendy | +0.013 |
Neg logit contributions | |
puts | -0.014 |
ice | -0.014 |
endant | -0.014 |
pasta | -0.014 |
sandwich | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
forward | +0.044 |
lot | +0.044 |
known | +0.043 |
Bet | +0.043 |
stretched | +0.042 |
Neg logit contributions | |
ice | -0.047 |
puts | -0.047 |
endant | -0.045 |
sandwich | -0.045 |
necklace | -0.044 |
Token | it |
Token ID | 340 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
forward | +0.007 |
mate | +0.007 |
known | +0.007 |
lot | +0.007 |
Monkey | +0.007 |
Neg logit contributions | |
ice | -0.008 |
puts | -0.008 |
endant | -0.008 |
pasta | -0.008 |
picks | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
puts | +0.007 |
endant | +0.006 |
picks | +0.006 |
ice | +0.006 |
finds | +0.006 |
Neg logit contributions | |
forward | -0.010 |
mate | -0.009 |
lot | -0.009 |
Wendy | -0.009 |
Monkey | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
mate | +0.004 |
forward | +0.004 |
lot | +0.004 |
Bet | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
ice | -0.004 |
endant | -0.004 |
puts | -0.004 |
pasta | -0.003 |
frost | -0.003 |
Token | friendly |
Token ID | 8030 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
forward | +0.008 |
Bet | +0.007 |
Wendy | +0.007 |
known | +0.007 |
June | +0.007 |
Neg logit contributions | |
ice | -0.006 |
necklace | -0.006 |
boo | -0.006 |
endant | -0.005 |
mess | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
mate | +0.002 |
Wendy | +0.002 |
lot | +0.002 |
forward | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
ice | -0.002 |
pasta | -0.002 |
dumps | -0.002 |
Token | out |
Token ID | 503 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
puts | +0.010 |
endant | +0.010 |
ice | +0.010 |
pasta | +0.010 |
dumps | +0.009 |
Neg logit contributions | |
Wendy | -0.008 |
Bet | -0.008 |
Monkey | -0.008 |
lot | -0.008 |
mate | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
mate | +0.015 |
Wendy | +0.015 |
Bet | +0.015 |
June | +0.014 |
Monkey | +0.014 |
Neg logit contributions | |
endant | -0.021 |
puts | -0.020 |
pasta | -0.020 |
ice | -0.020 |
dumps | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
forward | +0.005 |
mate | +0.005 |
Wendy | +0.004 |
lot | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
pasta | -0.003 |
ice | -0.003 |
dumps | -0.003 |
Token | kinds |
Token ID | 6982 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
forward | +0.012 |
lot | +0.012 |
mate | +0.012 |
Wendy | +0.012 |
Monkey | +0.012 |
Neg logit contributions | |
endant | -0.018 |
puts | -0.017 |
pasta | -0.016 |
dumps | -0.016 |
ice | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Wendy | +0.002 |
lot | +0.002 |
mate | +0.002 |
forward | +0.002 |
Bet | +0.002 |
Neg logit contributions | |
endant | -0.003 |
pasta | -0.003 |
puts | -0.003 |
ice | -0.003 |
picks | -0.002 |
Token | tasty |
Token ID | 25103 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
lot | +0.046 |
often | +0.042 |
forward | +0.042 |
Wendy | +0.039 |
mate | +0.037 |
Neg logit contributions | |
endant | -0.047 |
puts | -0.039 |
view | -0.039 |
Ta | -0.039 |
dumps | -0.039 |
Token | foods |
Token ID | 9013 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
endant | +0.001 |
view | +0.001 |
Ta | +0.001 |
puts | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
lot | -0.001 |
forward | -0.001 |
often | -0.001 |
Wendy | -0.001 |
Monkey | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
endant | +0.005 |
pasta | +0.005 |
ice | +0.005 |
puts | +0.005 |
frost | +0.005 |
Neg logit contributions | |
mate | -0.005 |
Wendy | -0.005 |
lot | -0.005 |
Bet | -0.005 |
June | -0.005 |
Token | like |
Token ID | 588 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.003 |
lot | +0.003 |
Wendy | +0.003 |
Monkey | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
pasta | -0.003 |
ice | -0.003 |
dumps | -0.003 |
Token | fruits |
Token ID | 15921 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
endant | +0.013 |
pasta | +0.012 |
ice | +0.012 |
puts | +0.012 |
frost | +0.011 |
Neg logit contributions | |
forward | -0.016 |
mate | -0.016 |
Wendy | -0.015 |
Bet | -0.015 |
June | -0.015 |
Token | held |
Token ID | 2714 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
forward | +0.011 |
mate | +0.010 |
lot | +0.010 |
Wendy | +0.010 |
Monkey | +0.010 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.008 |
ice | -0.008 |
picks | -0.008 |
pasta | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
puts | +0.015 |
endant | +0.015 |
picks | +0.015 |
ice | +0.014 |
pasta | +0.014 |
Neg logit contributions | |
often | -0.015 |
Bet | -0.015 |
mate | -0.015 |
rarely | -0.015 |
known | -0.015 |
Token | breath |
Token ID | 8033 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
endant | +0.019 |
puts | +0.018 |
pasta | +0.017 |
dumps | +0.017 |
view | +0.016 |
Neg logit contributions | |
lot | -0.023 |
forward | -0.023 |
mate | -0.022 |
Wendy | -0.022 |
often | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
mate | +0.002 |
Monkey | +0.002 |
Bet | +0.002 |
Wendy | +0.002 |
lot | +0.002 |
Neg logit contributions | |
endant | -0.001 |
ice | -0.001 |
pasta | -0.001 |
puts | -0.001 |
picks | -0.001 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
mate | +0.001 |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
Neg logit contributions | |
puts | -0.001 |
endant | -0.001 |
ice | -0.001 |
picks | -0.001 |
pasta | -0.001 |
Token | around |
Token ID | 1088 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
endant | +0.023 |
puts | +0.021 |
picks | +0.020 |
pasta | +0.020 |
dumps | +0.020 |
Neg logit contributions | |
mate | -0.030 |
Monkey | -0.029 |
Bet | -0.029 |
Wendy | -0.028 |
lot | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
pasta | +0.004 |
ice | +0.004 |
picks | +0.004 |
puts | +0.004 |
endant | +0.003 |
Neg logit contributions | |
mate | -0.004 |
Bet | -0.004 |
Wendy | -0.004 |
Monkey | -0.004 |
lot | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ice | +0.014 |
pasta | +0.013 |
endant | +0.012 |
puts | +0.012 |
frost | +0.012 |
Neg logit contributions | |
mate | -0.017 |
forward | -0.017 |
Bet | -0.017 |
Wendy | -0.016 |
Monkey | -0.016 |
Token | answer |
Token ID | 3280 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
forward | +0.003 |
Wendy | +0.003 |
mate | +0.003 |
Bet | +0.003 |
lot | +0.003 |
Neg logit contributions | |
endant | -0.002 |
ice | -0.002 |
pasta | -0.002 |
puts | -0.002 |
picks | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
endant | +0.007 |
ice | +0.006 |
pasta | +0.006 |
puts | +0.006 |
envelope | +0.006 |
Neg logit contributions | |
lot | -0.007 |
Bet | -0.007 |
known | -0.007 |
Wendy | -0.007 |
Monkey | -0.007 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
picks | +0.005 |
pasta | +0.005 |
dumps | +0.005 |
Neg logit contributions | |
mate | -0.004 |
forward | -0.004 |
lot | -0.004 |
often | -0.004 |
Wendy | -0.004 |
Token | age |
Token ID | 496 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
lot | +0.020 |
forward | +0.020 |
Wendy | +0.020 |
mate | +0.019 |
Monkey | +0.019 |
Neg logit contributions | |
endant | -0.026 |
puts | -0.024 |
pasta | -0.024 |
ice | -0.023 |
view | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
lot | +0.032 |
Wendy | +0.031 |
Monkey | +0.030 |
Bet | +0.030 |
mate | +0.030 |
Neg logit contributions | |
endant | -0.026 |
ice | -0.024 |
puts | -0.024 |
pasta | -0.023 |
view | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
forward | +0.002 |
June | +0.002 |
stretched | +0.002 |
mate | +0.002 |
known | +0.001 |
Neg logit contributions | |
ice | -0.001 |
pasta | -0.001 |
bread | -0.001 |
oy | -0.001 |
frost | -0.001 |
Token | neck |
Token ID | 7393 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
dumps | +0.008 |
pasta | +0.008 |
ws | +0.008 |
Neg logit contributions | |
lot | -0.015 |
forward | -0.014 |
mate | -0.014 |
often | -0.014 |
Wendy | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Wendy | +0.012 |
forward | +0.012 |
mate | +0.012 |
lot | +0.012 |
Monkey | +0.012 |
Neg logit contributions | |
endant | -0.014 |
ice | -0.013 |
puts | -0.012 |
pasta | -0.012 |
view | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.005 |
ice | +0.005 |
picks | +0.005 |
Neg logit contributions | |
mate | -0.005 |
forward | -0.005 |
lot | -0.004 |
June | -0.004 |
often | -0.004 |
Token | next |
Token ID | 1306 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
lot | +0.001 |
forward | +0.001 |
mate | +0.001 |
Wendy | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
dumps | -0.001 |
picks | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.010 |
pasta | +0.009 |
dumps | +0.009 |
picks | +0.009 |
Neg logit contributions | |
lot | -0.008 |
forward | -0.008 |
mate | -0.007 |
Wendy | -0.007 |
often | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
puts | +0.005 |
ice | +0.005 |
endant | +0.005 |
picks | +0.005 |
pasta | +0.005 |
Neg logit contributions | |
mate | -0.004 |
June | -0.003 |
June | -0.003 |
Bet | -0.003 |
forward | -0.003 |
Token | D |
Token ID | 360 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
mate | +0.001 |
June | +0.001 |
forward | +0.001 |
stretched | +0.001 |
June | +0.001 |
Neg logit contributions | |
ice | -0.001 |
puts | -0.001 |
pasta | -0.001 |
endant | -0.001 |
oy | -0.001 |
Token | ucky |
Token ID | 5309 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
endant | +0.022 |
puts | +0.020 |
pasta | +0.020 |
dumps | +0.019 |
view | +0.019 |
Neg logit contributions | |
forward | -0.022 |
lot | -0.022 |
Wendy | -0.021 |
mate | -0.021 |
often | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
endant | +0.024 |
pasta | +0.023 |
puts | +0.023 |
ice | +0.022 |
sandwich | +0.022 |
Neg logit contributions | |
forward | -0.021 |
Wendy | -0.021 |
lot | -0.021 |
Bet | -0.021 |
mate | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
forward | +0.008 |
known | +0.008 |
mate | +0.008 |
often | +0.007 |
Bet | +0.007 |
Neg logit contributions | |
puts | -0.005 |
ice | -0.005 |
endant | -0.005 |
picks | -0.005 |
dumps | -0.005 |
Token | pulled |
Token ID | 5954 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
forward | +0.010 |
mate | +0.009 |
Wendy | +0.009 |
Bet | +0.009 |
lot | +0.009 |
Neg logit contributions | |
puts | -0.007 |
endant | -0.006 |
picks | -0.006 |
ice | -0.006 |
dumps | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
known | +0.011 |
rarely | +0.011 |
often | +0.011 |
Bet | +0.011 |
mate | +0.011 |
Neg logit contributions | |
ice | -0.010 |
puts | -0.010 |
picks | -0.010 |
pasta | -0.009 |
dumps | -0.009 |
Token | dress |
Token ID | 6576 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
forward | +0.003 |
lot | +0.003 |
mate | +0.003 |
Wendy | +0.003 |
often | +0.003 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
picks | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
known | +0.020 |
Bet | +0.020 |
Monkey | +0.020 |
June | +0.020 |
Wendy | +0.019 |
Neg logit contributions | |
endant | -0.017 |
ice | -0.017 |
puts | -0.016 |
necklace | -0.015 |
sandwich | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
mate | +0.011 |
Bet | +0.011 |
Monkey | +0.010 |
often | +0.010 |
June | +0.010 |
Neg logit contributions | |
ice | -0.010 |
pasta | -0.009 |
puts | -0.009 |
endant | -0.009 |
frost | -0.009 |
Token | teeth |
Token ID | 9941 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
endant | +0.013 |
puts | +0.011 |
pasta | +0.011 |
dumps | +0.011 |
picks | +0.011 |
Neg logit contributions | |
forward | -0.019 |
lot | -0.018 |
mate | -0.018 |
Wendy | -0.018 |
often | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
endant | +0.001 |
ice | +0.001 |
puts | +0.001 |
pasta | +0.001 |
picks | +0.001 |
Neg logit contributions | |
Wendy | -0.001 |
mate | -0.001 |
lot | -0.001 |
Bet | -0.001 |
Monkey | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
forward | +0.003 |
mate | +0.003 |
known | +0.003 |
often | +0.003 |
lot | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
ice | -0.003 |
pasta | -0.003 |
dumps | -0.003 |
Token | tried |
Token ID | 3088 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
forward | +0.006 |
mate | +0.006 |
lot | +0.006 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
picks | -0.004 |
pasta | -0.004 |
dumps | -0.004 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
mate | +0.014 |
lot | +0.013 |
Monkey | +0.013 |
forward | +0.013 |
Wendy | +0.013 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.015 |
ice | -0.014 |
picks | -0.014 |
pasta | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
forward | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
Monkey | +0.001 |
mate | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
ice | -0.001 |
dumps | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
forward | +0.011 |
mate | +0.010 |
Bet | +0.009 |
Monkey | +0.009 |
lot | +0.009 |
Neg logit contributions | |
endant | -0.015 |
puts | -0.015 |
ice | -0.015 |
pasta | -0.015 |
frost | -0.014 |
Token | hoop |
Token ID | 44792 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
endant | +0.006 |
pasta | +0.005 |
puts | +0.005 |
picks | +0.005 |
shirts | +0.005 |
Neg logit contributions | |
forward | -0.010 |
Bet | -0.010 |
known | -0.010 |
mate | -0.010 |
Monkey | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
endant | +0.005 |
pasta | +0.005 |
ice | +0.005 |
puts | +0.005 |
sandwich | +0.005 |
Neg logit contributions | |
Bet | -0.006 |
Wendy | -0.006 |
known | -0.005 |
lot | -0.005 |
Ally | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
puts | +0.002 |
ice | +0.002 |
endant | +0.002 |
pasta | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.002 |
Monkey | -0.002 |
mate | -0.002 |
lot | -0.002 |
Wendy | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
lot | +0.005 |
forward | +0.005 |
Wendy | +0.005 |
mate | +0.005 |
often | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
pasta | -0.003 |
dumps | -0.003 |
picks | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | +7.77e-03 |
Pos logit contributions | |
Monkey | +0.005 |
June | +0.005 |
Wendy | +0.005 |
Boris | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
ice | -0.004 |
pasta | -0.004 |
view | -0.004 |
dig | -0.004 |
picks | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
mate | +0.000 |
forward | +0.000 |
Bet | +0.000 |
Monkey | +0.000 |
un | +0.000 |
Neg logit contributions | |
ice | -0.000 |
pasta | -0.000 |
frost | -0.000 |
endant | -0.000 |
yogurt | -0.000 |
Token | flew |
Token ID | 13112 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
endant | +0.033 |
puts | +0.031 |
pasta | +0.030 |
dumps | +0.029 |
ice | +0.029 |
Neg logit contributions | |
forward | -0.025 |
mate | -0.024 |
lot | -0.024 |
Wendy | -0.023 |
Monkey | -0.023 |
Token | off |
Token ID | 572 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
mate | +0.013 |
Monkey | +0.012 |
rarely | +0.012 |
Cop | +0.012 |
June | +0.011 |
Neg logit contributions | |
ice | -0.008 |
empty | -0.007 |
endant | -0.007 |
picks | -0.007 |
fills | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
puts | +0.001 |
endant | +0.001 |
picks | +0.001 |
ice | +0.001 |
pasta | +0.001 |
Neg logit contributions | |
forward | -0.001 |
mate | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
Monkey | -0.001 |
Token | Jack |
Token ID | 3619 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
endant | +0.005 |
pasta | +0.005 |
puts | +0.005 |
ice | +0.005 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.004 |
lot | -0.004 |
mate | -0.004 |
often | -0.004 |
Wendy | -0.004 |
Token | laughed |
Token ID | 13818 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.014 |
picks | +0.013 |
ice | +0.013 |
view | +0.012 |
Neg logit contributions | |
forward | -0.016 |
mate | -0.016 |
lot | -0.016 |
Wendy | -0.015 |
Monkey | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
ice | +0.013 |
pasta | +0.012 |
puts | +0.012 |
endant | +0.012 |
frost | +0.011 |
Neg logit contributions | |
Bet | -0.018 |
mate | -0.017 |
known | -0.017 |
June | -0.017 |
Monkey | -0.016 |
Token | laughed |
Token ID | 13818 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
mate | +0.002 |
forward | +0.002 |
lot | +0.002 |
stretched | +0.002 |
Bet | +0.002 |
Neg logit contributions | |
puts | -0.001 |
ice | -0.001 |
picks | -0.001 |
endant | -0.001 |
says | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ice | +0.013 |
pasta | +0.012 |
frost | +0.012 |
puts | +0.011 |
sandwich | +0.011 |
Neg logit contributions | |
Bet | -0.016 |
June | -0.015 |
known | -0.015 |
Monkey | -0.014 |
mate | -0.014 |
Token | enjoying |
Token ID | 13226 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
mate | +0.013 |
forward | +0.012 |
lot | +0.012 |
Monkey | +0.012 |
Wendy | +0.011 |
Neg logit contributions | |
puts | -0.010 |
endant | -0.010 |
ice | -0.010 |
picks | -0.010 |
pasta | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ice | +0.008 |
pasta | +0.007 |
puts | +0.007 |
picks | +0.007 |
frost | +0.007 |
Neg logit contributions | |
mate | -0.010 |
forward | -0.010 |
un | -0.009 |
Monkey | -0.009 |
Bet | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
lot | +0.007 |
forward | +0.007 |
often | +0.006 |
Wendy | +0.006 |
mate | +0.006 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
dumps | -0.006 |
view | -0.006 |
ws | -0.006 |
Token | together |
Token ID | 1978 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
endant | +0.014 |
pasta | +0.014 |
puts | +0.013 |
ice | +0.013 |
picks | +0.013 |
Neg logit contributions | |
mate | -0.012 |
Wendy | -0.012 |
Monkey | -0.012 |
Bet | -0.012 |
lot | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Bet | +0.023 |
June | +0.022 |
Monkey | +0.022 |
Wendy | +0.021 |
Ally | +0.021 |
Neg logit contributions | |
ice | -0.019 |
pasta | -0.019 |
puts | -0.018 |
sandwich | -0.017 |
frost | -0.017 |
Token | B |
Token ID | 33 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.005 |
dumps | +0.005 |
picks | +0.005 |
Neg logit contributions | |
forward | -0.003 |
lot | -0.002 |
mate | -0.002 |
Wendy | -0.002 |
Monkey | -0.002 |
Token | enny |
Token ID | 11870 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.009 |
pasta | +0.009 |
dumps | +0.009 |
picks | +0.009 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.006 |
mate | -0.006 |
Wendy | -0.006 |
often | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.009 |
mate | +0.009 |
Wendy | +0.009 |
Monkey | +0.008 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
picks | -0.009 |
dumps | -0.008 |
ice | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
mate | +0.002 |
lot | +0.002 |
forward | +0.002 |
Wendy | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.002 |
ice | -0.002 |
puts | -0.002 |
pasta | -0.002 |
picks | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
forward | +0.000 |
lot | +0.000 |
Wendy | +0.000 |
mate | +0.000 |
often | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
dumps | -0.000 |
picks | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
forward | +0.009 |
lot | +0.009 |
mate | +0.009 |
Wendy | +0.009 |
June | +0.008 |
Neg logit contributions | |
endant | -0.009 |
pasta | -0.009 |
puts | -0.009 |
ice | -0.009 |
picks | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
puts | +0.010 |
endant | +0.010 |
picks | +0.010 |
ice | +0.010 |
dumps | +0.009 |
Neg logit contributions | |
forward | -0.019 |
lot | -0.018 |
Wendy | -0.018 |
mate | -0.018 |
Monkey | -0.017 |
Token | saved |
Token ID | 7448 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ice | +0.011 |
endant | +0.011 |
pasta | +0.011 |
puts | +0.011 |
dig | +0.010 |
Neg logit contributions | |
lot | -0.013 |
Wendy | -0.012 |
forward | -0.012 |
mate | -0.011 |
often | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
stretched | +0.029 |
rarely | +0.028 |
June | +0.028 |
forward | +0.028 |
mate | +0.028 |
Neg logit contributions | |
ice | -0.019 |
pasta | -0.018 |
puts | -0.017 |
oy | -0.017 |
picks | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
mate | +0.003 |
forward | +0.003 |
lot | +0.003 |
known | +0.003 |
June | +0.003 |
Neg logit contributions | |
endant | -0.003 |
puts | -0.003 |
picks | -0.002 |
pasta | -0.002 |
dumps | -0.002 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
forward | +0.009 |
mate | +0.009 |
lot | +0.008 |
Wendy | +0.008 |
Monkey | +0.008 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.008 |
picks | -0.008 |
pasta | -0.008 |
ice | -0.008 |
Token | py |
Token ID | 9078 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
endant | +0.005 |
ice | +0.005 |
puts | +0.005 |
picks | +0.005 |
an | +0.005 |
Neg logit contributions | |
forward | -0.009 |
lot | -0.008 |
mate | -0.008 |
often | -0.008 |
Wendy | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
forward | +0.034 |
mate | +0.033 |
lot | +0.033 |
Wendy | +0.030 |
rarely | +0.028 |
Neg logit contributions | |
endant | -0.030 |
puts | -0.029 |
picks | -0.029 |
oy | -0.027 |
finds | -0.027 |
Token | them |
Token ID | 606 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ice | +0.015 |
puts | +0.015 |
pasta | +0.014 |
picks | +0.014 |
endant | +0.014 |
Neg logit contributions | |
forward | -0.015 |
mate | -0.013 |
lot | -0.013 |
often | -0.013 |
rarely | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
pasta | +0.006 |
ice | +0.006 |
picks | +0.006 |
Neg logit contributions | |
mate | -0.005 |
lot | -0.005 |
forward | -0.005 |
Wendy | -0.005 |
Bet | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
puts | +0.005 |
says | +0.005 |
picks | +0.005 |
ice | +0.004 |
endant | +0.004 |
Neg logit contributions | |
forward | -0.017 |
mate | -0.016 |
� | -0.014 |
stretched | -0.014 |
date | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ice | +0.025 |
pasta | +0.024 |
puts | +0.023 |
picks | +0.022 |
oy | +0.021 |
Neg logit contributions | |
forward | -0.029 |
mate | -0.029 |
stretched | -0.027 |
lot | -0.027 |
Bet | -0.027 |
Token | join |
Token ID | 4654 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
puts | +0.010 |
dig | +0.009 |
ice | +0.009 |
picks | +0.009 |
bury | +0.009 |
Neg logit contributions | |
forward | -0.015 |
Monkey | -0.013 |
Bet | -0.013 |
lot | -0.013 |
June | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
known | +0.005 |
rarely | +0.005 |
Bet | +0.005 |
lot | +0.005 |
barely | +0.005 |
Neg logit contributions | |
ice | -0.003 |
puts | -0.003 |
picks | -0.003 |
oy | -0.003 |
pasta | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Bet | +0.026 |
rarely | +0.025 |
known | +0.025 |
June | +0.025 |
mate | +0.024 |
Neg logit contributions | |
ice | -0.014 |
pasta | -0.013 |
puts | -0.012 |
wraps | -0.011 |
picks | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
mate | +0.001 |
forward | +0.001 |
lot | +0.001 |
known | +0.001 |
forever | +0.001 |
Neg logit contributions | |
puts | -0.001 |
endant | -0.001 |
ice | -0.001 |
picks | -0.001 |
dumps | -0.001 |
Token | Can |
Token ID | 6090 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
often | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
Neg logit contributions | |
puts | -0.002 |
endant | -0.002 |
Ta | -0.002 |
picks | -0.002 |
ice | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
forward | +0.004 |
lot | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.007 |
pasta | -0.007 |
dumps | -0.007 |
picks | -0.007 |
Token | secrets |
Token ID | 13141 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.003 |
pasta | +0.003 |
picks | +0.003 |
ice | +0.003 |
Neg logit contributions | |
forward | -0.005 |
Wendy | -0.005 |
mate | -0.005 |
lot | -0.005 |
Bet | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
pasta | +0.001 |
ice | +0.000 |
frost | +0.000 |
Neg logit contributions | |
Bet | -0.001 |
Wendy | -0.001 |
mate | -0.001 |
Monkey | -0.001 |
lot | -0.001 |
Token | One |
Token ID | 1881 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
forward | +0.001 |
mate | +0.001 |
lot | +0.001 |
Wendy | +0.001 |
often | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
pasta | -0.001 |
picks | -0.001 |
dumps | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
lot | +0.007 |
often | +0.006 |
forward | +0.006 |
much | +0.005 |
while | +0.005 |
Neg logit contributions | |
endant | -0.017 |
ws | -0.015 |
dumps | -0.015 |
puts | -0.015 |
picks | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
endant | +0.024 |
puts | +0.023 |
pasta | +0.023 |
ice | +0.023 |
picks | +0.022 |
Neg logit contributions | |
forward | -0.017 |
mate | -0.017 |
Bet | -0.016 |
June | -0.016 |
known | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
pasta | +0.018 |
endant | +0.017 |
ice | +0.017 |
puts | +0.017 |
frost | +0.017 |
Neg logit contributions | |
forward | -0.014 |
mate | -0.013 |
Bet | -0.012 |
known | -0.012 |
stretched | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
often | +0.006 |
lot | +0.005 |
forward | +0.005 |
soon | +0.005 |
Mitt | +0.005 |
Neg logit contributions | |
endant | -0.010 |
pasta | -0.009 |
inner | -0.008 |
ws | -0.008 |
view | -0.008 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.010 |
mate | +0.010 |
Wendy | +0.010 |
Monkey | +0.009 |
Neg logit contributions | |
endant | -0.014 |
puts | -0.013 |
pasta | -0.012 |
picks | -0.012 |
dumps | -0.012 |
Token | gr |
Token ID | 1036 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
mate | +0.003 |
Wendy | +0.003 |
lot | +0.003 |
forward | +0.003 |
Bet | +0.003 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
pasta | -0.004 |
ice | -0.004 |
dumps | -0.004 |
Token | umpy |
Token ID | 32152 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
pasta | +0.006 |
dumps | +0.006 |
view | +0.006 |
Neg logit contributions | |
forward | -0.007 |
lot | -0.007 |
mate | -0.007 |
Wendy | -0.006 |
Monkey | -0.006 |
Token | idea |
Token ID | 2126 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
dumps | +0.005 |
pasta | +0.005 |
view | +0.005 |
Neg logit contributions | |
lot | -0.008 |
forward | -0.008 |
often | -0.007 |
mate | -0.007 |
Wendy | -0.007 |
Token | ; |
Token ID | 26 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
endant | +0.033 |
puts | +0.031 |
pasta | +0.030 |
dumps | +0.029 |
picks | +0.029 |
Neg logit contributions | |
forward | -0.020 |
lot | -0.020 |
mate | -0.019 |
Wendy | -0.019 |
often | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
endant | +0.015 |
puts | +0.015 |
ice | +0.015 |
pasta | +0.014 |
picks | +0.013 |
Neg logit contributions | |
forward | -0.015 |
mate | -0.014 |
lot | -0.014 |
Wendy | -0.014 |
Bet | -0.013 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.003 |
view | +0.003 |
pasta | +0.003 |
dumps | +0.003 |
Neg logit contributions | |
lot | -0.003 |
forward | -0.002 |
often | -0.002 |
Monkey | -0.002 |
mate | -0.002 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
forward | +0.015 |
lot | +0.015 |
mate | +0.014 |
Wendy | +0.014 |
often | +0.014 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.016 |
pasta | -0.015 |
dumps | -0.015 |
picks | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
endant | +0.037 |
pasta | +0.036 |
puts | +0.036 |
ice | +0.035 |
picks | +0.033 |
Neg logit contributions | |
forward | -0.030 |
lot | -0.029 |
mate | -0.029 |
Wendy | -0.028 |
Bet | -0.026 |
Token | race |
Token ID | 3234 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
endant | +0.015 |
puts | +0.014 |
pasta | +0.013 |
dumps | +0.013 |
picks | +0.013 |
Neg logit contributions | |
forward | -0.020 |
lot | -0.020 |
mate | -0.020 |
Wendy | -0.019 |
often | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
endant | +0.001 |
ice | +0.001 |
puts | +0.001 |
pasta | +0.001 |
picks | +0.001 |
Neg logit contributions | |
Bet | -0.001 |
lot | -0.001 |
Wendy | -0.001 |
mate | -0.001 |
Monkey | -0.001 |
Token | tree |
Token ID | 5509 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
endant | +0.000 |
puts | +0.000 |
view | +0.000 |
pasta | +0.000 |
dumps | +0.000 |
Neg logit contributions | |
lot | -0.000 |
forward | -0.000 |
often | -0.000 |
mate | -0.000 |
Monkey | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
Wendy | +0.001 |
lot | +0.001 |
Bet | +0.001 |
mate | +0.001 |
June | +0.001 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
ice | -0.001 |
picks | -0.001 |
finds | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
often | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
dumps | -0.002 |
picks | -0.002 |
Token | away |
Token ID | 1497 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
mate | +0.008 |
Monkey | +0.008 |
Wendy | +0.008 |
known | +0.007 |
Bet | +0.007 |
Neg logit contributions | |
endant | -0.011 |
puts | -0.010 |
ice | -0.010 |
picks | -0.010 |
dumps | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Monkey | +0.010 |
Wendy | +0.010 |
June | +0.009 |
mate | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
ice | -0.006 |
endant | -0.006 |
puts | -0.006 |
pasta | -0.006 |
dumps | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ice | +0.009 |
puts | +0.008 |
endant | +0.008 |
pasta | +0.008 |
frost | +0.008 |
Neg logit contributions | |
forward | -0.007 |
mate | -0.006 |
Bet | -0.006 |
stretched | -0.006 |
Wendy | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.003 |
dumps | +0.003 |
ice | +0.003 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.005 |
mate | -0.005 |
Wendy | -0.005 |
often | -0.005 |
Token | rolled |
Token ID | 11686 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
puts | +0.013 |
endant | +0.013 |
picks | +0.013 |
ice | +0.012 |
finds | +0.012 |
Neg logit contributions | |
mate | -0.015 |
forward | -0.015 |
lot | -0.015 |
stretched | -0.014 |
Monkey | -0.014 |
Token | down |
Token ID | 866 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
ice | +0.001 |
picks | +0.001 |
dumps | +0.001 |
Neg logit contributions | |
mate | -0.001 |
Monkey | -0.001 |
known | -0.001 |
forward | -0.001 |
lot | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
ice | +0.007 |
puts | +0.005 |
picks | +0.005 |
pasta | +0.005 |
dumps | +0.005 |
Neg logit contributions | |
rarely | -0.012 |
mate | -0.012 |
June | -0.012 |
Monkey | -0.012 |
forward | -0.012 |
Token | hill |
Token ID | 12788 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
endant | +0.002 |
ws | +0.002 |
emon | +0.002 |
address | +0.002 |
frost | +0.002 |
Neg logit contributions | |
lot | -0.002 |
often | -0.002 |
Wendy | -0.002 |
forward | -0.002 |
Mitt | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ice | +0.006 |
dumps | +0.005 |
dig | +0.005 |
empty | +0.005 |
v | +0.005 |
Neg logit contributions | |
Wendy | -0.013 |
Bet | -0.013 |
Monkey | -0.013 |
June | -0.012 |
Fel | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
endant | +0.003 |
puts | +0.003 |
picks | +0.003 |
dumps | +0.002 |
pasta | +0.002 |
Neg logit contributions | |
forward | -0.002 |
mate | -0.002 |
lot | -0.002 |
often | -0.002 |
Monkey | -0.002 |
Token | chased |
Token ID | 26172 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
forward | +0.007 |
mate | +0.007 |
lot | +0.007 |
Wendy | +0.006 |
Monkey | +0.006 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
ice | -0.006 |
picks | -0.006 |
dumps | -0.006 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
forward | +0.010 |
lot | +0.010 |
Wendy | +0.010 |
mate | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
endant | -0.008 |
puts | -0.008 |
picks | -0.007 |
dumps | -0.007 |
ice | -0.007 |
Token | here |
Token ID | 994 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Wendy | +0.034 |
lot | +0.034 |
Monkey | +0.033 |
Bet | +0.032 |
June | +0.032 |
Neg logit contributions | |
endant | -0.019 |
pasta | -0.019 |
puts | -0.018 |
ice | -0.018 |
picks | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Wendy | +0.009 |
lot | +0.009 |
Bet | +0.009 |
Monkey | +0.009 |
mate | +0.008 |
Neg logit contributions | |
endant | -0.009 |
pasta | -0.009 |
ice | -0.008 |
puts | -0.008 |
sandwich | -0.008 |
Token | long |
Token ID | 890 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ice | +0.001 |
pasta | +0.001 |
sandwich | +0.000 |
oy | +0.000 |
endant | +0.000 |
Neg logit contributions | |
Bet | -0.001 |
stretched | -0.001 |
Wendy | -0.001 |
June | -0.001 |
forward | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
endant | +0.022 |
puts | +0.021 |
pasta | +0.021 |
ice | +0.020 |
dumps | +0.020 |
Neg logit contributions | |
forward | -0.024 |
Wendy | -0.023 |
mate | -0.023 |
Bet | -0.023 |
lot | -0.023 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
endant | +0.006 |
puts | +0.006 |
pasta | +0.006 |
ice | +0.005 |
picks | +0.005 |
Neg logit contributions | |
lot | -0.007 |
Wendy | -0.007 |
forward | -0.007 |
mate | -0.007 |
Bet | -0.007 |
Token | ." |
Token ID | 526 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
endant | +0.111 |
puts | +0.104 |
pasta | +0.102 |
dumps | +0.099 |
picks | +0.099 |
Neg logit contributions | |
forward | -0.064 |
lot | -0.063 |
Wendy | -0.060 |
mate | -0.060 |
Monkey | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
forward | +0.000 |
lot | +0.000 |
mate | +0.000 |
often | +0.000 |
stretched | +0.000 |
Neg logit contributions | |
endant | -0.000 |
puts | -0.000 |
pasta | -0.000 |
picks | -0.000 |
ice | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
picks | -0.002 |
ice | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
forward | +0.006 |
lot | +0.006 |
mate | +0.005 |
Wendy | +0.005 |
Monkey | +0.005 |
Neg logit contributions | |
endant | -0.004 |
puts | -0.004 |
view | -0.004 |
pasta | -0.004 |
ice | -0.004 |
Token | Can |
Token ID | 6090 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.004 |
ice | +0.004 |
dumps | +0.004 |
Neg logit contributions | |
forward | -0.005 |
lot | -0.004 |
Wendy | -0.004 |
mate | -0.004 |
often | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
endant | +0.001 |
puts | +0.001 |
pasta | +0.001 |
ice | +0.001 |
picks | +0.001 |
Neg logit contributions | |
lot | -0.001 |
forward | -0.001 |
Wendy | -0.001 |
mate | -0.001 |
Monkey | -0.001 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
endant | +0.011 |
puts | +0.010 |
pasta | +0.010 |
ice | +0.010 |
dumps | +0.010 |
Neg logit contributions | |
forward | -0.017 |
lot | -0.016 |
Wendy | -0.016 |
mate | -0.016 |
Monkey | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.005 |
pasta | +0.005 |
dumps | +0.005 |
ice | +0.005 |
Neg logit contributions | |
lot | -0.004 |
mate | -0.004 |
Wendy | -0.004 |
forward | -0.004 |
Monkey | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
forward | +0.012 |
Wendy | +0.012 |
mate | +0.012 |
lot | +0.011 |
Monkey | +0.011 |
Neg logit contributions | |
endant | -0.013 |
ice | -0.013 |
pasta | -0.013 |
puts | -0.013 |
view | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
pasta | +0.006 |
picks | +0.006 |
dumps | +0.006 |
Neg logit contributions | |
forward | -0.006 |
mate | -0.006 |
lot | -0.006 |
often | -0.006 |
stretched | -0.006 |
Token | oy |
Token ID | 35104 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
lot | +0.002 |
forward | +0.002 |
often | +0.002 |
mate | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.001 |
puts | -0.001 |
dumps | -0.001 |
ws | -0.001 |
view | -0.001 |
Token | ster |
Token ID | 1706 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
endant | +0.045 |
puts | +0.042 |
dumps | +0.038 |
view | +0.038 |
pasta | +0.037 |
Neg logit contributions | |
forward | -0.086 |
lot | -0.084 |
mate | -0.082 |
often | -0.080 |
Monkey | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
endant | +0.012 |
puts | +0.011 |
pasta | +0.010 |
dumps | +0.010 |
view | +0.010 |
Neg logit contributions | |
lot | -0.009 |
forward | -0.009 |
mate | -0.008 |
Wendy | -0.008 |
often | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
mate | +0.005 |
lot | +0.004 |
forward | +0.004 |
Wendy | +0.004 |
Monkey | +0.004 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
ice | -0.006 |
pasta | -0.006 |
picks | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.004 |
dumps | +0.004 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.003 |
lot | -0.003 |
often | -0.003 |
Wendy | -0.003 |
mate | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
forward | +0.011 |
lot | +0.011 |
mate | +0.010 |
Wendy | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
endant | -0.012 |
puts | -0.011 |
pasta | -0.011 |
ice | -0.011 |
picks | -0.011 |
Token | necklace |
Token ID | 38987 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
forward | +0.002 |
lot | +0.002 |
mate | +0.002 |
Wendy | +0.002 |
Monkey | +0.002 |
Neg logit contributions | |
endant | -0.002 |
puts | -0.002 |
pasta | -0.002 |
dumps | -0.001 |
ice | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Wendy | +0.012 |
lot | +0.012 |
forward | +0.012 |
Bet | +0.012 |
mate | +0.011 |
Neg logit contributions | |
endant | -0.014 |
pasta | -0.013 |
puts | -0.013 |
sandwich | -0.013 |
ice | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
mate | +0.004 |
forward | +0.004 |
lot | +0.004 |
Bet | +0.004 |
June | +0.004 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.005 |
pasta | -0.005 |
dumps | -0.005 |
picks | -0.005 |
Token | found |
Token ID | 1043 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
endant | +0.004 |
puts | +0.004 |
pasta | +0.003 |
dumps | +0.003 |
picks | +0.003 |
Neg logit contributions | |
forward | -0.004 |
lot | -0.004 |
mate | -0.004 |
Wendy | -0.004 |
Monkey | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
dumps | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.001 |
lot | -0.001 |
mate | -0.001 |
Wendy | -0.001 |
often | -0.001 |
Token | seaw |
Token ID | 32085 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
endant | +0.007 |
puts | +0.006 |
dumps | +0.006 |
view | +0.006 |
picks | +0.006 |
Neg logit contributions | |
lot | -0.012 |
forward | -0.011 |
mate | -0.011 |
often | -0.011 |
Wendy | -0.011 |
Token | eed |
Token ID | 2308 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
puts | +0.050 |
view | +0.050 |
endant | +0.048 |
dumps | +0.046 |
ice | +0.044 |
Neg logit contributions | |
lot | -0.081 |
forward | -0.076 |
mate | -0.075 |
often | -0.072 |
grace | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
endant | +0.021 |
puts | +0.019 |
dumps | +0.018 |
pasta | +0.018 |
view | +0.018 |
Neg logit contributions | |
forward | -0.014 |
lot | -0.014 |
mate | -0.013 |
Wendy | -0.013 |
often | -0.013 |
Token | use |
Token ID | 779 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
endant | +0.008 |
puts | +0.008 |
pasta | +0.007 |
dumps | +0.007 |
ice | +0.007 |
Neg logit contributions | |
forward | -0.013 |
lot | -0.012 |
Wendy | -0.012 |
mate | -0.012 |
Monkey | -0.012 |
Token | as |
Token ID | 355 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Wendy | +0.005 |
mate | +0.005 |
forward | +0.005 |
Bet | +0.005 |
lot | +0.005 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.006 |
pasta | -0.006 |
ice | -0.006 |
picks | -0.006 |
Token | string |
Token ID | 4731 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
pasta | +0.006 |
endant | +0.006 |
ice | +0.006 |
puts | +0.005 |
oy | +0.005 |
Neg logit contributions | |
Bet | -0.007 |
Wendy | -0.007 |
June | -0.007 |
mate | -0.006 |
Monkey | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
endant | +0.002 |
puts | +0.002 |
pasta | +0.002 |
dumps | +0.002 |
picks | +0.002 |
Neg logit contributions | |
forward | -0.001 |
lot | -0.001 |
mate | -0.001 |
Wendy | -0.001 |
often | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
lot | +0.011 |
forward | +0.010 |
Wendy | +0.009 |
often | +0.009 |
Mitt | +0.009 |
Neg logit contributions | |
endant | -0.021 |
puts | -0.019 |
weighs | -0.019 |
dumps | -0.019 |
picks | -0.018 |
Token | wise |
Token ID | 10787 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
endant | +0.003 |
pasta | +0.003 |
puts | +0.003 |
ice | +0.003 |
sandwich | +0.003 |
Neg logit contributions | |
forward | -0.004 |
mate | -0.004 |
Wendy | -0.004 |
lot | -0.004 |
Monkey | -0.004 |
Token | guy |
Token ID | 3516 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
endant | +0.005 |
puts | +0.004 |
ice | +0.004 |
pasta | +0.004 |
picks | +0.004 |
Neg logit contributions | |
forward | -0.009 |
mate | -0.009 |
lot | -0.009 |
Wendy | -0.008 |
often | -0.008 |
Token | called |
Token ID | 1444 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
forward | +0.007 |
lot | +0.007 |
Wendy | +0.006 |
stretched | +0.006 |
mate | +0.006 |
Neg logit contributions | |
endant | -0.007 |
puts | -0.007 |
ice | -0.007 |
pasta | -0.007 |
picks | -0.007 |
Token | Mr |
Token ID | 1770 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
pasta | +0.018 |
endant | +0.018 |
puts | +0.017 |
ice | +0.017 |
dumps | +0.016 |
Neg logit contributions | |
forward | -0.023 |
lot | -0.022 |
mate | -0.021 |
often | -0.021 |
stretched | -0.021 |
Token | Smith |
Token ID | 4176 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
endant | +0.078 |
puts | +0.073 |
pasta | +0.071 |
dumps | +0.069 |
picks | +0.069 |
Neg logit contributions | |
forward | -0.048 |
lot | -0.047 |
mate | -0.045 |
Wendy | -0.045 |
often | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
endant | +0.034 |
pasta | +0.031 |
ice | +0.030 |
puts | +0.030 |
picks | +0.029 |
Neg logit contributions | |
Wendy | -0.031 |
forward | -0.030 |
lot | -0.030 |
mate | -0.030 |
Bet | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
endant | +0.014 |
puts | +0.013 |
pasta | +0.013 |
ice | +0.013 |
dumps | +0.012 |
Neg logit contributions | |
forward | -0.010 |
mate | -0.010 |
lot | -0.010 |
Wendy | -0.009 |
often | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
forward | +0.011 |
mate | +0.010 |
lot | +0.010 |
Wendy | +0.010 |
Monkey | +0.009 |
Neg logit contributions | |
endant | -0.009 |
puts | -0.009 |
pasta | -0.008 |
picks | -0.008 |
ice | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
endant | +0.015 |
ice | +0.014 |
puts | +0.014 |
pasta | +0.014 |
picks | +0.013 |
Neg logit contributions | |
forward | -0.018 |
mate | -0.017 |
Wendy | -0.017 |
lot | -0.016 |
Monkey | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
lot | +0.004 |
forward | +0.004 |
mate | +0.004 |
Wendy | +0.004 |
often | +0.004 |
Neg logit contributions | |
endant | -0.006 |
puts | -0.006 |
pasta | -0.006 |
dumps | -0.006 |
picks | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
lot | +0.009 |
forward | +0.008 |
Wendy | +0.008 |
Mitt | +0.007 |
often | +0.007 |
Neg logit contributions | |
endant | -0.017 |
puts | -0.015 |
weighs | -0.015 |
dumps | -0.014 |
ws | -0.014 |
Token | bald |
Token ID | 28273 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
endant | +0.003 |
pasta | +0.003 |
ice | +0.003 |
puts | +0.003 |
sandwich | +0.003 |
Neg logit contributions | |
forward | -0.003 |
mate | -0.003 |
Wendy | -0.003 |
lot | -0.003 |
Monkey | -0.003 |
Token | man |
Token ID | 582 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
endant | +0.021 |
ice | +0.020 |
pasta | +0.019 |
puts | +0.019 |
sandwich | +0.018 |
Neg logit contributions | |
forward | -0.037 |
Wendy | -0.035 |
mate | -0.034 |
Bet | -0.034 |
lot | -0.033 |
Token | named |
Token ID | 3706 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
endant | +0.031 |
puts | +0.028 |
pasta | +0.028 |
dumps | +0.028 |
picks | +0.027 |
Neg logit contributions | |
forward | -0.012 |
lot | -0.012 |
mate | -0.011 |
often | -0.011 |
Wendy | -0.011 |
Token | Mr |
Token ID | 1770 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
endant | +0.009 |
puts | +0.008 |
pasta | +0.008 |
dumps | +0.008 |
picks | +0.007 |
Neg logit contributions | |
forward | -0.006 |
lot | -0.006 |
Wendy | -0.006 |
mate | -0.006 |
often | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
endant | +0.091 |
puts | +0.085 |
dumps | +0.083 |
view | +0.082 |
pasta | +0.082 |
Neg logit contributions | |
lot | -0.040 |
forward | -0.040 |
mate | -0.038 |
Wendy | -0.037 |
Monkey | -0.037 |
Token | Smith |
Token ID | 4176 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
endant | +0.031 |
pasta | +0.030 |
puts | +0.030 |
ice | +0.029 |
frost | +0.028 |
Neg logit contributions | |
forward | -0.023 |
lot | -0.023 |
mate | -0.022 |
Wendy | -0.022 |
often | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
endant | +0.010 |
puts | +0.010 |
pasta | +0.009 |
dumps | +0.009 |
ice | +0.009 |
Neg logit contributions | |
forward | -0.007 |
lot | -0.007 |
mate | -0.006 |
Wendy | -0.006 |
Monkey | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
forward | +0.003 |
lot | +0.003 |
mate | +0.003 |
Wendy | +0.003 |
often | +0.003 |
Neg logit contributions | |
endant | -0.005 |
puts | -0.004 |
pasta | -0.004 |
ice | -0.004 |
dumps | -0.004 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
lot | +0.008 |
forward | +0.008 |
often | +0.008 |
mate | +0.008 |
Wendy | +0.008 |
Neg logit contributions | |
endant | -0.010 |
puts | -0.009 |
pasta | -0.009 |
dumps | -0.009 |
view | -0.009 |