Token | said |
Token ID | 531 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
anne | +0.019 |
rina | +0.019 |
jo | +0.018 |
beard | +0.018 |
helicopters | +0.018 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.013 |
pin | -0.012 |
cater | -0.012 |
first | -0.011 |
Token | $ |
Token ID | 720 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
rina | +0.002 |
anne | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
jo | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
Fro | -0.001 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
lipstick | +0.034 |
cater | +0.033 |
P | +0.032 |
Fro | +0.032 |
pin | +0.032 |
Neg logit contributions | |
beard | -0.032 |
helicopters | -0.031 |
motors | -0.031 |
rockets | -0.030 |
anne | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
rina | +0.003 |
anne | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.001 |
cater | -0.001 |
Fro | -0.001 |
Token | 99 |
Token ID | 2079 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
lipstick | +0.002 |
pin | +0.002 |
cater | +0.002 |
cent | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
helicopters | -0.001 |
rockets | -0.001 |
der | -0.001 |
Token | per |
Token ID | 583 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
helicopters | +0.017 |
rina | +0.016 |
rockets | +0.016 |
beard | +0.015 |
anne | +0.015 |
Neg logit contributions | |
lipstick | -0.011 |
pin | -0.010 |
P | -0.010 |
cater | -0.009 |
first | -0.009 |
Token | pound |
Token ID | 14896 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
lipstick | +0.080 |
P | +0.074 |
pin | +0.068 |
cater | +0.067 |
but | +0.067 |
Neg logit contributions | |
anne | -0.063 |
rina | -0.062 |
jo | -0.061 |
beard | -0.060 |
helicopters | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
lipstick | +0.016 |
P | +0.014 |
cater | +0.013 |
pin | +0.013 |
Fro | +0.013 |
Neg logit contributions | |
anne | -0.017 |
rina | -0.017 |
jo | -0.017 |
beard | -0.016 |
helicopters | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
lipstick | +0.001 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
cent | +0.001 |
Neg logit contributions | |
anne | -0.001 |
helicopters | -0.001 |
rina | -0.001 |
rockets | -0.001 |
aliens | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
Fro | +0.002 |
but | +0.002 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.004 |
helicopters | -0.004 |
beard | -0.004 |
jo | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
anne | +0.007 |
beard | +0.007 |
rina | +0.007 |
jo | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
Fro | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
Fro | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.009 |
cater | +0.008 |
first | +0.008 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
P | +0.009 |
lipstick | +0.009 |
Fro | +0.007 |
but | +0.007 |
pin | +0.007 |
Neg logit contributions | |
rina | -0.017 |
anne | -0.017 |
jo | -0.016 |
beard | -0.016 |
helicopters | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
jo | -0.002 |
beard | -0.002 |
helicopters | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
helicopters | +0.004 |
jo | +0.004 |
beard | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
but | -0.003 |
Token | ot |
Token ID | 30972 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.019 |
pin | +0.017 |
but | +0.017 |
cater | +0.017 |
Neg logit contributions | |
beard | -0.025 |
rina | -0.025 |
helicopters | -0.024 |
anne | -0.024 |
jo | -0.023 |
Token | ter |
Token ID | 353 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lipstick | +0.072 |
P | +0.057 |
brush | +0.053 |
Gw | +0.051 |
Jade | +0.051 |
Neg logit contributions | |
beard | -0.074 |
rina | -0.066 |
helicopters | -0.066 |
eer | -0.063 |
opter | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
lipstick | +0.026 |
P | +0.025 |
pin | +0.025 |
cater | +0.024 |
first | +0.023 |
Neg logit contributions | |
anne | -0.041 |
rina | -0.041 |
helicopters | -0.041 |
rockets | -0.040 |
jo | -0.040 |
Token | always |
Token ID | 1464 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
beard | -0.007 |
helicopters | -0.007 |
Token | gentle |
Token ID | 10296 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
beard | -0.009 |
jo | -0.009 |
helicopters | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.007 |
Fro | +0.007 |
Neg logit contributions | |
anne | -0.027 |
rina | -0.027 |
jo | -0.026 |
beard | -0.026 |
helicopters | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
jo | +0.010 |
beard | +0.010 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
first | -0.006 |
Token | walked |
Token ID | 6807 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
jo | +0.008 |
helicopters | +0.008 |
beard | +0.008 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.007 |
pin | -0.006 |
cater | -0.006 |
first | -0.006 |
Token | away |
Token ID | 1497 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
anne | +0.012 |
beard | +0.012 |
jo | +0.012 |
rina | +0.012 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
cater | -0.008 |
pin | -0.008 |
cent | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
beard | +0.010 |
jo | +0.010 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.007 |
cater | -0.006 |
Fro | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.010 |
pin | +0.009 |
cater | +0.009 |
but | +0.008 |
Neg logit contributions | |
rina | -0.014 |
anne | -0.014 |
beard | -0.014 |
jo | -0.014 |
helicopters | -0.013 |
Token | ot |
Token ID | 30972 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.019 |
pin | +0.017 |
cater | +0.017 |
Fro | +0.017 |
Neg logit contributions | |
beard | -0.020 |
rina | -0.020 |
helicopters | -0.019 |
rockets | -0.019 |
anne | -0.019 |
Token | ter |
Token ID | 353 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
lipstick | +0.067 |
P | +0.055 |
Jade | +0.049 |
cent | +0.048 |
Gw | +0.047 |
Neg logit contributions | |
beard | -0.077 |
rina | -0.073 |
helicopters | -0.072 |
jo | -0.070 |
rockets | -0.069 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
lipstick | +0.026 |
P | +0.025 |
pin | +0.024 |
cater | +0.023 |
first | +0.023 |
Neg logit contributions | |
anne | -0.037 |
rina | -0.037 |
beard | -0.036 |
jo | -0.036 |
helicopters | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
pin | +0.010 |
cater | +0.010 |
but | +0.010 |
Neg logit contributions | |
anne | -0.037 |
rina | -0.036 |
jo | -0.036 |
beard | -0.035 |
helicopters | -0.035 |
Token | waved |
Token ID | 26834 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.005 |
beard | -0.005 |
helicopters | -0.005 |
Token | back |
Token ID | 736 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
but | +0.006 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
jo | -0.009 |
beard | -0.008 |
helicopters | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
anne | +0.007 |
jo | +0.007 |
rina | +0.007 |
beard | +0.007 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.007 |
cater | -0.006 |
pin | -0.006 |
Fro | -0.006 |
Token | |
Token ID | 220 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
rina | +0.015 |
helicopters | +0.014 |
anne | +0.014 |
beard | +0.014 |
rockets | +0.014 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.011 |
but | -0.009 |
pin | -0.009 |
cater | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.010 |
cater | +0.010 |
first | +0.009 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
beard | -0.015 |
jo | -0.015 |
helicopters | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.003 |
jo | -0.003 |
rina | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Rob | +0.007 |
anne | +0.007 |
jo | +0.006 |
rina | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
first | -0.005 |
Token | ot |
Token ID | 30972 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.020 |
pin | +0.019 |
cater | +0.018 |
first | +0.018 |
Neg logit contributions | |
anne | -0.026 |
rina | -0.026 |
jo | -0.025 |
beard | -0.025 |
helicopters | -0.025 |
Token | ter |
Token ID | 353 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
lipstick | +0.064 |
P | +0.052 |
but | +0.046 |
brush | +0.045 |
cent | +0.045 |
Neg logit contributions | |
beard | -0.077 |
rina | -0.073 |
anne | -0.071 |
jo | -0.069 |
helicopters | -0.069 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
lipstick | +0.025 |
P | +0.024 |
pin | +0.023 |
cater | +0.022 |
first | +0.022 |
Neg logit contributions | |
helicopters | -0.039 |
rina | -0.039 |
anne | -0.039 |
rockets | -0.039 |
beard | -0.038 |
Token | so |
Token ID | 523 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | relieved |
Token ID | 22598 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
anne | +0.006 |
rina | +0.006 |
jo | +0.006 |
beard | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
Fro | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
anne | -0.003 |
rina | -0.003 |
jo | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.012 |
cater | +0.012 |
first | +0.011 |
Neg logit contributions | |
anne | -0.014 |
rina | -0.013 |
jo | -0.013 |
beard | -0.013 |
helicopters | -0.013 |
Token | went |
Token ID | 1816 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
anne | +0.004 |
rina | +0.004 |
jo | +0.004 |
beard | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.002 |
cater | -0.002 |
first | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
helicopters | +0.003 |
anne | +0.003 |
rockets | +0.003 |
hikes | +0.003 |
rina | +0.003 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
cater | -0.002 |
Watch | -0.002 |
cent | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
helicopters | +0.015 |
rockets | +0.014 |
anne | +0.014 |
rina | +0.014 |
beard | +0.014 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.010 |
cater | -0.009 |
pin | -0.009 |
Pam | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
first | +0.008 |
so | +0.008 |
Neg logit contributions | |
anne | -0.026 |
rina | -0.025 |
jo | -0.025 |
beard | -0.024 |
opter | -0.023 |
Token | mis |
Token ID | 2984 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
helicopters | +0.010 |
anne | +0.010 |
rina | +0.010 |
rockets | +0.009 |
beard | +0.009 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
Jade | -0.007 |
pin | -0.007 |
cater | -0.007 |
Token | chie |
Token ID | 3043 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
lipstick | +0.068 |
P | +0.064 |
pin | +0.057 |
cater | +0.057 |
but | +0.055 |
Neg logit contributions | |
anne | -0.066 |
rina | -0.064 |
jo | -0.064 |
beard | -0.062 |
helicopters | -0.061 |
Token | vous |
Token ID | 31222 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
lipstick | +0.026 |
P | +0.024 |
pin | +0.022 |
cater | +0.022 |
Fro | +0.021 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.023 |
jo | -0.023 |
beard | -0.022 |
helicopters | -0.022 |
Token | ways |
Token ID | 2842 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
lipstick | +0.019 |
P | +0.017 |
pin | +0.015 |
cater | +0.015 |
first | +0.014 |
Neg logit contributions | |
anne | -0.028 |
rina | -0.028 |
jo | -0.027 |
beard | -0.027 |
helicopters | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
anne | -0.019 |
jo | -0.019 |
rina | -0.019 |
beard | -0.019 |
helicopters | -0.018 |
Token | causing |
Token ID | 6666 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
helicopters | +0.006 |
rockets | +0.006 |
anne | +0.006 |
jo | +0.006 |
motors | +0.006 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
cater | -0.002 |
ula | -0.002 |
Jade | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
rina | -0.007 |
anne | -0.007 |
beard | -0.006 |
jo | -0.006 |
helicopters | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Pam | +0.002 |
Neg logit contributions | |
beard | -0.003 |
anne | -0.003 |
helicopters | -0.003 |
rina | -0.003 |
jo | -0.003 |
Token | scientist |
Token ID | 11444 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.018 |
Fro | +0.018 |
Jade | +0.017 |
but | +0.017 |
Neg logit contributions | |
beard | -0.021 |
helicopters | -0.019 |
aliens | -0.019 |
rina | -0.019 |
rockets | -0.019 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.011 |
cater | +0.010 |
first | +0.010 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.019 |
helicopters | -0.018 |
beard | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
cent | +0.004 |
Neg logit contributions | |
beard | -0.008 |
rina | -0.008 |
helicopters | -0.008 |
rockets | -0.008 |
anne | -0.008 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
lipstick | +0.019 |
P | +0.016 |
Fro | +0.015 |
Jade | +0.015 |
Pam | +0.015 |
Neg logit contributions | |
beard | -0.019 |
helicopters | -0.018 |
aliens | -0.018 |
rina | -0.018 |
rockets | -0.017 |
Token | ter |
Token ID | 353 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
lipstick | +0.068 |
P | +0.055 |
Gw | +0.051 |
brush | +0.050 |
jump | +0.049 |
Neg logit contributions | |
beard | -0.070 |
rina | -0.064 |
helicopters | -0.061 |
jo | -0.060 |
aliens | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
lipstick | +0.028 |
P | +0.025 |
pin | +0.022 |
cater | +0.022 |
Fro | +0.020 |
Neg logit contributions | |
rina | -0.049 |
anne | -0.049 |
beard | -0.048 |
jo | -0.048 |
helicopters | -0.047 |
Token | swim |
Token ID | 9422 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
Fro | +0.005 |
cent | +0.005 |
iw | +0.005 |
Neg logit contributions | |
helicopters | -0.007 |
rina | -0.007 |
beard | -0.007 |
rockets | -0.007 |
aliens | -0.007 |
Token | around |
Token ID | 1088 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
beard | +0.007 |
anne | +0.006 |
rina | +0.006 |
jo | +0.006 |
rockets | +0.006 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
cater | -0.004 |
pin | -0.004 |
cent | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
beard | +0.011 |
rockets | +0.011 |
helicopters | +0.011 |
aliens | +0.011 |
rina | +0.011 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.007 |
cater | -0.006 |
cent | -0.006 |
Watch | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
anne | +0.012 |
rina | +0.012 |
jo | +0.012 |
beard | +0.012 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.007 |
cater | -0.006 |
first | -0.006 |
Token | |
Token ID | 220 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
lipstick | +0.010 |
pin | +0.009 |
P | +0.008 |
cater | +0.008 |
first | +0.008 |
Neg logit contributions | |
anne | -0.009 |
jo | -0.009 |
rina | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
P | +0.008 |
lipstick | +0.008 |
Fro | +0.007 |
but | +0.007 |
pin | +0.006 |
Neg logit contributions | |
rina | -0.014 |
anne | -0.014 |
beard | -0.014 |
helicopters | -0.014 |
rockets | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
first | +0.005 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
jo | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
jo | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
first | -0.001 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
lipstick | +0.020 |
P | +0.018 |
pin | +0.017 |
cater | +0.016 |
but | +0.016 |
Neg logit contributions | |
rina | -0.024 |
anne | -0.024 |
beard | -0.023 |
jo | -0.023 |
helicopters | -0.022 |
Token | ter |
Token ID | 353 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
lipstick | +0.063 |
P | +0.051 |
brush | +0.045 |
cent | +0.044 |
but | +0.044 |
Neg logit contributions | |
beard | -0.074 |
rina | -0.070 |
anne | -0.067 |
helicopters | -0.066 |
jo | -0.066 |
Token | spent |
Token ID | 3377 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.021 |
pin | +0.021 |
first | +0.020 |
cater | +0.020 |
Neg logit contributions | |
helicopters | -0.034 |
anne | -0.034 |
rina | -0.034 |
rockets | -0.033 |
jo | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
rina | +0.014 |
beard | +0.014 |
anne | +0.014 |
jo | +0.014 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.009 |
cater | -0.009 |
pin | -0.008 |
cent | -0.008 |
Token | entire |
Token ID | 2104 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
lipstick | +0.016 |
P | +0.015 |
pin | +0.013 |
cater | +0.013 |
Fro | +0.013 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.019 |
beard | -0.018 |
helicopters | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.013 |
pin | +0.012 |
cater | +0.012 |
first | +0.012 |
Neg logit contributions | |
rina | -0.022 |
anne | -0.021 |
jo | -0.021 |
beard | -0.021 |
helicopters | -0.020 |
Token | here |
Token ID | 994 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
cater | +0.003 |
pin | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
rina | -0.006 |
anne | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
jo | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
rina | -0.005 |
anne | -0.005 |
beard | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
Token | â |
Token ID | 22940 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
lipstick | +0.007 |
pin | +0.006 |
P | +0.006 |
cater | +0.006 |
cent | +0.005 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
jo | -0.010 |
beard | -0.010 |
helicopters | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
anne | +0.004 |
rina | +0.004 |
jo | +0.004 |
beard | +0.004 |
opter | +0.004 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
cater | -0.004 |
Fro | -0.004 |
pin | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
rina | +0.009 |
anne | +0.008 |
helicopters | +0.008 |
jo | +0.008 |
aliens | +0.008 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
but | -0.006 |
pin | -0.005 |
cater | -0.005 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
lipstick | +0.017 |
P | +0.014 |
Jade | +0.013 |
but | +0.013 |
Gw | +0.013 |
Neg logit contributions | |
beard | -0.019 |
rina | -0.017 |
helicopters | -0.017 |
motors | -0.017 |
anne | -0.016 |
Token | ter |
Token ID | 353 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
lipstick | +0.075 |
P | +0.062 |
Gw | +0.058 |
but | +0.057 |
brush | +0.057 |
Neg logit contributions | |
beard | -0.059 |
rina | -0.051 |
eer | -0.050 |
helicopters | -0.049 |
opter | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
lipstick | +0.033 |
P | +0.030 |
pin | +0.029 |
cater | +0.028 |
first | +0.028 |
Neg logit contributions | |
rina | -0.043 |
anne | -0.043 |
helicopters | -0.041 |
beard | -0.041 |
jo | -0.041 |
Token | very |
Token ID | 845 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
cater | +0.003 |
pin | +0.003 |
cent | +0.003 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
beard | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
first | +0.003 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
first | +0.002 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.005 |
beard | -0.005 |
helicopters | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.008 |
pin | +0.007 |
cater | +0.007 |
but | +0.007 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
jo | -0.010 |
beard | -0.010 |
helicopters | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
anne | +0.001 |
rina | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
first | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
rina | +0.003 |
anne | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
jo | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.001 |
cater | -0.001 |
Fro | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
anne | +0.011 |
rina | +0.011 |
jo | +0.010 |
beard | +0.010 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
first | -0.005 |
Token | crit |
Token ID | 1955 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.019 |
pin | +0.017 |
Jade | +0.017 |
cater | +0.017 |
Neg logit contributions | |
rina | -0.023 |
beard | -0.022 |
anne | -0.022 |
helicopters | -0.022 |
jo | -0.022 |
Token | ter |
Token ID | 353 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
lipstick | +0.053 |
P | +0.045 |
pin | +0.039 |
cater | +0.038 |
Jade | +0.037 |
Neg logit contributions | |
rina | -0.079 |
beard | -0.078 |
anne | -0.077 |
jo | -0.076 |
helicopters | -0.076 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.017 |
pin | +0.016 |
cater | +0.016 |
first | +0.015 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.024 |
jo | -0.024 |
beard | -0.024 |
helicopters | -0.024 |
Token | more |
Token ID | 517 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.008 |
cater | +0.008 |
pin | +0.008 |
cent | +0.007 |
Neg logit contributions | |
anne | -0.013 |
rina | -0.013 |
beard | -0.013 |
jo | -0.013 |
helicopters | -0.013 |
Token | brave |
Token ID | 14802 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.004 |
but | +0.003 |
cater | +0.003 |
Neg logit contributions | |
rina | -0.010 |
anne | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.011 |
pin | +0.010 |
but | +0.010 |
cater | +0.010 |
Neg logit contributions | |
rina | -0.034 |
anne | -0.033 |
jo | -0.032 |
beard | -0.032 |
helicopters | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
rina | +0.003 |
anne | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
cent | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.009 |
first | +0.009 |
cater | +0.009 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
jo | -0.016 |
beard | -0.015 |
helicopters | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
lipstick | +0.005 |
cent | +0.004 |
P | +0.004 |
pin | +0.004 |
first | +0.004 |
Neg logit contributions | |
anne | -0.005 |
helicopters | -0.005 |
jo | -0.005 |
beard | -0.005 |
rockets | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
rina | -0.003 |
anne | -0.003 |
beard | -0.003 |
jo | -0.003 |
helicopters | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
helicopters | +0.007 |
Rob | +0.007 |
beard | +0.007 |
rina | +0.007 |
opter | +0.007 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.006 |
first | -0.006 |
pin | -0.006 |
but | -0.006 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.019 |
pin | +0.017 |
cater | +0.016 |
but | +0.016 |
Neg logit contributions | |
beard | -0.025 |
rina | -0.025 |
anne | -0.024 |
helicopters | -0.024 |
jo | -0.024 |
Token | ter |
Token ID | 353 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
lipstick | +0.066 |
P | +0.052 |
brush | +0.048 |
Gw | +0.047 |
Jade | +0.047 |
Neg logit contributions | |
beard | -0.070 |
rina | -0.062 |
helicopters | -0.061 |
eer | -0.060 |
opter | -0.059 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
lipstick | +0.023 |
P | +0.022 |
pin | +0.022 |
cater | +0.020 |
first | +0.020 |
Neg logit contributions | |
helicopters | -0.035 |
rina | -0.035 |
anne | -0.035 |
rockets | -0.034 |
jo | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
helicopters | +0.001 |
beard | +0.001 |
jo | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
cent | -0.000 |
Token | song |
Token ID | 3496 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
lipstick | +0.020 |
P | +0.019 |
Jade | +0.017 |
Pam | +0.017 |
Linda | +0.016 |
Neg logit contributions | |
rina | -0.019 |
beard | -0.019 |
helicopters | -0.018 |
anne | -0.018 |
rockets | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
cater | +0.009 |
pin | +0.009 |
Fro | +0.008 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.018 |
beard | -0.018 |
helicopters | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
lipstick | +0.017 |
P | +0.015 |
pin | +0.014 |
cater | +0.014 |
first | +0.013 |
Neg logit contributions | |
anne | -0.018 |
rina | -0.018 |
jo | -0.018 |
beard | -0.017 |
helicopters | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
rina | -0.007 |
anne | -0.007 |
beard | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
first | -0.002 |
Token | cat |
Token ID | 3797 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.008 |
Fro | +0.007 |
Jade | +0.007 |
pin | +0.007 |
Neg logit contributions | |
rina | -0.008 |
anne | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
rockets | -0.008 |
Token | grinned |
Token ID | 36268 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
lipstick | +0.024 |
P | +0.022 |
pin | +0.020 |
cater | +0.020 |
Fro | +0.019 |
Neg logit contributions | |
anne | -0.029 |
rina | -0.029 |
jo | -0.028 |
beard | -0.028 |
helicopters | -0.027 |
Token | mis |
Token ID | 2984 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
lipstick | +0.015 |
P | +0.013 |
pin | +0.012 |
cater | +0.011 |
Fro | +0.010 |
Neg logit contributions | |
rina | -0.034 |
anne | -0.034 |
jo | -0.034 |
beard | -0.034 |
helicopters | -0.033 |
Token | chie |
Token ID | 3043 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
lipstick | +0.075 |
P | +0.068 |
pin | +0.060 |
but | +0.060 |
first | +0.060 |
Neg logit contributions | |
anne | -0.056 |
jo | -0.055 |
beard | -0.054 |
rina | -0.054 |
helicopters | -0.050 |
Token | v |
Token ID | 85 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
lipstick | +0.046 |
P | +0.042 |
pin | +0.038 |
cater | +0.038 |
Fro | +0.037 |
Neg logit contributions | |
anne | -0.038 |
jo | -0.036 |
rina | -0.035 |
beard | -0.033 |
helicopters | -0.031 |
Token | ously |
Token ID | 3481 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
anne | +0.018 |
rina | +0.018 |
beard | +0.017 |
jo | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.024 |
P | -0.023 |
pin | -0.022 |
cater | -0.021 |
first | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
but | +0.003 |
Neg logit contributions | |
rina | -0.010 |
anne | -0.010 |
beard | -0.010 |
jo | -0.010 |
helicopters | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.012 |
cater | +0.012 |
first | +0.011 |
Neg logit contributions | |
anne | -0.017 |
rina | -0.017 |
jo | -0.017 |
beard | -0.016 |
helicopters | -0.016 |
Token | success |
Token ID | 1943 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
pin | +0.010 |
cater | +0.010 |
Fro | +0.010 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
beard | -0.016 |
jo | -0.015 |
helicopters | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
anne | +0.000 |
rina | +0.000 |
jo | +0.000 |
beard | +0.000 |
helicopters | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
Fro | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
but | +0.006 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | thanked |
Token ID | 26280 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.004 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
jo | -0.005 |
helicopters | -0.005 |
beard | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
lipstick | +0.006 |
cent | +0.005 |
P | +0.005 |
pin | +0.005 |
bottle | +0.005 |
Neg logit contributions | |
helicopters | -0.008 |
rockets | -0.008 |
beard | -0.008 |
rina | -0.008 |
aliens | -0.007 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
lipstick | +0.025 |
P | +0.022 |
Fro | +0.020 |
pin | +0.020 |
but | +0.019 |
Neg logit contributions | |
beard | -0.028 |
helicopters | -0.026 |
rina | -0.026 |
rockets | -0.026 |
anne | -0.026 |
Token | ter |
Token ID | 353 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
lipstick | +0.061 |
P | +0.049 |
Fro | +0.044 |
Gw | +0.043 |
cent | +0.043 |
Neg logit contributions | |
beard | -0.072 |
rina | -0.066 |
helicopters | -0.065 |
jo | -0.063 |
anne | -0.062 |
Token | for |
Token ID | 329 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
lipstick | +0.019 |
P | +0.016 |
pin | +0.015 |
cater | +0.014 |
Fro | +0.013 |
Neg logit contributions | |
rina | -0.044 |
anne | -0.044 |
jo | -0.043 |
beard | -0.043 |
helicopters | -0.042 |
Token | helping |
Token ID | 5742 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.006 |
cater | +0.006 |
cent | +0.006 |
pin | +0.006 |
Neg logit contributions | |
rockets | -0.009 |
helicopters | -0.009 |
rina | -0.009 |
beard | -0.009 |
aliens | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
cater | +0.007 |
cent | +0.007 |
Gw | +0.007 |
Neg logit contributions | |
beard | -0.004 |
helicopters | -0.004 |
rina | -0.004 |
jo | -0.004 |
rockets | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
lipstick | +0.016 |
P | +0.014 |
pin | +0.012 |
cater | +0.012 |
Fro | +0.011 |
Neg logit contributions | |
rina | -0.026 |
anne | -0.026 |
beard | -0.025 |
jo | -0.025 |
helicopters | -0.025 |
Token | together |
Token ID | 1978 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
cater | +0.011 |
pin | +0.011 |
Fro | +0.010 |
Neg logit contributions | |
anne | -0.020 |
beard | -0.020 |
rina | -0.020 |
helicopters | -0.020 |
jo | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
anne | +0.006 |
rina | +0.006 |
jo | +0.005 |
beard | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.003 |
cater | -0.003 |
but | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
P | +0.006 |
lipstick | +0.005 |
Fro | +0.005 |
but | +0.004 |
Pam | +0.004 |
Neg logit contributions | |
rina | -0.011 |
anne | -0.011 |
helicopters | -0.011 |
beard | -0.011 |
rockets | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
P | +0.002 |
lipstick | +0.002 |
Fro | +0.002 |
pin | +0.002 |
first | +0.002 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.003 |
helicopters | -0.003 |
beard | -0.003 |
rockets | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.007 |
beard | +0.007 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.003 |
cater | -0.003 |
first | -0.003 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
lipstick | +0.017 |
P | +0.015 |
pin | +0.013 |
but | +0.013 |
Fro | +0.013 |
Neg logit contributions | |
beard | -0.017 |
rina | -0.017 |
helicopters | -0.017 |
anne | -0.016 |
rockets | -0.016 |
Token | ters |
Token ID | 1010 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
lipstick | +0.064 |
P | +0.051 |
brush | +0.047 |
cent | +0.046 |
Gw | +0.045 |
Neg logit contributions | |
beard | -0.069 |
rina | -0.064 |
helicopters | -0.063 |
jo | -0.060 |
anne | -0.060 |
Token | were |
Token ID | 547 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
lipstick | +0.027 |
P | +0.025 |
pin | +0.025 |
cater | +0.023 |
first | +0.023 |
Neg logit contributions | |
anne | -0.036 |
rina | -0.036 |
jo | -0.036 |
beard | -0.035 |
helicopters | -0.035 |
Token | now |
Token ID | 783 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
anne | +0.001 |
jo | +0.001 |
rina | +0.001 |
beard | +0.001 |
rockets | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
so | -0.000 |
pin | -0.000 |
first | -0.000 |
Token | friends |
Token ID | 2460 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
anne | +0.017 |
rina | +0.017 |
jo | +0.017 |
beard | +0.016 |
helicopters | +0.015 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
pin | -0.008 |
cater | -0.007 |
first | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
lipstick | +0.020 |
P | +0.018 |
pin | +0.017 |
cater | +0.016 |
but | +0.016 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.024 |
jo | -0.024 |
beard | -0.024 |
helicopters | -0.023 |
Token | € |
Token ID | 26391 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
anne | +0.018 |
rina | +0.018 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.020 |
P | -0.018 |
pin | -0.017 |
cater | -0.017 |
first | -0.016 |
Token | � |
Token ID | 129 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
rina | +0.023 |
helicopters | +0.023 |
anne | +0.022 |
aliens | +0.021 |
rockets | +0.021 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
but | -0.014 |
pin | -0.013 |
Fro | -0.013 |
Token | � |
Token ID | 241 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
anne | +0.006 |
rina | +0.006 |
jo | +0.006 |
beard | +0.006 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
pin | -0.008 |
cater | -0.008 |
first | -0.008 |
Token | What |
Token ID | 2061 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.010 |
pin | +0.010 |
cater | +0.009 |
bottle | +0.009 |
Neg logit contributions | |
anne | -0.014 |
jo | -0.013 |
rina | -0.012 |
beard | -0.012 |
Rob | -0.012 |
Token | is |
Token ID | 318 |
Feature activation | +9.27e-04 |
Pos logit contributions | |
rina | +0.020 |
anne | +0.020 |
jo | +0.019 |
beard | +0.019 |
helicopters | +0.018 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
pin | -0.014 |
cater | -0.013 |
first | -0.013 |
Token | wrong |
Token ID | 2642 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
cater | +0.000 |
pin | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
rina | -0.000 |
anne | -0.000 |
helicopters | -0.000 |
beard | -0.000 |
rockets | -0.000 |
Token | ? |
Token ID | 30 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
lipstick | +0.049 |
P | +0.041 |
pin | +0.039 |
Fro | +0.037 |
cater | +0.036 |
Neg logit contributions | |
rina | -0.074 |
anne | -0.074 |
beard | -0.072 |
jo | -0.072 |
helicopters | -0.070 |
Token | â |
Token ID | 22940 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
lipstick | +0.009 |
pin | +0.008 |
cater | +0.008 |
P | +0.008 |
first | +0.008 |
Neg logit contributions | |
anne | -0.009 |
jo | -0.009 |
rina | -0.009 |
beard | -0.009 |
helicopters | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
anne | +0.006 |
jo | +0.005 |
rina | +0.005 |
beard | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
cater | -0.005 |
pin | -0.005 |
Fro | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
rina | +0.013 |
helicopters | +0.013 |
anne | +0.012 |
aliens | +0.012 |
rockets | +0.012 |
Neg logit contributions | |
P | -0.007 |
lipstick | -0.007 |
but | -0.006 |
Fro | -0.006 |
with | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.012 |
cater | +0.011 |
first | +0.011 |
Neg logit contributions | |
anne | -0.015 |
rina | -0.015 |
jo | -0.015 |
beard | -0.014 |
helicopters | -0.014 |
Token | Emily |
Token ID | 48640 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
anne | +0.004 |
jo | +0.004 |
rina | +0.004 |
beard | +0.004 |
rockets | +0.003 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
Fro | -0.003 |
cater | -0.003 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
rina | -0.005 |
anne | -0.005 |
beard | -0.005 |
helicopters | -0.005 |
jo | -0.005 |
Token | encouraged |
Token ID | 10085 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.007 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
beard | -0.016 |
jo | -0.016 |
helicopters | -0.016 |
Token | by |
Token ID | 416 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
lipstick | +0.010 |
pitcher | +0.009 |
Fro | +0.009 |
tad | +0.009 |
Watch | +0.009 |
Neg logit contributions | |
jo | -0.012 |
anne | -0.012 |
rina | -0.011 |
helicopters | -0.011 |
storms | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.011 |
pin | +0.010 |
Watch | +0.010 |
cent | +0.010 |
Neg logit contributions | |
rina | -0.021 |
helicopters | -0.020 |
rockets | -0.020 |
beard | -0.019 |
anne | -0.019 |
Token | pap |
Token ID | 20461 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.019 |
pin | +0.017 |
Jade | +0.017 |
Fro | +0.017 |
Neg logit contributions | |
rina | -0.024 |
anne | -0.023 |
jo | -0.022 |
beard | -0.022 |
helicopters | -0.022 |
Token | a |
Token ID | 64 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
lipstick | +0.060 |
P | +0.055 |
pin | +0.052 |
cater | +0.051 |
first | +0.049 |
Neg logit contributions | |
anne | -0.066 |
rina | -0.065 |
jo | -0.064 |
beard | -0.063 |
helicopters | -0.062 |
Token | 's |
Token ID | 338 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.010 |
cater | +0.009 |
Fro | +0.009 |
Neg logit contributions | |
anne | -0.022 |
rina | -0.022 |
jo | -0.022 |
beard | -0.022 |
helicopters | -0.021 |
Token | words |
Token ID | 2456 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.006 |
pin | +0.005 |
Fro | +0.005 |
Jade | +0.005 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
rockets | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
pin | +0.007 |
cater | +0.007 |
Fro | +0.006 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.019 |
beard | -0.019 |
helicopters | -0.018 |
Token | Every |
Token ID | 3887 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.007 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.017 |
rina | -0.017 |
jo | -0.016 |
beard | -0.016 |
helicopters | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
pin | +0.009 |
first | +0.009 |
lipstick | +0.009 |
Fro | +0.009 |
cater | +0.008 |
Neg logit contributions | |
der | -0.007 |
anne | -0.007 |
happens | -0.007 |
rockets | -0.007 |
storms | -0.007 |
Token | wondered |
Token ID | 14028 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.011 |
pin | +0.011 |
cater | +0.010 |
first | +0.010 |
Neg logit contributions | |
anne | -0.021 |
rina | -0.020 |
jo | -0.020 |
helicopters | -0.020 |
beard | -0.020 |
Token | what |
Token ID | 644 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
rina | +0.014 |
anne | +0.013 |
beard | +0.013 |
helicopters | +0.013 |
jo | +0.013 |
Neg logit contributions | |
lipstick | -0.015 |
P | -0.013 |
pin | -0.012 |
cater | -0.012 |
Fro | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
pin | +0.009 |
cater | +0.009 |
but | +0.009 |
Neg logit contributions | |
rina | -0.016 |
anne | -0.016 |
jo | -0.016 |
beard | -0.015 |
helicopters | -0.015 |
Token | tasted |
Token ID | 29187 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
cater | +0.002 |
pin | +0.002 |
Fro | +0.001 |
Neg logit contributions | |
rina | -0.002 |
beard | -0.002 |
anne | -0.002 |
jo | -0.002 |
rockets | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
lipstick | +0.043 |
Pam | +0.038 |
Fro | +0.038 |
Gw | +0.038 |
P | +0.037 |
Neg logit contributions | |
beard | -0.030 |
rina | -0.029 |
der | -0.029 |
happens | -0.028 |
land | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
lipstick | +0.066 |
P | +0.060 |
Pam | +0.058 |
Fro | +0.057 |
pin | +0.057 |
Neg logit contributions | |
rina | -0.052 |
rockets | -0.052 |
anne | -0.051 |
beard | -0.051 |
helicopters | -0.050 |
Token | She |
Token ID | 1375 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
lipstick | +0.012 |
pin | +0.012 |
cater | +0.012 |
Fro | +0.011 |
cent | +0.011 |
Neg logit contributions | |
anne | -0.015 |
jo | -0.014 |
storms | -0.013 |
rina | -0.013 |
der | -0.013 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
pin | +0.006 |
cater | +0.005 |
first | +0.005 |
Neg logit contributions | |
anne | -0.011 |
jo | -0.011 |
rina | -0.011 |
helicopters | -0.011 |
beard | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.006 |
jo | -0.006 |
rina | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
Token | jar |
Token ID | 17379 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Jade | +0.019 |
Yes | +0.019 |
Pam | +0.019 |
P | +0.018 |
lipstick | +0.018 |
Neg logit contributions | |
beard | -0.025 |
rockets | -0.022 |
marsh | -0.022 |
happens | -0.022 |
rina | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
but | +0.000 |
pin | +0.000 |
so | +0.000 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
jo | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
Token | |
Token ID | 220 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
rockets | +0.001 |
Neg logit contributions | |
P | -0.001 |
lipstick | -0.001 |
Fro | -0.001 |
but | -0.001 |
Pam | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
P | +0.004 |
lipstick | +0.003 |
Fro | +0.003 |
but | +0.003 |
first | +0.003 |
Neg logit contributions | |
rina | -0.010 |
anne | -0.010 |
helicopters | -0.010 |
rockets | -0.009 |
beard | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
rina | +0.003 |
anne | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
jo | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
Fro | -0.001 |
pin | -0.001 |
cater | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
anne | +0.012 |
rina | +0.012 |
beard | +0.011 |
jo | +0.011 |
helicopters | +0.011 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
Fro | -0.005 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
lipstick | +0.015 |
P | +0.014 |
pin | +0.013 |
cater | +0.012 |
first | +0.012 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.019 |
beard | -0.018 |
helicopters | -0.018 |
Token | ter |
Token ID | 353 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
lipstick | +0.056 |
P | +0.046 |
Fro | +0.039 |
cent | +0.039 |
cater | +0.039 |
Neg logit contributions | |
beard | -0.073 |
rina | -0.071 |
helicopters | -0.069 |
anne | -0.068 |
jo | -0.068 |
Token | was |
Token ID | 373 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
pin | +0.022 |
P | +0.022 |
first | +0.022 |
cater | +0.022 |
lipstick | +0.021 |
Neg logit contributions | |
helicopters | -0.040 |
anne | -0.040 |
rockets | -0.040 |
beard | -0.039 |
rina | -0.039 |
Token | so |
Token ID | 523 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
so | +0.000 |
pin | +0.000 |
first | +0.000 |
Neg logit contributions | |
anne | -0.002 |
beard | -0.002 |
rina | -0.002 |
jo | -0.002 |
helicopters | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
rina | +0.006 |
anne | +0.005 |
jo | +0.005 |
beard | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
first | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
but | -0.000 |
pin | -0.000 |
cater | -0.000 |
Token | bear |
Token ID | 6842 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.018 |
pin | +0.017 |
cater | +0.016 |
but | +0.016 |
Neg logit contributions | |
beard | -0.025 |
rina | -0.025 |
anne | -0.024 |
helicopters | -0.024 |
jo | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
lipstick | +0.015 |
P | +0.014 |
pin | +0.013 |
cater | +0.013 |
but | +0.013 |
Neg logit contributions | |
rina | -0.025 |
helicopters | -0.024 |
anne | -0.024 |
rockets | -0.024 |
jo | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
cent | +0.004 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
jo | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
rina | +0.002 |
anne | +0.002 |
jo | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.001 |
cater | -0.001 |
first | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
anne | +0.007 |
beard | +0.007 |
rina | +0.007 |
jo | +0.007 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.005 |
Fro | -0.005 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.016 |
pin | +0.014 |
cater | +0.014 |
Fro | +0.014 |
Neg logit contributions | |
beard | -0.018 |
rina | -0.018 |
helicopters | -0.017 |
anne | -0.017 |
jo | -0.017 |
Token | ter |
Token ID | 353 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
lipstick | +0.059 |
P | +0.049 |
Jade | +0.043 |
Gw | +0.042 |
cent | +0.042 |
Neg logit contributions | |
beard | -0.071 |
rina | -0.067 |
helicopters | -0.065 |
jo | -0.065 |
anne | -0.063 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
lipstick | +0.020 |
P | +0.019 |
pin | +0.019 |
cater | +0.018 |
but | +0.017 |
Neg logit contributions | |
rina | -0.033 |
helicopters | -0.033 |
anne | -0.033 |
rockets | -0.033 |
jo | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
beard | +0.012 |
helicopters | +0.011 |
rockets | +0.011 |
rina | +0.011 |
anne | +0.011 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.007 |
cater | -0.007 |
pin | -0.007 |
cent | -0.007 |
Token | cane |
Token ID | 33009 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.007 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
beard | -0.010 |
jo | -0.010 |
helicopters | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.010 |
pin | +0.009 |
cater | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
anne | -0.021 |
beard | -0.021 |
rina | -0.021 |
helicopters | -0.021 |
rockets | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
cater | +0.000 |
pin | +0.000 |
Jade | +0.000 |
Neg logit contributions | |
beard | -0.000 |
anne | -0.000 |
jo | -0.000 |
rina | -0.000 |
rockets | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
P | +0.006 |
lipstick | +0.006 |
but | +0.005 |
Fro | +0.005 |
first | +0.005 |
Neg logit contributions | |
rina | -0.011 |
anne | -0.011 |
beard | -0.010 |
helicopters | -0.010 |
jo | -0.010 |
Token | blinked |
Token ID | 40360 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
jo | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.000 |
pin | +0.000 |
cater | +0.000 |
first | +0.000 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
jo | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
P | +0.009 |
lipstick | +0.008 |
Jade | +0.008 |
Yes | +0.008 |
Pam | +0.007 |
Neg logit contributions | |
rockets | -0.006 |
helicopters | -0.006 |
rina | -0.006 |
aliens | -0.006 |
anne | -0.006 |
Token | eyel |
Token ID | 29708 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
Jade | +0.004 |
Yes | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
rockets | -0.005 |
Token | ashes |
Token ID | 7465 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
lipstick | +0.071 |
P | +0.065 |
pin | +0.063 |
cater | +0.063 |
first | +0.063 |
Neg logit contributions | |
anne | -0.053 |
jo | -0.050 |
rina | -0.048 |
beard | -0.047 |
der | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.019 |
Gw | +0.017 |
Jade | +0.017 |
Yes | +0.016 |
Neg logit contributions | |
rockets | -0.031 |
anne | -0.031 |
jo | -0.030 |
helicopters | -0.030 |
beard | -0.030 |
Token | kept |
Token ID | 4030 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
lipstick | +0.034 |
P | +0.030 |
pin | +0.028 |
cater | +0.028 |
Fro | +0.027 |
Neg logit contributions | |
anne | -0.036 |
rina | -0.036 |
beard | -0.035 |
jo | -0.035 |
rockets | -0.034 |
Token | hopping |
Token ID | 47153 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
rina | +0.015 |
anne | +0.014 |
helicopters | +0.014 |
beard | +0.014 |
rockets | +0.014 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
cater | -0.008 |
pin | -0.008 |
Fro | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
beard | +0.003 |
anne | +0.003 |
jo | +0.002 |
rina | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
Jade | -0.003 |
Token | From |
Token ID | 4863 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
anne | +0.001 |
rina | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
first | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
cent | +0.007 |
cater | +0.007 |
pin | +0.007 |
Neg logit contributions | |
beard | -0.009 |
rina | -0.008 |
helicopters | -0.008 |
anne | -0.008 |
rockets | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
anne | -0.011 |
rina | -0.011 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
lipstick | +0.022 |
cater | +0.017 |
P | +0.017 |
pin | +0.017 |
makeup | +0.016 |
Neg logit contributions | |
rina | -0.033 |
anne | -0.033 |
jo | -0.033 |
helicopters | -0.032 |
rockets | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
helicopters | +0.005 |
beard | +0.005 |
rockets | +0.005 |
rina | +0.005 |
anne | +0.005 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
pin | -0.002 |
cent | -0.002 |
cater | -0.002 |
Token | ot |
Token ID | 30972 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.018 |
pin | +0.016 |
cater | +0.016 |
cent | +0.016 |
Neg logit contributions | |
beard | -0.025 |
rina | -0.025 |
anne | -0.025 |
helicopters | -0.024 |
jo | -0.024 |
Token | ter |
Token ID | 353 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
lipstick | +0.061 |
P | +0.047 |
brush | +0.044 |
Gw | +0.042 |
makeup | +0.042 |
Neg logit contributions | |
beard | -0.071 |
rina | -0.064 |
helicopters | -0.064 |
eer | -0.061 |
anne | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
lipstick | +0.029 |
P | +0.028 |
pin | +0.027 |
cater | +0.026 |
first | +0.025 |
Neg logit contributions | |
anne | -0.041 |
rina | -0.041 |
helicopters | -0.040 |
jo | -0.040 |
beard | -0.040 |
Token | always |
Token ID | 1464 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
jo | +0.010 |
beard | +0.010 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
first | -0.005 |
Token | careful |
Token ID | 8161 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
Fro | +0.001 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
beard | -0.002 |
jo | -0.002 |
helicopters | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
pin | +0.006 |
cater | +0.005 |
first | +0.005 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
beard | -0.007 |
helicopters | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
anne | +0.030 |
rina | +0.030 |
jo | +0.029 |
beard | +0.029 |
helicopters | +0.028 |
Neg logit contributions | |
lipstick | -0.028 |
P | -0.025 |
pin | -0.023 |
cater | -0.023 |
Fro | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
lipstick | +0.002 |
Watch | +0.002 |
P | +0.001 |
cent | +0.001 |
cater | +0.001 |
Neg logit contributions | |
rina | -0.002 |
helicopters | -0.002 |
anne | -0.002 |
rockets | -0.002 |
jo | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
Pam | +0.002 |
Fro | +0.002 |
Jade | +0.002 |
Neg logit contributions | |
anne | -0.002 |
helicopters | -0.002 |
rockets | -0.002 |
rina | -0.002 |
beard | -0.002 |
Token | j |
Token ID | 474 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
Fro | +0.001 |
pin | +0.001 |
Pam | +0.001 |
Neg logit contributions | |
anne | -0.002 |
beard | -0.002 |
helicopters | -0.002 |
rina | -0.002 |
rockets | -0.002 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
anne | +0.005 |
jo | +0.004 |
beard | +0.004 |
rina | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
Fro | -0.003 |
but | -0.003 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
rina | +0.111 |
anne | +0.105 |
jo | +0.103 |
announcements | +0.101 |
helicopters | +0.100 |
Neg logit contributions | |
lipstick | -0.097 |
pin | -0.084 |
cater | -0.084 |
but | -0.084 |
first | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
anne | +0.026 |
jo | +0.025 |
rina | +0.025 |
rockets | +0.025 |
beard | +0.025 |
Neg logit contributions | |
lipstick | -0.018 |
P | -0.017 |
Fro | -0.015 |
pin | -0.014 |
cater | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
jo | +0.008 |
beard | +0.007 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
Fro | -0.004 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.011 |
cater | +0.010 |
first | +0.010 |
Neg logit contributions | |
rina | -0.016 |
anne | -0.016 |
beard | -0.016 |
helicopters | -0.015 |
jo | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
anne | +0.017 |
rina | +0.017 |
jo | +0.016 |
beard | +0.016 |
helicopters | +0.016 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.004 |
first | -0.004 |
Token | box |
Token ID | 3091 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.013 |
pin | +0.011 |
cater | +0.011 |
Fro | +0.011 |
Neg logit contributions | |
rina | -0.020 |
anne | -0.020 |
beard | -0.019 |
jo | -0.019 |
helicopters | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
rockets | +0.003 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
cater | -0.001 |
pin | -0.001 |
Fro | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
anne | -0.014 |
rina | -0.014 |
beard | -0.014 |
jo | -0.014 |
helicopters | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | j |
Token ID | 474 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
pin | +0.000 |
cater | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
beard | -0.001 |
jo | -0.001 |
helicopters | -0.000 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
anne | +0.006 |
rina | +0.006 |
jo | +0.006 |
beard | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
but | -0.003 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
rina | +0.121 |
anne | +0.115 |
jo | +0.114 |
announcements | +0.112 |
helicopters | +0.110 |
Neg logit contributions | |
lipstick | -0.077 |
with | -0.068 |
but | -0.067 |
pin | -0.066 |
first | -0.065 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rina | +0.035 |
anne | +0.035 |
jo | +0.034 |
beard | +0.033 |
helicopters | +0.033 |
Neg logit contributions | |
lipstick | -0.019 |
P | -0.017 |
pin | -0.016 |
cater | -0.015 |
but | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
but | +0.002 |
Neg logit contributions | |
rina | -0.003 |
anne | -0.003 |
jo | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.001 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
jo | -0.002 |
beard | -0.002 |
helicopters | -0.002 |
Token | paused |
Token ID | 24487 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
pin | +0.005 |
cater | +0.005 |
first | +0.005 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
jo | -0.008 |
beard | -0.008 |
helicopters | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.006 |
beard | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
first | -0.006 |
Token | take |
Token ID | 1011 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | out |
Token ID | 503 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.007 |
beard | +0.007 |
opter | +0.006 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
so | -0.003 |
first | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
rockets | +0.018 |
helicopters | +0.018 |
beard | +0.018 |
rina | +0.018 |
anne | +0.018 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
cater | -0.013 |
pin | -0.013 |
Fro | -0.013 |
Token | j |
Token ID | 474 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
Fro | +0.004 |
pin | +0.004 |
cater | +0.004 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
beard | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
but | +0.006 |
Neg logit contributions | |
anne | -0.009 |
jo | -0.009 |
beard | -0.008 |
rina | -0.008 |
rockets | -0.008 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
rina | +0.088 |
anne | +0.084 |
jo | +0.081 |
helicopters | +0.079 |
announcements | +0.079 |
Neg logit contributions | |
lipstick | -0.093 |
first | -0.081 |
pin | -0.081 |
but | -0.081 |
cater | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
rockets | +0.024 |
beard | +0.024 |
jo | +0.023 |
anne | +0.023 |
helicopters | +0.023 |
Neg logit contributions | |
lipstick | -0.015 |
P | -0.014 |
Fro | -0.012 |
cater | -0.011 |
pin | -0.011 |
Token | try |
Token ID | 1949 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
cater | +0.003 |
pin | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
beard | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
but | +0.001 |
pin | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.003 |
rina | -0.003 |
jo | -0.003 |
beard | -0.003 |
opter | -0.003 |
Token | solve |
Token ID | 8494 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.015 |
rina | -0.015 |
jo | -0.015 |
beard | -0.015 |
helicopters | -0.015 |
Token | Mia |
Token ID | 32189 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
lipstick | +0.010 |
pin | +0.008 |
P | +0.008 |
cater | +0.008 |
cent | +0.008 |
Neg logit contributions | |
anne | -0.013 |
rina | -0.013 |
rockets | -0.013 |
aliens | -0.012 |
jo | -0.012 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
rina | +0.006 |
anne | +0.006 |
beard | +0.006 |
helicopters | +0.006 |
jo | +0.006 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
first | -0.004 |
cater | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
first | +0.005 |
Neg logit contributions | |
anne | -0.019 |
rina | -0.019 |
jo | -0.019 |
beard | -0.018 |
helicopters | -0.018 |
Token | great |
Token ID | 1049 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.000 |
cater | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
rina | -0.001 |
anne | -0.001 |
helicopters | -0.001 |
beard | -0.001 |
rockets | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rina | +0.014 |
jo | +0.014 |
anne | +0.013 |
beard | +0.012 |
storms | +0.012 |
Neg logit contributions | |
lipstick | -0.009 |
pin | -0.008 |
P | -0.008 |
cater | -0.008 |
first | -0.008 |
Token | Fer |
Token ID | 12880 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
but | +0.004 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
jo | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
Token | ris |
Token ID | 2442 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
rina | +0.054 |
anne | +0.053 |
helicopters | +0.049 |
beard | +0.049 |
jo | +0.049 |
Neg logit contributions | |
lipstick | -0.115 |
P | -0.107 |
pin | -0.103 |
first | -0.101 |
cater | -0.101 |
Token | wheel |
Token ID | 7825 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
rina | +0.052 |
anne | +0.051 |
jo | +0.049 |
beard | +0.049 |
helicopters | +0.046 |
Neg logit contributions | |
lipstick | -0.044 |
first | -0.039 |
pin | -0.038 |
P | -0.038 |
but | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
anne | +0.018 |
rina | +0.017 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.013 |
cater | -0.012 |
pin | -0.012 |
Fro | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
cater | +0.002 |
Fro | +0.002 |
pin | +0.002 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
helicopters | -0.002 |
rockets | -0.002 |
jo | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
rina | +0.033 |
beard | +0.033 |
jo | +0.032 |
anne | +0.032 |
helicopters | +0.031 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.011 |
pin | -0.010 |
so | -0.009 |
first | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
anne | +0.001 |
rina | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
first | -0.000 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
rina | +0.012 |
anne | +0.012 |
beard | +0.012 |
jo | +0.012 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
cater | -0.008 |
pin | -0.008 |
but | -0.008 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
beard | -0.001 |
jo | -0.001 |
helicopters | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
helicopters | -0.008 |
jo | -0.008 |
rockets | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
pin | +0.000 |
Pam | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
anne | -0.000 |
helicopters | -0.000 |
rina | -0.000 |
rockets | -0.000 |
beard | -0.000 |
Token | Fer |
Token ID | 12880 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
anne | +0.000 |
rina | +0.000 |
helicopters | +0.000 |
jo | +0.000 |
beard | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
Fro | -0.000 |
Token | ris |
Token ID | 2442 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
rina | +0.059 |
anne | +0.059 |
beard | +0.056 |
jo | +0.056 |
helicopters | +0.055 |
Neg logit contributions | |
lipstick | -0.094 |
P | -0.088 |
pin | -0.083 |
cater | -0.082 |
first | -0.080 |
Token | wheel |
Token ID | 7825 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
rina | +0.053 |
anne | +0.052 |
beard | +0.051 |
jo | +0.050 |
aliens | +0.048 |
Neg logit contributions | |
lipstick | -0.047 |
pin | -0.041 |
first | -0.041 |
P | -0.040 |
but | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
anne | +0.014 |
jo | +0.014 |
rina | +0.014 |
helicopters | +0.014 |
beard | +0.013 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
cater | -0.007 |
pin | -0.007 |
Fro | -0.007 |
Token | most |
Token ID | 749 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
rina | +0.010 |
anne | +0.010 |
helicopters | +0.010 |
beard | +0.010 |
jo | +0.010 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.006 |
cater | -0.006 |
Fro | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
Fro | +0.008 |
cater | +0.008 |
Neg logit contributions | |
anne | -0.014 |
rina | -0.014 |
jo | -0.014 |
helicopters | -0.014 |
beard | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
so | +0.000 |
pin | +0.000 |
cater | +0.000 |
Neg logit contributions | |
anne | -0.000 |
rina | -0.000 |
jo | -0.000 |
beard | -0.000 |
opter | -0.000 |
Token | big |
Token ID | 1263 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
anne | +0.016 |
rina | +0.016 |
beard | +0.015 |
helicopters | +0.015 |
rockets | +0.015 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
pin | -0.008 |
Fro | -0.008 |
Pam | -0.008 |
Token | camera |
Token ID | 4676 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
anne | +0.013 |
helicopters | +0.013 |
beard | +0.013 |
rockets | +0.013 |
rina | +0.013 |
Neg logit contributions | |
lipstick | -0.012 |
P | -0.012 |
pin | -0.010 |
Fro | -0.010 |
cater | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
anne | +0.023 |
rina | +0.023 |
jo | +0.023 |
beard | +0.023 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.012 |
P | -0.011 |
pin | -0.010 |
cater | -0.010 |
first | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
anne | +0.013 |
rina | +0.013 |
jo | +0.012 |
beard | +0.012 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.003 |
cater | -0.003 |
first | -0.003 |
Token | tripod |
Token ID | 47439 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
rina | +0.019 |
anne | +0.018 |
jo | +0.018 |
beard | +0.018 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.012 |
pin | -0.011 |
cater | -0.011 |
first | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rina | +0.087 |
anne | +0.087 |
beard | +0.085 |
jo | +0.084 |
helicopters | +0.083 |
Neg logit contributions | |
lipstick | -0.055 |
P | -0.049 |
pin | -0.046 |
but | -0.045 |
first | -0.044 |
Token | It |
Token ID | 632 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
anne | +0.002 |
beard | +0.002 |
rina | +0.002 |
jo | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
pin | -0.002 |
P | -0.002 |
cater | -0.002 |
cent | -0.002 |
Token | belongs |
Token ID | 14448 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
anne | +0.024 |
rina | +0.024 |
jo | +0.023 |
helicopters | +0.023 |
beard | +0.023 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
pin | -0.015 |
first | -0.014 |
called | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
lipstick | +0.008 |
cater | +0.007 |
Watch | +0.007 |
P | +0.007 |
Fro | +0.007 |
Neg logit contributions | |
rockets | -0.009 |
beard | -0.009 |
rina | -0.009 |
anne | -0.009 |
jo | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.016 |
pin | +0.014 |
cater | +0.014 |
first | +0.013 |
Neg logit contributions | |
anne | -0.039 |
rina | -0.039 |
jo | -0.038 |
beard | -0.038 |
helicopters | -0.037 |
Token | with |
Token ID | 351 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
beard | +0.005 |
rina | +0.005 |
anne | +0.005 |
jo | +0.005 |
rockets | +0.005 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
Gw | -0.003 |
Token | fries |
Token ID | 31757 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.009 |
pin | +0.009 |
cater | +0.009 |
Fro | +0.008 |
Neg logit contributions | |
rina | -0.012 |
helicopters | -0.012 |
beard | -0.012 |
anne | -0.012 |
rockets | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.009 |
cater | +0.009 |
pin | +0.009 |
Pam | +0.008 |
Neg logit contributions | |
beard | -0.014 |
rina | -0.014 |
anne | -0.014 |
rockets | -0.014 |
jo | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
beard | +0.007 |
jo | +0.007 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
first | -0.007 |
Token | mil |
Token ID | 1465 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
anne | +0.023 |
beard | +0.022 |
rina | +0.022 |
jo | +0.022 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.017 |
P | -0.016 |
cater | -0.014 |
Pam | -0.014 |
pin | -0.014 |
Token | ksh |
Token ID | 50133 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.008 |
pin | +0.007 |
cater | +0.007 |
Fro | +0.007 |
Neg logit contributions | |
rina | -0.003 |
anne | -0.003 |
jo | -0.003 |
helicopters | -0.003 |
beard | -0.003 |
Token | ake |
Token ID | 539 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
helicopters | +0.065 |
aliens | +0.064 |
rina | +0.063 |
rockets | +0.062 |
announcements | +0.061 |
Neg logit contributions | |
lipstick | -0.072 |
P | -0.065 |
first | -0.058 |
cent | -0.057 |
pin | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
anne | +0.023 |
rina | +0.023 |
jo | +0.022 |
beard | +0.022 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.017 |
P | -0.016 |
pin | -0.014 |
cater | -0.014 |
Fro | -0.014 |
Token | But |
Token ID | 887 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
anne | +0.000 |
helicopters | +0.000 |
jo | +0.000 |
rina | +0.000 |
rockets | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
pin | -0.000 |
cater | -0.000 |
cent | -0.000 |
first | -0.000 |
Token | after |
Token ID | 706 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
rina | +0.008 |
helicopters | +0.007 |
anne | +0.007 |
rockets | +0.007 |
marsh | +0.007 |
Neg logit contributions | |
lipstick | -0.005 |
cent | -0.005 |
Watch | -0.005 |
P | -0.005 |
cater | -0.005 |
Token | eating |
Token ID | 6600 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
rina | +0.016 |
anne | +0.016 |
beard | +0.016 |
helicopters | +0.016 |
jo | +0.016 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.010 |
pin | -0.009 |
cater | -0.009 |
Fro | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
rina | +0.012 |
anne | +0.011 |
helicopters | +0.011 |
beard | +0.011 |
rockets | +0.011 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
but | -0.006 |
called | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
anne | +0.015 |
rina | +0.015 |
jo | +0.015 |
beard | +0.015 |
helicopters | +0.015 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.004 |
cater | -0.004 |
Fro | -0.004 |
Token | bounce |
Token ID | 20110 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
cater | +0.007 |
cent | +0.007 |
pin | +0.007 |
Neg logit contributions | |
anne | -0.012 |
helicopters | -0.012 |
rina | -0.012 |
jo | -0.012 |
beard | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
cater | +0.005 |
Diane | +0.005 |
cent | +0.005 |
Neg logit contributions | |
beard | -0.008 |
rockets | -0.008 |
helicopters | -0.008 |
aliens | -0.008 |
jo | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.004 |
cater | +0.004 |
cent | +0.004 |
Neg logit contributions | |
helicopters | -0.010 |
rockets | -0.010 |
rina | -0.010 |
beard | -0.010 |
anne | -0.010 |
Token | tr |
Token ID | 491 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
helicopters | +0.001 |
rockets | +0.001 |
anne | +0.001 |
beard | +0.001 |
jo | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
Pam | -0.001 |
Fro | -0.001 |
pin | -0.001 |
Token | amp |
Token ID | 696 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
rina | +0.073 |
anne | +0.072 |
beard | +0.070 |
jo | +0.070 |
helicopters | +0.069 |
Neg logit contributions | |
lipstick | -0.065 |
P | -0.059 |
pin | -0.054 |
cater | -0.053 |
Fro | -0.052 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
anne | +0.030 |
rina | +0.030 |
jo | +0.028 |
beard | +0.028 |
helicopters | +0.027 |
Neg logit contributions | |
lipstick | -0.090 |
P | -0.086 |
pin | -0.082 |
cater | -0.081 |
first | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
anne | +0.028 |
jo | +0.027 |
rina | +0.027 |
beard | +0.027 |
helicopters | +0.026 |
Neg logit contributions | |
lipstick | -0.022 |
P | -0.020 |
pin | -0.018 |
cater | -0.018 |
Pam | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.001 |
cent | +0.001 |
Diane | +0.001 |
arant | +0.001 |
Neg logit contributions | |
helicopters | -0.004 |
rockets | -0.004 |
anne | -0.004 |
jo | -0.004 |
hikes | -0.004 |
Token | Mia |
Token ID | 32189 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.006 |
cater | +0.006 |
cent | +0.006 |
pin | +0.006 |
Neg logit contributions | |
rina | -0.008 |
anne | -0.008 |
jo | -0.008 |
beard | -0.008 |
rockets | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
anne | +0.022 |
rina | +0.022 |
jo | +0.022 |
beard | +0.022 |
helicopters | +0.021 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
pin | -0.008 |
cater | -0.008 |
first | -0.007 |
Token | powerful |
Token ID | 3665 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
anne | +0.023 |
beard | +0.023 |
rina | +0.023 |
helicopters | +0.022 |
rockets | +0.022 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
pin | -0.013 |
Pam | -0.012 |
Fro | -0.012 |
Token | z |
Token ID | 1976 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
anne | +0.009 |
rina | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
jo | +0.008 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
pin | -0.008 |
Fro | -0.008 |
first | -0.008 |
Token | ebra |
Token ID | 37052 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
beard | +0.007 |
rina | +0.007 |
jo | +0.007 |
anne | +0.007 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.012 |
P | -0.012 |
but | -0.011 |
so | -0.011 |
Pam | -0.010 |
Token | named |
Token ID | 3706 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
anne | +0.013 |
rina | +0.013 |
jo | +0.013 |
beard | +0.013 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
Pam | -0.005 |
Token | Zig |
Token ID | 24992 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
lipstick | +0.019 |
P | +0.017 |
pin | +0.016 |
cater | +0.016 |
first | +0.015 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.024 |
jo | -0.024 |
beard | -0.023 |
helicopters | -0.023 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
helicopters | +0.058 |
happens | +0.056 |
rockets | +0.055 |
anne | +0.055 |
aliens | +0.053 |
Neg logit contributions | |
lipstick | -0.070 |
P | -0.069 |
first | -0.068 |
Fro | -0.067 |
cater | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
anne | +0.034 |
rina | +0.033 |
beard | +0.032 |
jo | +0.032 |
helicopters | +0.031 |
Neg logit contributions | |
lipstick | -0.024 |
P | -0.022 |
cater | -0.020 |
pin | -0.020 |
but | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
anne | +0.015 |
rina | +0.015 |
beard | +0.014 |
jo | +0.014 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.020 |
P | -0.020 |
but | -0.018 |
cater | -0.018 |
Fro | -0.018 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
but | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
rockets | +0.005 |
beard | +0.005 |
helicopters | +0.005 |
aliens | +0.004 |
rina | +0.004 |
Neg logit contributions | |
lipstick | -0.004 |
Jade | -0.004 |
P | -0.003 |
Diane | -0.003 |
Pam | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
anne | +0.014 |
helicopters | +0.013 |
jo | +0.013 |
rina | +0.013 |
rockets | +0.013 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
Fro | -0.008 |
cater | -0.007 |
pin | -0.007 |
Token | lots |
Token ID | 6041 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.011 |
rina | -0.011 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
anne | +0.015 |
rina | +0.015 |
jo | +0.015 |
beard | +0.015 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
first | -0.005 |
Token | rocks |
Token ID | 12586 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
rina | +0.002 |
anne | +0.002 |
beard | +0.002 |
jo | +0.002 |
storms | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
cater | -0.001 |
pin | -0.001 |
but | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
rina | +0.024 |
anne | +0.024 |
jo | +0.023 |
beard | +0.023 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.012 |
P | -0.010 |
pin | -0.009 |
but | -0.009 |
cater | -0.009 |
Token | steep |
Token ID | 14559 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
anne | +0.016 |
rina | +0.016 |
jo | +0.015 |
beard | +0.015 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.012 |
P | -0.011 |
cater | -0.010 |
pin | -0.010 |
but | -0.010 |
Token | hills |
Token ID | 18639 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
anne | +0.092 |
rina | +0.092 |
jo | +0.088 |
beard | +0.085 |
onda | +0.083 |
Neg logit contributions | |
lipstick | -0.046 |
but | -0.045 |
pin | -0.040 |
by | -0.040 |
past | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
rina | +0.061 |
anne | +0.060 |
jo | +0.058 |
beard | +0.058 |
helicopters | +0.054 |
Neg logit contributions | |
lipstick | -0.028 |
but | -0.027 |
P | -0.026 |
with | -0.025 |
first | -0.025 |
Token | But |
Token ID | 887 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
rina | +0.013 |
anne | +0.013 |
jo | +0.013 |
beard | +0.013 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
but | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
helicopters | +0.010 |
beard | +0.010 |
rina | +0.010 |
rockets | +0.010 |
anne | +0.009 |
Neg logit contributions | |
lipstick | -0.009 |
cater | -0.008 |
cent | -0.008 |
P | -0.008 |
pin | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
cater | +0.003 |
pin | +0.003 |
Pam | +0.003 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.003 |
jo | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
helicopters | +0.002 |
rockets | +0.001 |
motors | +0.001 |
jo | +0.001 |
anne | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
Fro | -0.001 |
Pam | -0.001 |
Jade | -0.001 |
Token | sc |
Token ID | 629 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
helicopters | +0.011 |
rockets | +0.011 |
anne | +0.011 |
rina | +0.010 |
jo | +0.010 |
Neg logit contributions | |
P | -0.010 |
lipstick | -0.009 |
Fro | -0.008 |
Pam | -0.008 |
Jade | -0.008 |
Token | ooter |
Token ID | 25141 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
P | +0.014 |
lipstick | +0.014 |
cater | +0.013 |
Fro | +0.012 |
pin | +0.012 |
Neg logit contributions | |
jo | -0.016 |
anne | -0.015 |
helicopters | -0.014 |
opter | -0.013 |
rina | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
jo | +0.002 |
anne | +0.002 |
helicopters | +0.002 |
rockets | +0.002 |
rina | +0.002 |
Neg logit contributions | |
P | -0.001 |
lipstick | -0.001 |
Fro | -0.001 |
Pam | -0.001 |
cater | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
Fro | +0.005 |
cater | +0.005 |
pin | +0.005 |
Neg logit contributions | |
anne | -0.010 |
helicopters | -0.010 |
rina | -0.010 |
jo | -0.010 |
rockets | -0.010 |
Token | tr |
Token ID | 491 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
helicopters | +0.015 |
rockets | +0.014 |
anne | +0.014 |
rina | +0.014 |
jo | +0.014 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.013 |
Fro | -0.012 |
Pam | -0.011 |
Jade | -0.011 |
Token | icycle |
Token ID | 35298 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
rina | +0.066 |
anne | +0.066 |
beard | +0.065 |
helicopters | +0.063 |
jo | +0.062 |
Neg logit contributions | |
lipstick | -0.066 |
P | -0.058 |
pin | -0.056 |
cater | -0.053 |
first | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
jo | +0.008 |
beard | +0.007 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.007 |
pin | -0.006 |
cater | -0.006 |
Fro | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
beard | +0.002 |
rina | +0.002 |
opter | +0.002 |
anne | +0.002 |
jo | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
but | -0.001 |
P | -0.001 |
so | -0.000 |
with | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
beard | +0.004 |
jo | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
pin | -0.003 |
P | -0.003 |
first | -0.003 |
but | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
pin | +0.000 |
cater | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
anne | -0.000 |
rina | -0.000 |
jo | -0.000 |
helicopters | -0.000 |
beard | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.019 |
pin | +0.017 |
cater | +0.017 |
Fro | +0.017 |
Neg logit contributions | |
anne | -0.025 |
rina | -0.025 |
jo | -0.025 |
helicopters | -0.025 |
rockets | -0.025 |
Token | all |
Token ID | 477 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
anne | +0.004 |
rina | +0.004 |
beard | +0.004 |
jo | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
but | -0.003 |
first | -0.003 |
pin | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
rina | +0.016 |
anne | +0.016 |
beard | +0.016 |
jo | +0.016 |
helicopters | +0.015 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
but | -0.007 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
anne | +0.011 |
rina | +0.011 |
jo | +0.010 |
beard | +0.010 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.007 |
cater | -0.006 |
first | -0.006 |
Token | things |
Token ID | 1243 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
rina | +0.012 |
anne | +0.011 |
beard | +0.011 |
jo | +0.011 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.007 |
but | -0.006 |
pin | -0.006 |
first | -0.006 |
Token | Jo |
Token ID | 5302 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
rina | +0.022 |
anne | +0.022 |
jo | +0.021 |
beard | +0.021 |
helicopters | +0.020 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.012 |
pin | -0.011 |
but | -0.011 |
first | -0.010 |
Token | jo |
Token ID | 7639 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
lighthouse | +0.027 |
rockets | +0.026 |
helicopters | +0.026 |
beard | +0.025 |
aliens | +0.023 |
Neg logit contributions | |
lipstick | -0.092 |
but | -0.092 |
by | -0.091 |
first | -0.091 |
called | -0.089 |
Token | made |
Token ID | 925 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
rina | +0.052 |
beard | +0.050 |
anne | +0.050 |
helicopters | +0.050 |
rockets | +0.049 |
Neg logit contributions | |
lipstick | -0.031 |
pin | -0.028 |
P | -0.028 |
but | -0.026 |
cater | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
cater | +0.008 |
pin | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
rina | -0.009 |
jo | -0.009 |
anne | -0.009 |
helicopters | -0.009 |
beard | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
beard | +0.009 |
rina | +0.009 |
helicopters | +0.009 |
anne | +0.009 |
opter | +0.008 |
Neg logit contributions | |
P | -0.004 |
L | -0.003 |
but | -0.003 |
lipstick | -0.003 |
first | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
P | +0.004 |
lipstick | +0.004 |
but | +0.004 |
first | +0.004 |
with | +0.003 |
Neg logit contributions | |
rina | -0.010 |
anne | -0.010 |
beard | -0.010 |
helicopters | -0.010 |
rockets | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | backyard |
Token ID | 24296 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
cater | +0.009 |
pin | +0.009 |
first | +0.008 |
Neg logit contributions | |
rina | -0.013 |
anne | -0.013 |
jo | -0.013 |
beard | -0.013 |
helicopters | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
anne | +0.018 |
rina | +0.018 |
jo | +0.018 |
beard | +0.018 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.006 |
but | -0.006 |
cater | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
anne | +0.021 |
rina | +0.020 |
jo | +0.020 |
beard | +0.019 |
opter | +0.019 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.005 |
first | -0.004 |
but | -0.004 |
cater | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
rina | +0.018 |
anne | +0.018 |
jo | +0.018 |
beard | +0.018 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
cater | -0.008 |
pin | -0.008 |
first | -0.007 |
Token | tr |
Token ID | 491 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
rina | +0.018 |
anne | +0.017 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.011 |
pin | -0.010 |
cater | -0.010 |
but | -0.010 |
Token | amp |
Token ID | 696 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
rina | +0.075 |
anne | +0.073 |
helicopters | +0.072 |
beard | +0.072 |
jo | +0.071 |
Neg logit contributions | |
lipstick | -0.055 |
P | -0.049 |
pin | -0.045 |
cater | -0.044 |
first | -0.043 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
rina | +0.034 |
beard | +0.033 |
anne | +0.032 |
jo | +0.031 |
helicopters | +0.031 |
Neg logit contributions | |
lipstick | -0.076 |
P | -0.071 |
pin | -0.068 |
cater | -0.068 |
first | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
rina | +0.036 |
anne | +0.035 |
jo | +0.034 |
beard | +0.034 |
helicopters | +0.034 |
Neg logit contributions | |
lipstick | -0.024 |
P | -0.022 |
pin | -0.020 |
cater | -0.020 |
but | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
rina | +0.009 |
anne | +0.009 |
helicopters | +0.008 |
jo | +0.008 |
beard | +0.008 |
Neg logit contributions | |
P | -0.005 |
lipstick | -0.005 |
but | -0.004 |
Fro | -0.004 |
pin | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
rina | +0.008 |
anne | +0.008 |
helicopters | +0.008 |
beard | +0.007 |
rockets | +0.007 |
Neg logit contributions | |
P | -0.003 |
lipstick | -0.003 |
but | -0.003 |
with | -0.002 |
first | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
helicopters | +0.008 |
rockets | +0.008 |
anne | +0.007 |
rina | +0.007 |
beard | +0.007 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
pin | -0.003 |
Fro | -0.003 |
cater | -0.003 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
rina | +0.043 |
anne | +0.042 |
jo | +0.042 |
beard | +0.042 |
helicopters | +0.041 |
Neg logit contributions | |
lipstick | -0.024 |
P | -0.021 |
pin | -0.019 |
cater | -0.018 |
Fro | -0.017 |
Token | building |
Token ID | 2615 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
beard | +0.009 |
jo | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.005 |
but | -0.004 |
Token | ig |
Token ID | 45329 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
rina | +0.030 |
anne | +0.030 |
jo | +0.029 |
beard | +0.029 |
helicopters | +0.029 |
Neg logit contributions | |
lipstick | -0.021 |
P | -0.019 |
pin | -0.017 |
cater | -0.017 |
Fro | -0.016 |
Token | lo |
Token ID | 5439 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
anne | +0.013 |
rina | +0.013 |
jo | +0.013 |
beard | +0.013 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.031 |
P | -0.030 |
cater | -0.028 |
pin | -0.028 |
Fro | -0.027 |
Token | os |
Token ID | 418 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
aliens | +0.066 |
rina | +0.064 |
beard | +0.062 |
helicopters | +0.061 |
rockets | +0.060 |
Neg logit contributions | |
lipstick | -0.057 |
first | -0.055 |
P | -0.054 |
called | -0.054 |
pin | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
anne | +0.050 |
rina | +0.050 |
jo | +0.047 |
beard | +0.047 |
helicopters | +0.044 |
Neg logit contributions | |
lipstick | -0.026 |
P | -0.024 |
pin | -0.022 |
but | -0.021 |
with | -0.021 |
Token | One |
Token ID | 1881 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
first | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.009 |
cater | +0.008 |
first | +0.008 |
Neg logit contributions | |
rina | -0.015 |
anne | -0.015 |
beard | -0.014 |
jo | -0.014 |
helicopters | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.012 |
cater | +0.012 |
cent | +0.011 |
Neg logit contributions | |
anne | -0.022 |
jo | -0.021 |
rina | -0.021 |
helicopters | -0.021 |
rockets | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
helicopters | +0.003 |
rockets | +0.003 |
anne | +0.003 |
rina | +0.003 |
beard | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
Fro | -0.002 |
Pam | -0.002 |
Token | bounce |
Token ID | 20110 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.011 |
cater | +0.011 |
cent | +0.011 |
Neg logit contributions | |
anne | -0.023 |
beard | -0.023 |
rina | -0.023 |
helicopters | -0.023 |
jo | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
lipstick | +0.006 |
cater | +0.006 |
P | +0.006 |
cent | +0.005 |
Fro | +0.005 |
Neg logit contributions | |
rockets | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
aliens | -0.008 |
motors | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
Pam | +0.003 |
Neg logit contributions | |
helicopters | -0.006 |
rockets | -0.006 |
beard | -0.006 |
rina | -0.006 |
motors | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
Pam | +0.011 |
Fro | +0.011 |
pin | +0.011 |
Neg logit contributions | |
helicopters | -0.014 |
rockets | -0.014 |
beard | -0.013 |
rina | -0.013 |
anne | -0.013 |
Token | tr |
Token ID | 491 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
anne | +0.006 |
helicopters | +0.006 |
jo | +0.006 |
rockets | +0.006 |
beard | +0.006 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
Fro | -0.005 |
cater | -0.005 |
Token | amp |
Token ID | 696 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
rina | +0.071 |
anne | +0.070 |
beard | +0.069 |
jo | +0.068 |
helicopters | +0.067 |
Neg logit contributions | |
lipstick | -0.059 |
P | -0.053 |
pin | -0.048 |
cater | -0.048 |
first | -0.046 |
Token | oline |
Token ID | 14453 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
rina | +0.031 |
anne | +0.030 |
beard | +0.030 |
jo | +0.029 |
helicopters | +0.028 |
Neg logit contributions | |
lipstick | -0.079 |
P | -0.074 |
pin | -0.071 |
cater | -0.070 |
first | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
anne | +0.016 |
jo | +0.016 |
beard | +0.016 |
rockets | +0.016 |
rina | +0.016 |
Neg logit contributions | |
lipstick | -0.019 |
P | -0.017 |
cater | -0.016 |
pin | -0.016 |
Fro | -0.016 |
Token | their |
Token ID | 511 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | backyard |
Token ID | 24296 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
anne | +0.017 |
rockets | +0.017 |
jo | +0.017 |
rina | +0.016 |
helicopters | +0.016 |
Neg logit contributions | |
lipstick | -0.018 |
P | -0.016 |
pin | -0.015 |
cater | -0.015 |
Fro | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
anne | +0.023 |
rina | +0.023 |
jo | +0.023 |
beard | +0.023 |
helicopters | +0.023 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.012 |
pin | -0.011 |
cater | -0.010 |
first | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
jo | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.007 |
cater | -0.006 |
first | -0.006 |
Token | always |
Token ID | 1464 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
beard | +0.026 |
anne | +0.026 |
jo | +0.026 |
rina | +0.025 |
rockets | +0.025 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.011 |
pin | -0.010 |
so | -0.010 |
first | -0.010 |
Token | careful |
Token ID | 8161 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
anne | +0.012 |
rina | +0.012 |
beard | +0.012 |
jo | +0.012 |
helicopters | +0.012 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.005 |
Fro | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
rina | +0.000 |
anne | +0.000 |
beard | +0.000 |
jo | +0.000 |
helicopters | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
first | -0.000 |
Token | elev |
Token ID | 7662 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
rina | +0.007 |
helicopters | +0.007 |
anne | +0.007 |
jo | +0.007 |
rockets | +0.007 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.005 |
Fro | -0.005 |
Token | ators |
Token ID | 2024 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
anne | +0.030 |
beard | +0.028 |
rina | +0.028 |
jo | +0.027 |
helicopters | +0.026 |
Neg logit contributions | |
lipstick | -0.095 |
first | -0.090 |
P | -0.088 |
pin | -0.086 |
by | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
anne | +0.027 |
rina | +0.027 |
jo | +0.026 |
beard | +0.026 |
helicopters | +0.025 |
Neg logit contributions | |
lipstick | -0.018 |
P | -0.016 |
pin | -0.014 |
cater | -0.014 |
first | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
rina | +0.009 |
anne | +0.008 |
beard | +0.008 |
helicopters | +0.008 |
rockets | +0.008 |
Neg logit contributions | |
P | -0.004 |
lipstick | -0.003 |
Fro | -0.003 |
but | -0.003 |
L | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
rina | +0.017 |
anne | +0.017 |
helicopters | +0.016 |
beard | +0.016 |
jo | +0.016 |
Neg logit contributions | |
P | -0.008 |
lipstick | -0.008 |
with | -0.007 |
first | -0.007 |
by | -0.007 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
P | +0.005 |
lipstick | +0.005 |
first | +0.005 |
but | +0.004 |
by | +0.003 |
Neg logit contributions | |
rina | -0.037 |
helicopters | -0.037 |
anne | -0.036 |
beard | -0.036 |
motors | -0.036 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.000 |
first | +0.000 |
Neg logit contributions | |
anne | -0.001 |
rina | -0.001 |
jo | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
Token | even |
Token ID | 772 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
Fro | +0.003 |
pin | +0.003 |
cater | +0.003 |
Neg logit contributions | |
helicopters | -0.004 |
rina | -0.003 |
rockets | -0.003 |
anne | -0.003 |
jo | -0.003 |
Token | more |
Token ID | 517 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.006 |
Fro | +0.006 |
Jade | +0.006 |
Pam | +0.005 |
Neg logit contributions | |
helicopters | -0.008 |
rockets | -0.008 |
rina | -0.008 |
beard | -0.008 |
happens | -0.008 |
Token | about |
Token ID | 546 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
Fro | +0.005 |
pin | +0.005 |
Pam | +0.005 |
Neg logit contributions | |
helicopters | -0.003 |
rockets | -0.003 |
rina | -0.003 |
anne | -0.003 |
jo | -0.003 |
Token | how |
Token ID | 703 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.007 |
beard | +0.007 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
first | -0.003 |
Token | volcan |
Token ID | 17516 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
rina | +0.028 |
anne | +0.028 |
jo | +0.027 |
beard | +0.027 |
helicopters | +0.026 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.014 |
pin | -0.013 |
cater | -0.013 |
first | -0.012 |
Token | oes |
Token ID | 3028 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
anne | +0.082 |
rina | +0.082 |
beard | +0.080 |
jo | +0.079 |
helicopters | +0.078 |
Neg logit contributions | |
lipstick | -0.041 |
P | -0.036 |
first | -0.032 |
but | -0.032 |
pin | -0.032 |
Token | work |
Token ID | 670 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.005 |
cater | +0.004 |
but | +0.004 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
first | +0.004 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
jo | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
rina | +0.001 |
beard | +0.001 |
anne | +0.001 |
helicopters | +0.001 |
rockets | +0.001 |
Neg logit contributions | |
P | -0.001 |
lipstick | -0.001 |
cater | -0.000 |
Fro | -0.000 |
Pam | -0.000 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
anne | +0.001 |
jo | +0.001 |
rina | +0.001 |
helicopters | +0.001 |
beard | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
first | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
beard | -0.004 |
jo | -0.004 |
helicopters | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
first | +0.004 |
Neg logit contributions | |
rina | -0.008 |
beard | -0.008 |
anne | -0.008 |
jo | -0.008 |
helicopters | -0.008 |
Token | know |
Token ID | 760 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.016 |
cater | +0.014 |
Fro | +0.014 |
pin | +0.014 |
Neg logit contributions | |
anne | -0.029 |
rina | -0.029 |
jo | -0.028 |
helicopters | -0.028 |
beard | -0.027 |
Token | all |
Token ID | 477 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
Fro | +0.001 |
Neg logit contributions | |
rina | -0.001 |
anne | -0.001 |
jo | -0.001 |
helicopters | -0.001 |
beard | -0.001 |
Token | about |
Token ID | 546 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
Fro | +0.002 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
beard | -0.005 |
Token | microsc |
Token ID | 21145 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
rina | -0.007 |
anne | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
beard | -0.007 |
Token | opes |
Token ID | 13920 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Amen | +0.044 |
anne | +0.042 |
announcements | +0.039 |
rina | +0.039 |
helicopters | +0.038 |
Neg logit contributions | |
lipstick | -0.077 |
P | -0.071 |
first | -0.068 |
so | -0.067 |
cater | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
jo | +0.004 |
beard | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.001 |
but | -0.001 |
cater | -0.001 |
Token | |
Token ID | 220 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
but | +0.006 |
so | +0.005 |
first | +0.005 |
Neg logit contributions | |
beard | -0.015 |
rina | -0.015 |
jo | -0.015 |
anne | -0.014 |
rockets | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
but | +0.004 |
first | +0.004 |
with | +0.004 |
Neg logit contributions | |
beard | -0.013 |
rina | -0.013 |
helicopters | -0.013 |
rockets | -0.013 |
anne | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
lipstick | +0.005 |
first | +0.005 |
but | +0.005 |
with | +0.005 |
so | +0.005 |
Neg logit contributions | |
beard | -0.015 |
rina | -0.015 |
rockets | -0.015 |
jo | -0.015 |
anne | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.004 |
cater | +0.004 |
first | +0.004 |
Neg logit contributions | |
rina | -0.007 |
anne | -0.007 |
jo | -0.006 |
beard | -0.006 |
helicopters | -0.006 |
Token | drinking |
Token ID | 7722 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
rina | +0.014 |
anne | +0.014 |
jo | +0.014 |
beard | +0.013 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
but | -0.005 |
cater | -0.005 |
Token | y |
Token ID | 331 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.013 |
pin | +0.011 |
cater | +0.011 |
Fro | +0.010 |
Neg logit contributions | |
anne | -0.025 |
rina | -0.025 |
jo | -0.025 |
beard | -0.024 |
helicopters | -0.024 |
Token | ummy |
Token ID | 13513 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rina | +0.010 |
anne | +0.010 |
jo | +0.010 |
beard | +0.010 |
helicopters | +0.010 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
cater | -0.004 |
pin | -0.004 |
first | -0.004 |
Token | mil |
Token ID | 1465 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
but | +0.002 |
Neg logit contributions | |
rina | -0.003 |
anne | -0.003 |
jo | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | ksh |
Token ID | 50133 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
lipstick | +0.015 |
P | +0.014 |
pin | +0.013 |
cater | +0.013 |
Fro | +0.013 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
helicopters | -0.007 |
rockets | -0.007 |
jo | -0.007 |
Token | akes |
Token ID | 1124 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
aliens | +0.061 |
helicopters | +0.059 |
rockets | +0.057 |
announcements | +0.057 |
rina | +0.057 |
Neg logit contributions | |
lipstick | -0.061 |
P | -0.055 |
first | -0.051 |
by | -0.050 |
Yes | -0.049 |
Token | in |
Token ID | 287 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
anne | +0.011 |
rina | +0.011 |
jo | +0.011 |
beard | +0.011 |
helicopters | +0.011 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.005 |
pin | -0.004 |
but | -0.004 |
first | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
anne | +0.017 |
rina | +0.017 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.016 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
first | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
pin | +0.009 |
cater | +0.009 |
first | +0.008 |
Neg logit contributions | |
rina | -0.016 |
anne | -0.015 |
jo | -0.015 |
beard | -0.015 |
helicopters | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
anne | +0.005 |
rina | +0.005 |
beard | +0.004 |
jo | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
but | -0.002 |
first | -0.002 |
pin | -0.002 |
Token | as |
Token ID | 355 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
rina | +0.011 |
anne | +0.011 |
jo | +0.011 |
beard | +0.011 |
helicopters | +0.011 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.005 |
but | -0.004 |
pin | -0.004 |
cater | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
anne | +0.002 |
jo | +0.002 |
rina | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
cater | -0.001 |
first | -0.001 |
pin | -0.001 |
Token | drank |
Token ID | 24070 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
anne | +0.022 |
rina | +0.022 |
jo | +0.022 |
beard | +0.022 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.017 |
P | -0.015 |
pin | -0.015 |
cater | -0.014 |
first | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.011 |
Token | mil |
Token ID | 1465 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.010 |
pin | +0.009 |
cater | +0.009 |
Fro | +0.009 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | ksh |
Token ID | 50133 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
lipstick | +0.019 |
P | +0.018 |
pin | +0.017 |
cater | +0.017 |
Fro | +0.016 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
helicopters | -0.008 |
rockets | -0.008 |
jo | -0.008 |
Token | akes |
Token ID | 1124 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
aliens | +0.062 |
helicopters | +0.059 |
rockets | +0.058 |
rina | +0.058 |
announcements | +0.056 |
Neg logit contributions | |
lipstick | -0.061 |
P | -0.056 |
first | -0.050 |
by | -0.050 |
with | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
jo | +0.004 |
beard | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
first | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
beard | +0.004 |
jo | +0.004 |
helicopters | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
but | -0.002 |
Fro | -0.002 |
pin | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
P | +0.005 |
lipstick | +0.005 |
but | +0.004 |
first | +0.004 |
with | +0.004 |
Neg logit contributions | |
rina | -0.014 |
beard | -0.014 |
anne | -0.014 |
helicopters | -0.014 |
aliens | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
beard | +0.001 |
jo | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
first | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
anne | +0.027 |
rina | +0.026 |
jo | +0.026 |
beard | +0.026 |
helicopters | +0.025 |
Neg logit contributions | |
lipstick | -0.026 |
P | -0.023 |
pin | -0.022 |
cater | -0.022 |
first | -0.021 |
Token | L |
Token ID | 43 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
rina | +0.025 |
anne | +0.025 |
jo | +0.024 |
beard | +0.023 |
helicopters | +0.023 |
Neg logit contributions | |
lipstick | -0.019 |
P | -0.019 |
pin | -0.016 |
first | -0.016 |
cater | -0.016 |
Token | ily |
Token ID | 813 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
cater | +0.011 |
pin | +0.011 |
Fro | +0.010 |
Neg logit contributions | |
rina | -0.017 |
anne | -0.017 |
jo | -0.017 |
beard | -0.017 |
helicopters | -0.016 |
Token | liked |
Token ID | 8288 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.017 |
pin | +0.016 |
cater | +0.015 |
first | +0.015 |
Neg logit contributions | |
rina | -0.027 |
anne | -0.027 |
jo | -0.026 |
helicopters | -0.026 |
beard | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
helicopters | +0.017 |
anne | +0.017 |
rina | +0.017 |
rockets | +0.017 |
beard | +0.017 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.005 |
Fro | -0.005 |
Token | play |
Token ID | 711 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
cent | +0.010 |
Fro | +0.010 |
pin | +0.010 |
Neg logit contributions | |
anne | -0.021 |
helicopters | -0.020 |
rockets | -0.020 |
jo | -0.020 |
beard | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
lipstick | +0.018 |
P | +0.016 |
cater | +0.015 |
Pam | +0.014 |
cent | +0.014 |
Neg logit contributions | |
rockets | -0.042 |
beard | -0.042 |
helicopters | -0.042 |
aliens | -0.040 |
rina | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
helicopters | -0.005 |
rockets | -0.005 |
anne | -0.005 |
rina | -0.005 |
beard | -0.005 |
Token | garden |
Token ID | 11376 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
pin | +0.010 |
cater | +0.009 |
but | +0.009 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
beard | -0.012 |
helicopters | -0.012 |
jo | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
Fro | +0.006 |
Jade | +0.006 |
Neg logit contributions | |
rockets | -0.006 |
beard | -0.006 |
rina | -0.006 |
anne | -0.006 |
helicopters | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.010 |
but | +0.010 |
cent | +0.010 |
Neg logit contributions | |
helicopters | -0.027 |
rockets | -0.027 |
rina | -0.027 |
anne | -0.027 |
beard | -0.026 |
Token | flower |
Token ID | 15061 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
helicopters | +0.002 |
rockets | +0.002 |
beard | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
Fro | -0.002 |
Jade | -0.002 |
Pam | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
Jade | +0.009 |
Fro | +0.008 |
Gw | +0.008 |
Neg logit contributions | |
rina | -0.013 |
anne | -0.013 |
beard | -0.013 |
rockets | -0.013 |
jo | -0.013 |
Token | eat |
Token ID | 4483 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
Fro | +0.000 |
ula | +0.000 |
Jade | +0.000 |
Neg logit contributions | |
rockets | -0.000 |
helicopters | -0.000 |
rina | -0.000 |
anne | -0.000 |
aliens | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
rina | +0.007 |
helicopters | +0.007 |
rockets | +0.007 |
anne | +0.007 |
beard | +0.007 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.005 |
Fro | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
rina | +0.005 |
anne | +0.005 |
beard | +0.005 |
jo | +0.005 |
rockets | +0.005 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
Fro | -0.004 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
lipstick | +0.001 |
pin | +0.001 |
cater | +0.001 |
P | +0.001 |
first | +0.001 |
Neg logit contributions | |
rina | -0.001 |
anne | -0.001 |
jo | -0.001 |
helicopters | -0.001 |
aliens | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
lipstick | +0.021 |
P | +0.017 |
pin | +0.015 |
cater | +0.014 |
Fro | +0.014 |
Neg logit contributions | |
rina | -0.043 |
beard | -0.042 |
anne | -0.042 |
helicopters | -0.042 |
rockets | -0.041 |
Token | will |
Token ID | 481 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.003 |
rina | -0.003 |
jo | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | fly |
Token ID | 6129 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
rina | -0.005 |
anne | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
jo | -0.004 |
Token | ." |
Token ID | 526 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
rina | +0.005 |
anne | +0.005 |
beard | +0.005 |
jo | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
cater | -0.003 |
pin | -0.003 |
Fro | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
lipstick | +0.002 |
pin | +0.002 |
P | +0.002 |
cent | +0.002 |
cater | +0.002 |
Neg logit contributions | |
anne | -0.002 |
jo | -0.002 |
helicopters | -0.001 |
rina | -0.001 |
rockets | -0.001 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
helicopters | +0.017 |
rockets | +0.017 |
beard | +0.015 |
motors | +0.015 |
aliens | +0.015 |
Neg logit contributions | |
lipstick | -0.025 |
ey | -0.023 |
cent | -0.021 |
cater | -0.020 |
liking | -0.020 |
Token | pushed |
Token ID | 7121 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
pin | +0.000 |
cater | +0.000 |
but | +0.000 |
Neg logit contributions | |
rina | -0.001 |
anne | -0.001 |
jo | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
helicopters | +0.011 |
beard | +0.010 |
rockets | +0.010 |
motors | +0.010 |
jo | +0.010 |
Neg logit contributions | |
lipstick | -0.008 |
liking | -0.007 |
bottle | -0.007 |
Of | -0.007 |
Gw | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
anne | +0.004 |
jo | +0.004 |
rina | +0.004 |
helicopters | +0.004 |
beard | +0.004 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
cater | -0.003 |
Fro | -0.003 |
Pam | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
but | +0.008 |
Neg logit contributions | |
anne | -0.015 |
rina | -0.015 |
beard | -0.015 |
jo | -0.015 |
helicopters | -0.015 |
Token | paw |
Token ID | 41827 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
anne | +0.021 |
rina | +0.021 |
jo | +0.021 |
beard | +0.021 |
helicopters | +0.020 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.013 |
pin | -0.012 |
cater | -0.011 |
first | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
lipstick | +0.023 |
P | +0.021 |
cater | +0.018 |
Fro | +0.018 |
pin | +0.018 |
Neg logit contributions | |
anne | -0.040 |
helicopters | -0.040 |
jo | -0.040 |
rockets | -0.040 |
rina | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
helicopters | +0.008 |
rockets | +0.008 |
anne | +0.008 |
rina | +0.008 |
beard | +0.008 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
Fro | -0.004 |
cater | -0.004 |
cent | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
rina | +0.004 |
anne | +0.004 |
beard | +0.004 |
helicopters | +0.004 |
jo | +0.004 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
cater | -0.003 |
pin | -0.003 |
cent | -0.003 |
Token | flew |
Token ID | 13112 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
anne | +0.006 |
rina | +0.006 |
beard | +0.005 |
jo | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
pin | -0.003 |
lipstick | -0.003 |
P | -0.003 |
cater | -0.003 |
first | -0.003 |
Token | faster |
Token ID | 5443 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
anne | +0.014 |
rina | +0.014 |
beard | +0.014 |
helicopters | +0.014 |
jo | +0.014 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.008 |
cater | -0.008 |
pin | -0.008 |
cent | -0.007 |
Token | John |
Token ID | 1757 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
beard | +0.003 |
jo | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
pin | -0.002 |
but | -0.002 |
first | -0.002 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
helicopters | +0.003 |
beard | +0.003 |
jo | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
first | -0.002 |
cater | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.001 |
first | +0.001 |
cater | +0.001 |
Neg logit contributions | |
rina | -0.007 |
anne | -0.007 |
beard | -0.006 |
jo | -0.006 |
rockets | -0.006 |
Token | believe |
Token ID | 1975 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
first | +0.002 |
but | +0.002 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
beard | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
anne | +0.009 |
rina | +0.009 |
jo | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
but | -0.006 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
anne | +0.012 |
rina | +0.012 |
jo | +0.011 |
beard | +0.011 |
helicopters | +0.011 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
first | -0.005 |
cater | -0.005 |
pin | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
lipstick | +0.030 |
P | +0.027 |
but | +0.025 |
first | +0.025 |
pin | +0.025 |
Neg logit contributions | |
anne | -0.047 |
rina | -0.047 |
jo | -0.047 |
beard | -0.046 |
helicopters | -0.045 |
Token | There |
Token ID | 1318 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
lipstick | +0.017 |
P | +0.015 |
pin | +0.015 |
cater | +0.014 |
first | +0.014 |
Neg logit contributions | |
anne | -0.015 |
rina | -0.015 |
jo | -0.015 |
helicopters | -0.014 |
beard | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
but | +0.003 |
first | +0.003 |
pin | +0.003 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
beard | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
jo | -0.002 |
beard | -0.002 |
helicopters | -0.002 |
Token | many |
Token ID | 867 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
first | -0.001 |
cater | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
lipstick | +0.020 |
P | +0.017 |
pin | +0.016 |
cater | +0.016 |
Fro | +0.015 |
Neg logit contributions | |
anne | -0.030 |
rina | -0.030 |
jo | -0.029 |
beard | -0.029 |
helicopters | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
but | +0.001 |
Neg logit contributions | |
rina | -0.001 |
beard | -0.001 |
helicopters | -0.001 |
anne | -0.001 |
rockets | -0.001 |
Token | beach |
Token ID | 10481 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
Pam | +0.006 |
Neg logit contributions | |
rina | -0.007 |
beard | -0.007 |
anne | -0.007 |
helicopters | -0.006 |
jo | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
pin | +0.001 |
cater | +0.001 |
Fro | +0.001 |
Neg logit contributions | |
anne | -0.002 |
rina | -0.002 |
jo | -0.002 |
beard | -0.002 |
helicopters | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.004 |
jo | -0.003 |
rina | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
helicopters | +0.001 |
beard | +0.001 |
jo | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
but | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.008 |
first | +0.007 |
but | +0.006 |
by | +0.005 |
Neg logit contributions | |
rina | -0.049 |
helicopters | -0.049 |
anne | -0.049 |
beard | -0.049 |
motors | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
lipstick | +0.022 |
P | +0.021 |
pin | +0.018 |
but | +0.018 |
first | +0.018 |
Neg logit contributions | |
rina | -0.033 |
anne | -0.032 |
beard | -0.032 |
helicopters | -0.032 |
jo | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
rina | +0.015 |
anne | +0.015 |
jo | +0.014 |
beard | +0.014 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
first | -0.005 |
Token | young |
Token ID | 1862 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
anne | +0.023 |
rina | +0.023 |
beard | +0.022 |
jo | +0.022 |
helicopters | +0.022 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.011 |
pin | -0.010 |
cater | -0.009 |
first | -0.009 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
pin | +0.007 |
cater | +0.007 |
but | +0.007 |
Neg logit contributions | |
rina | -0.013 |
anne | -0.013 |
jo | -0.013 |
beard | -0.013 |
helicopters | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anne | +0.001 |
jo | +0.001 |
rina | +0.001 |
rockets | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
pin | -0.001 |
P | -0.001 |
cater | -0.001 |
first | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
anne | +0.027 |
rina | +0.027 |
beard | +0.026 |
jo | +0.026 |
helicopters | +0.026 |
Neg logit contributions | |
lipstick | -0.021 |
P | -0.019 |
pin | -0.018 |
cater | -0.017 |
first | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
lipstick | +0.007 |
Watch | +0.006 |
P | +0.006 |
Of | +0.006 |
Yes | +0.006 |
Neg logit contributions | |
helicopters | -0.007 |
rockets | -0.007 |
rina | -0.007 |
aliens | -0.007 |
marsh | -0.006 |
Token | pair |
Token ID | 5166 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
P | +0.003 |
lipstick | +0.003 |
Jade | +0.002 |
Fro | +0.002 |
Pam | +0.002 |
Neg logit contributions | |
helicopters | -0.003 |
anne | -0.003 |
rockets | -0.003 |
rina | -0.003 |
beard | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
Fro | +0.010 |
Diane | +0.010 |
Hermione | +0.010 |
Neg logit contributions | |
anne | -0.009 |
jo | -0.009 |
opter | -0.008 |
awoke | -0.008 |
helicopters | -0.008 |
Token | scissors |
Token ID | 41786 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
P | +0.022 |
lipstick | +0.021 |
Fro | +0.019 |
Jade | +0.019 |
first | +0.018 |
Neg logit contributions | |
helicopters | -0.028 |
rockets | -0.027 |
motors | -0.026 |
anne | -0.025 |
aliens | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
anne | +0.000 |
jo | +0.000 |
rina | +0.000 |
rockets | +0.000 |
helicopters | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
pin | -0.000 |
P | -0.000 |
cater | -0.000 |
first | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.011 |
pin | +0.010 |
cater | +0.010 |
Fro | +0.009 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
jo | -0.016 |
beard | -0.016 |
helicopters | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
helicopters | -0.008 |
jo | -0.008 |
beard | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.006 |
pin | +0.005 |
cater | +0.005 |
Fro | +0.005 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
jo | -0.008 |
helicopters | -0.007 |
beard | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
pin | +0.008 |
cater | +0.007 |
Fro | +0.007 |
Neg logit contributions | |
anne | -0.010 |
jo | -0.010 |
rina | -0.010 |
beard | -0.010 |
helicopters | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
lipstick | +0.012 |
P | +0.010 |
pin | +0.010 |
cater | +0.009 |
first | +0.009 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.024 |
helicopters | -0.023 |
jo | -0.023 |
beard | -0.023 |
Token | went |
Token ID | 1816 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
anne | +0.009 |
rina | +0.009 |
jo | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
first | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.008 |
cater | +0.008 |
cent | +0.008 |
Yes | +0.008 |
Neg logit contributions | |
rockets | -0.010 |
helicopters | -0.009 |
beard | -0.009 |
hikes | -0.009 |
anne | -0.009 |
Token | an |
Token ID | 281 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
jo | +0.008 |
beard | +0.008 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
Fro | -0.003 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
jo | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
cater | -0.003 |
first | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
anne | +0.004 |
jo | +0.003 |
rockets | +0.003 |
helicopters | +0.003 |
rina | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
Fro | -0.002 |
pin | -0.002 |
cater | -0.002 |
Token | discovered |
Token ID | 5071 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.004 |
cater | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
first | +0.004 |
Neg logit contributions | |
anne | -0.013 |
rina | -0.013 |
jo | -0.013 |
beard | -0.013 |
helicopters | -0.013 |
Token | mysterious |
Token ID | 11428 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.002 |
Fro | +0.002 |
pin | +0.002 |
Pam | +0.002 |
Neg logit contributions | |
rina | -0.003 |
anne | -0.003 |
beard | -0.003 |
helicopters | -0.003 |
rockets | -0.003 |
Token | gray |
Token ID | 12768 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
beard | +0.008 |
jo | +0.008 |
helicopters | +0.008 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.008 |
pin | -0.007 |
Fro | -0.007 |
first | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.013 |
pin | +0.012 |
but | +0.011 |
cater | +0.011 |
Neg logit contributions | |
anne | -0.025 |
jo | -0.024 |
rina | -0.024 |
beard | -0.024 |
helicopters | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
lipstick | +0.005 |
cater | +0.004 |
P | +0.004 |
Gw | +0.004 |
pin | +0.004 |
Neg logit contributions | |
rina | -0.005 |
beard | -0.005 |
anne | -0.005 |
helicopters | -0.005 |
rockets | -0.005 |
Token | So |
Token ID | 1406 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
pin | +0.011 |
but | +0.011 |
cater | +0.011 |
Neg logit contributions | |
rina | -0.019 |
anne | -0.018 |
beard | -0.018 |
jo | -0.018 |
helicopters | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
lipstick | +0.034 |
ula | +0.029 |
pin | +0.028 |
issors | +0.027 |
cater | +0.027 |
Neg logit contributions | |
rockets | -0.031 |
beard | -0.030 |
rina | -0.030 |
helicopters | -0.030 |
jo | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
lipstick | +0.009 |
issors | +0.008 |
ula | +0.008 |
Jade | +0.007 |
P | +0.007 |
Neg logit contributions | |
helicopters | -0.004 |
rockets | -0.004 |
beard | -0.003 |
marsh | -0.003 |
cub | -0.003 |
Token | l |
Token ID | 300 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
cater | +0.001 |
pin | +0.001 |
but | +0.001 |
Neg logit contributions | |
rina | -0.002 |
anne | -0.002 |
beard | -0.002 |
jo | -0.002 |
helicopters | -0.002 |
Token | icked |
Token ID | 9484 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
pin | +0.008 |
cater | +0.008 |
but | +0.007 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
beard | -0.007 |
helicopters | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.001 |
cater | +0.001 |
pin | +0.001 |
cent | +0.001 |
Neg logit contributions | |
helicopters | -0.001 |
rina | -0.001 |
beard | -0.001 |
rockets | -0.001 |
anne | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
beard | +0.001 |
rockets | +0.001 |
der | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
Jade | -0.001 |
Gw | -0.001 |
Fro | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.013 |
pin | +0.011 |
cater | +0.011 |
first | +0.011 |
Neg logit contributions | |
anne | -0.023 |
rina | -0.023 |
jo | -0.023 |
beard | -0.023 |
helicopters | -0.022 |
Token | tongue |
Token ID | 11880 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
anne | +0.002 |
beard | +0.002 |
rina | +0.002 |
rockets | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
Jade | -0.003 |
Pam | -0.002 |
Gw | -0.002 |
Token | each |
Token ID | 1123 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
cent | +0.003 |
Neg logit contributions | |
anne | -0.006 |
rina | -0.006 |
helicopters | -0.006 |
beard | -0.006 |
rockets | -0.006 |
Token | other |
Token ID | 584 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
lipstick | +0.024 |
P | +0.024 |
Jade | +0.022 |
Fro | +0.021 |
Gw | +0.021 |
Neg logit contributions | |
anne | -0.024 |
rina | -0.021 |
jo | -0.021 |
helicopters | -0.020 |
beard | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
anne | +0.009 |
rina | +0.009 |
jo | +0.008 |
beard | +0.008 |
helicopters | +0.008 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.005 |
first | -0.005 |
Token | potatoes |
Token ID | 18821 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
beard | +0.002 |
jo | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
Fro | -0.002 |
Jade | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.006 |
pin | +0.006 |
cater | +0.006 |
Fro | +0.005 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
beard | -0.009 |
jo | -0.009 |
helicopters | -0.009 |
Token | And |
Token ID | 843 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
jo | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.010 |
P | -0.009 |
pin | -0.008 |
cater | -0.008 |
first | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
rina | +0.012 |
anne | +0.012 |
jo | +0.011 |
beard | +0.011 |
helicopters | +0.011 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.009 |
pin | -0.009 |
cater | -0.008 |
cent | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
beard | +0.001 |
jo | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
cater | -0.001 |
cent | -0.001 |
Token | surprise |
Token ID | 5975 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
rina | +0.025 |
anne | +0.025 |
jo | +0.024 |
beard | +0.024 |
helicopters | +0.024 |
Neg logit contributions | |
lipstick | -0.022 |
P | -0.020 |
pin | -0.019 |
cater | -0.018 |
but | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -5.63e-04 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
Fro | +0.004 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
jo | -0.012 |
beard | -0.012 |
helicopters | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
rina | +0.000 |
anne | +0.000 |
beard | +0.000 |
jo | +0.000 |
helicopters | +0.000 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
cent | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
rina | +0.007 |
anne | +0.007 |
jo | +0.007 |
beard | +0.007 |
rockets | +0.007 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.007 |
pin | -0.006 |
first | -0.006 |
cater | -0.006 |
Token | get |
Token ID | 651 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
jo | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
cater | +0.004 |
pin | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
beard | -0.008 |
jo | -0.008 |
helicopters | -0.008 |
Token | dry |
Token ID | 5894 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.007 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
jo | -0.016 |
beard | -0.016 |
helicopters | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
lipstick | +0.015 |
P | +0.014 |
cater | +0.012 |
pin | +0.012 |
Fro | +0.012 |
Neg logit contributions | |
rina | -0.024 |
anne | -0.023 |
helicopters | -0.023 |
beard | -0.023 |
jo | -0.023 |
Token | organized |
Token ID | 8389 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
beard | -0.009 |
jo | -0.009 |
helicopters | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
anne | +0.014 |
rina | +0.013 |
jo | +0.013 |
beard | +0.013 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
first | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
pin | +0.004 |
cent | +0.004 |
cater | +0.004 |
Neg logit contributions | |
rina | -0.008 |
anne | -0.008 |
helicopters | -0.008 |
rockets | -0.008 |
jo | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
rina | +0.017 |
anne | +0.017 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.016 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.010 |
pin | -0.009 |
cater | -0.009 |
Fro | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
anne | +0.001 |
rina | +0.001 |
jo | +0.001 |
helicopters | +0.001 |
beard | +0.001 |
Neg logit contributions | |
lipstick | -0.000 |
P | -0.000 |
pin | -0.000 |
first | -0.000 |
but | -0.000 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.003 |
pin | +0.003 |
first | +0.003 |
but | +0.003 |
Neg logit contributions | |
anne | -0.011 |
jo | -0.010 |
rina | -0.010 |
beard | -0.010 |
helicopters | -0.010 |
Token | went |
Token ID | 1816 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
rina | +0.014 |
anne | +0.014 |
jo | +0.013 |
helicopters | +0.013 |
beard | +0.013 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.006 |
pin | -0.005 |
pick | -0.005 |
welcome | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
cater | +0.002 |
pin | +0.002 |
cent | +0.001 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
rockets | -0.004 |
jo | -0.004 |
helicopters | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.001 |
cater | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
beard | -0.007 |
helicopters | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.009 |
Pam | +0.009 |
but | +0.009 |
Neg logit contributions | |
helicopters | -0.009 |
rockets | -0.009 |
beard | -0.009 |
rina | -0.008 |
aliens | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
anne | +0.027 |
jo | +0.026 |
rina | +0.025 |
beard | +0.025 |
helicopters | +0.025 |
Neg logit contributions | |
lipstick | -0.021 |
P | -0.019 |
pin | -0.018 |
cater | -0.018 |
cent | -0.016 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.006 |
first | +0.005 |
with | +0.005 |
L | +0.004 |
Neg logit contributions | |
anne | -0.023 |
jo | -0.023 |
rina | -0.023 |
opter | -0.022 |
beard | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
anne | +0.033 |
rina | +0.033 |
jo | +0.032 |
beard | +0.032 |
helicopters | +0.031 |
Neg logit contributions | |
lipstick | -0.022 |
P | -0.020 |
pin | -0.018 |
cater | -0.018 |
first | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
rina | +0.040 |
beard | +0.040 |
anne | +0.039 |
jo | +0.039 |
helicopters | +0.038 |
Neg logit contributions | |
lipstick | -0.031 |
P | -0.028 |
but | -0.026 |
first | -0.024 |
cater | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
anne | +0.020 |
rina | +0.019 |
jo | +0.019 |
beard | +0.019 |
helicopters | +0.018 |
Neg logit contributions | |
lipstick | -0.020 |
P | -0.018 |
pin | -0.016 |
cater | -0.016 |
cent | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
anne | +0.010 |
rina | +0.010 |
jo | +0.009 |
beard | +0.009 |
helicopters | +0.009 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.003 |
cater | -0.003 |
first | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
anne | +0.012 |
helicopters | +0.012 |
beard | +0.012 |
rina | +0.012 |
rockets | +0.012 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
Pam | -0.007 |
Fro | -0.007 |
Jade | -0.007 |
Token | many |
Token ID | 867 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rina | +0.028 |
anne | +0.027 |
jo | +0.027 |
beard | +0.026 |
opter | +0.025 |
Neg logit contributions | |
lipstick | -0.008 |
so | -0.007 |
P | -0.007 |
first | -0.006 |
but | -0.006 |
Token | cars |
Token ID | 5006 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
anne | +0.035 |
rina | +0.034 |
jo | +0.032 |
beard | +0.031 |
storms | +0.029 |
Neg logit contributions | |
lipstick | -0.026 |
pin | -0.023 |
P | -0.023 |
but | -0.022 |
first | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
cater | +0.000 |
pin | +0.000 |
Fro | +0.000 |
Neg logit contributions | |
anne | -0.001 |
jo | -0.001 |
beard | -0.001 |
rina | -0.001 |
rockets | -0.001 |
Token | different |
Token ID | 1180 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
cater | +0.002 |
but | +0.002 |
Neg logit contributions | |
anne | -0.004 |
rina | -0.004 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | colors |
Token ID | 7577 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
anne | +0.023 |
rina | +0.023 |
jo | +0.022 |
beard | +0.021 |
helicopters | +0.021 |
Neg logit contributions | |
lipstick | -0.018 |
P | -0.016 |
pin | -0.015 |
but | -0.015 |
first | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
but | +0.004 |
pin | +0.004 |
first | +0.004 |
Neg logit contributions | |
anne | -0.014 |
rina | -0.014 |
jo | -0.014 |
beard | -0.014 |
helicopters | -0.013 |
Token | sizes |
Token ID | 10620 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
rina | +0.016 |
anne | +0.016 |
jo | +0.015 |
beard | +0.014 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.027 |
P | -0.025 |
pin | -0.024 |
but | -0.024 |
cater | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
but | +0.005 |
first | +0.005 |
pin | +0.005 |
Neg logit contributions | |
anne | -0.012 |
rina | -0.012 |
jo | -0.011 |
beard | -0.011 |
helicopters | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
rina | +0.012 |
beard | +0.012 |
jo | +0.012 |
anne | +0.011 |
opter | +0.011 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.009 |
but | -0.008 |
Pam | -0.007 |
first | -0.007 |
Token | pretend |
Token ID | 16614 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
anne | +0.018 |
rina | +0.018 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.008 |
P | -0.007 |
pin | -0.007 |
first | -0.007 |
but | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
rina | +0.003 |
anne | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
cater | -0.002 |
but | -0.002 |
Token | want |
Token ID | 765 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.008 |
pin | +0.007 |
cater | +0.007 |
Fro | +0.007 |
Neg logit contributions | |
anne | -0.013 |
rina | -0.013 |
jo | -0.012 |
beard | -0.012 |
helicopters | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
beard | -0.005 |
Token | come |
Token ID | 1282 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
lipstick | +0.010 |
P | +0.009 |
pin | +0.008 |
cater | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
rina | -0.019 |
anne | -0.019 |
jo | -0.019 |
beard | -0.019 |
helicopters | -0.019 |
Token | watch |
Token ID | 2342 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
helicopters | +0.001 |
jo | +0.001 |
beard | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.000 |
pin | -0.000 |
cater | -0.000 |
Fro | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
Fro | +0.005 |
Neg logit contributions | |
rina | -0.009 |
anne | -0.009 |
jo | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
Token | lightning |
Token ID | 14357 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rina | +0.001 |
anne | +0.001 |
jo | +0.001 |
beard | +0.001 |
helicopters | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
cater | -0.001 |
pin | -0.001 |
first | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
rina | +0.031 |
beard | +0.031 |
anne | +0.030 |
jo | +0.029 |
helicopters | +0.029 |
Neg logit contributions | |
lipstick | -0.022 |
but | -0.022 |
first | -0.021 |
P | -0.020 |
so | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
lipstick | +0.000 |
P | +0.000 |
cater | +0.000 |
cent | +0.000 |
issors | +0.000 |
Neg logit contributions | |
helicopters | -0.000 |
anne | -0.000 |
jo | -0.000 |
rockets | -0.000 |
rina | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
anne | +0.011 |
rina | +0.011 |
jo | +0.010 |
helicopters | +0.010 |
beard | +0.010 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.005 |
cater | -0.005 |
cent | -0.005 |
Token | agreed |
Token ID | 4987 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
first | +0.004 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
jo | -0.007 |
beard | -0.007 |
helicopters | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
anne | +0.005 |
rina | +0.005 |
jo | +0.005 |
beard | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
cater | -0.003 |
Fro | -0.003 |
pin | -0.003 |
Token | curious |
Token ID | 11040 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
rina | +0.002 |
anne | +0.002 |
helicopters | +0.002 |
beard | +0.002 |
jo | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
cater | -0.001 |
cent | -0.001 |
pin | -0.001 |
Token | about |
Token ID | 546 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
but | +0.002 |
cater | +0.002 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.004 |
beard | -0.004 |
jo | -0.004 |
helicopters | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
Fro | +0.006 |
pin | +0.006 |
first | +0.006 |
Neg logit contributions | |
helicopters | -0.010 |
rina | -0.009 |
rockets | -0.009 |
anne | -0.009 |
jo | -0.009 |
Token | thing |
Token ID | 1517 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
anne | +0.001 |
helicopters | +0.001 |
rina | +0.001 |
beard | +0.001 |
rockets | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
Fro | -0.001 |
Jade | -0.001 |
Pam | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
anne | +0.005 |
jo | +0.005 |
rina | +0.005 |
helicopters | +0.005 |
rockets | +0.005 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
Fro | -0.004 |
Watch | -0.004 |
Gw | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
lipstick | +0.011 |
P | +0.010 |
ula | +0.010 |
cent | +0.009 |
cater | +0.009 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
jo | -0.008 |
helicopters | -0.008 |
rockets | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
anne | +0.024 |
rina | +0.024 |
jo | +0.024 |
beard | +0.024 |
helicopters | +0.023 |
Neg logit contributions | |
lipstick | -0.009 |
P | -0.008 |
pin | -0.007 |
cater | -0.007 |
first | -0.006 |
Token | show |
Token ID | 905 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
lipstick | +0.024 |
P | +0.022 |
Fro | +0.019 |
cater | +0.019 |
pin | +0.019 |
Neg logit contributions | |
anne | -0.030 |
rina | -0.028 |
helicopters | -0.028 |
jo | -0.028 |
rockets | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.003 |
cater | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
rina | -0.005 |
anne | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
beard | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.002 |
cater | +0.002 |
pin | +0.002 |
Fro | +0.002 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.004 |
jo | -0.004 |
helicopters | -0.004 |
rockets | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.011 |
pin | +0.010 |
cater | +0.010 |
cent | +0.010 |
Neg logit contributions | |
rina | -0.029 |
anne | -0.029 |
helicopters | -0.028 |
jo | -0.028 |
rockets | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
but | +0.005 |
Neg logit contributions | |
anne | -0.016 |
rina | -0.016 |
jo | -0.016 |
beard | -0.016 |
helicopters | -0.016 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
anne | +0.015 |
rina | +0.015 |
jo | +0.015 |
beard | +0.015 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.013 |
P | -0.012 |
pin | -0.011 |
cater | -0.011 |
first | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
but | +0.004 |
so | +0.003 |
first | +0.003 |
Neg logit contributions | |
anne | -0.010 |
rina | -0.010 |
jo | -0.010 |
beard | -0.010 |
helicopters | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.002 |
cater | +0.002 |
but | +0.002 |
Neg logit contributions | |
rina | -0.008 |
anne | -0.008 |
jo | -0.007 |
beard | -0.007 |
opter | -0.007 |
Token | man |
Token ID | 582 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
jo | +0.002 |
beard | +0.002 |
helicopters | +0.002 |
Neg logit contributions | |
lipstick | -0.002 |
pin | -0.002 |
P | -0.002 |
cater | -0.002 |
first | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
rina | +0.009 |
anne | +0.009 |
beard | +0.008 |
jo | +0.008 |
helicopters | +0.008 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
but | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
rina | +0.015 |
anne | +0.015 |
jo | +0.015 |
beard | +0.015 |
helicopters | +0.014 |
Neg logit contributions | |
lipstick | -0.019 |
P | -0.018 |
pin | -0.017 |
cater | -0.017 |
but | -0.016 |
Token | sang |
Token ID | 25889 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
anne | +0.016 |
rina | +0.016 |
jo | +0.016 |
beard | +0.016 |
helicopters | +0.015 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.013 |
pin | -0.012 |
cater | -0.012 |
first | -0.011 |
Token | about |
Token ID | 546 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
but | +0.006 |
pin | +0.006 |
cater | +0.006 |
Neg logit contributions | |
anne | -0.014 |
rina | -0.014 |
jo | -0.014 |
beard | -0.014 |
helicopters | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.007 |
beard | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
pin | -0.003 |
cater | -0.003 |
but | -0.003 |
Token | lake |
Token ID | 13546 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
anne | +0.008 |
rina | +0.008 |
jo | +0.008 |
beard | +0.008 |
helicopters | +0.007 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
first | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.006 |
beard | +0.006 |
helicopters | +0.006 |
Neg logit contributions | |
lipstick | -0.007 |
P | -0.006 |
pin | -0.006 |
cater | -0.006 |
first | -0.006 |
Token | take |
Token ID | 1011 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.005 |
pin | +0.004 |
cater | +0.004 |
Fro | +0.004 |
Neg logit contributions | |
anne | -0.009 |
rina | -0.009 |
jo | -0.009 |
beard | -0.009 |
helicopters | -0.009 |
Token | out |
Token ID | 503 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
anne | +0.007 |
rina | +0.007 |
jo | +0.007 |
beard | +0.007 |
opter | +0.006 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.003 |
pin | -0.003 |
so | -0.003 |
first | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
rockets | +0.018 |
helicopters | +0.018 |
beard | +0.018 |
rina | +0.018 |
anne | +0.018 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.015 |
cater | -0.013 |
pin | -0.013 |
Fro | -0.013 |
Token | j |
Token ID | 474 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
lipstick | +0.005 |
P | +0.004 |
Fro | +0.004 |
pin | +0.004 |
cater | +0.004 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
beard | -0.005 |
jo | -0.005 |
helicopters | -0.005 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
lipstick | +0.007 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
but | +0.006 |
Neg logit contributions | |
anne | -0.009 |
jo | -0.009 |
beard | -0.008 |
rina | -0.008 |
rockets | -0.008 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
rina | +0.088 |
anne | +0.084 |
jo | +0.081 |
helicopters | +0.079 |
announcements | +0.079 |
Neg logit contributions | |
lipstick | -0.093 |
first | -0.081 |
pin | -0.081 |
but | -0.081 |
cater | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
rockets | +0.024 |
beard | +0.024 |
jo | +0.023 |
anne | +0.023 |
helicopters | +0.023 |
Neg logit contributions | |
lipstick | -0.015 |
P | -0.014 |
Fro | -0.012 |
cater | -0.011 |
pin | -0.011 |
Token | try |
Token ID | 1949 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
cater | +0.003 |
pin | +0.003 |
Fro | +0.003 |
Neg logit contributions | |
anne | -0.007 |
rina | -0.007 |
beard | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
lipstick | +0.001 |
P | +0.001 |
but | +0.001 |
pin | +0.001 |
first | +0.001 |
Neg logit contributions | |
anne | -0.003 |
rina | -0.003 |
jo | -0.003 |
beard | -0.003 |
opter | -0.003 |
Token | solve |
Token ID | 8494 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
lipstick | +0.008 |
P | +0.007 |
pin | +0.006 |
cater | +0.006 |
first | +0.006 |
Neg logit contributions | |
anne | -0.015 |
rina | -0.015 |
jo | -0.015 |
beard | -0.015 |
helicopters | -0.015 |
Token | visit |
Token ID | 3187 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
anne | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
helicopters | +0.003 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
pin | -0.001 |
first | -0.001 |
cater | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
anne | +0.002 |
rina | +0.002 |
jo | +0.002 |
opter | +0.002 |
beard | +0.002 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
first | -0.001 |
with | -0.001 |
but | -0.001 |
Token | neighbor |
Token ID | 4780 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
anne | +0.014 |
rina | +0.014 |
jo | +0.014 |
beard | +0.014 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.010 |
pin | -0.009 |
first | -0.009 |
cater | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anne | +0.005 |
rina | +0.005 |
beard | +0.005 |
jo | +0.005 |
helicopters | +0.005 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.004 |
pin | -0.004 |
cater | -0.004 |
cent | -0.004 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
anne | +0.003 |
helicopters | +0.003 |
rina | +0.003 |
jo | +0.003 |
beard | +0.003 |
Neg logit contributions | |
lipstick | -0.003 |
P | -0.002 |
cater | -0.002 |
cent | -0.002 |
pin | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
opter | +0.079 |
anne | +0.078 |
rina | +0.075 |
jo | +0.075 |
helicopters | +0.073 |
Neg logit contributions | |
lipstick | -0.026 |
P | -0.025 |
but | -0.023 |
by | -0.023 |
first | -0.023 |
Token | Lee |
Token ID | 5741 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
anne | +0.062 |
jo | +0.061 |
rina | +0.060 |
beard | +0.058 |
helicopters | +0.057 |
Neg logit contributions | |
lipstick | -0.063 |
P | -0.063 |
first | -0.055 |
cater | -0.055 |
Fro | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
rina | +0.019 |
anne | +0.018 |
helicopters | +0.018 |
beard | +0.018 |
jo | +0.018 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.005 |
but | -0.004 |
first | -0.004 |
called | -0.004 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
rina | +0.064 |
anne | +0.064 |
jo | +0.063 |
beard | +0.063 |
helicopters | +0.061 |
Neg logit contributions | |
lipstick | -0.042 |
P | -0.039 |
pin | -0.034 |
cater | -0.033 |
but | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
anne | +0.076 |
opter | +0.075 |
rina | +0.075 |
jo | +0.073 |
helicopters | +0.073 |
Neg logit contributions | |
lipstick | -0.029 |
P | -0.028 |
by | -0.025 |
but | -0.024 |
with | -0.024 |
Token | Lee |
Token ID | 5741 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
anne | +0.062 |
rina | +0.061 |
jo | +0.060 |
beard | +0.060 |
helicopters | +0.058 |
Neg logit contributions | |
lipstick | -0.053 |
P | -0.050 |
cater | -0.044 |
pin | -0.044 |
first | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
anne | +0.017 |
rina | +0.017 |
jo | +0.017 |
beard | +0.017 |
helicopters | +0.017 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
cater | -0.004 |
first | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
anne | +0.008 |
jo | +0.008 |
rina | +0.008 |
helicopters | +0.008 |
rockets | +0.008 |
Neg logit contributions | |
lipstick | -0.005 |
pin | -0.005 |
P | -0.005 |
cater | -0.004 |
Fro | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
rina | +0.014 |
anne | +0.014 |
beard | +0.014 |
aliens | +0.013 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.008 |
pin | -0.008 |
first | -0.008 |
called | -0.008 |
but | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
rina | +0.012 |
beard | +0.012 |
anne | +0.012 |
jo | +0.012 |
opter | +0.011 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.003 |
so | -0.003 |
pin | -0.003 |
first | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
anne | +0.015 |
helicopters | +0.015 |
rina | +0.015 |
rockets | +0.015 |
jo | +0.015 |
Neg logit contributions | |
lipstick | -0.011 |
P | -0.011 |
Fro | -0.010 |
Pam | -0.009 |
Jade | -0.009 |
Token | tr |
Token ID | 491 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
anne | +0.015 |
rina | +0.015 |
helicopters | +0.015 |
jo | +0.015 |
rockets | +0.015 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.013 |
pin | -0.011 |
cater | -0.011 |
Fro | -0.011 |
Token | icycle |
Token ID | 35298 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
rina | +0.063 |
anne | +0.062 |
beard | +0.061 |
jo | +0.059 |
helicopters | +0.059 |
Neg logit contributions | |
lipstick | -0.063 |
P | -0.056 |
pin | -0.053 |
cater | -0.051 |
first | -0.050 |
Token | that |
Token ID | 326 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
anne | +0.001 |
jo | +0.001 |
helicopters | +0.001 |
rockets | +0.001 |
rina | +0.001 |
Neg logit contributions | |
lipstick | -0.001 |
P | -0.001 |
Fro | -0.001 |
Pam | -0.001 |
cater | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
anne | +0.031 |
rina | +0.030 |
jo | +0.030 |
helicopters | +0.029 |
beard | +0.029 |
Neg logit contributions | |
lipstick | -0.016 |
P | -0.014 |
pin | -0.012 |
cater | -0.012 |
Fro | -0.012 |
Token | would |
Token ID | 561 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
lipstick | +0.004 |
P | +0.004 |
pin | +0.004 |
cater | +0.003 |
first | +0.003 |
Neg logit contributions | |
rina | -0.004 |
anne | -0.004 |
beard | -0.004 |
jo | -0.004 |
helicopters | -0.004 |
Token | ride |
Token ID | 6594 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
lipstick | +0.006 |
P | +0.005 |
pin | +0.005 |
cater | +0.005 |
first | +0.005 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
beard | -0.007 |
jo | -0.007 |
helicopters | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
helicopters | +0.003 |
rockets | +0.003 |
anne | +0.003 |
rina | +0.003 |
beard | +0.003 |
Neg logit contributions | |
lipstick | -0.002 |
P | -0.002 |
pin | -0.002 |
Fro | -0.002 |
Pam | -0.002 |
Token | bounce |
Token ID | 20110 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
lipstick | +0.014 |
P | +0.012 |
pin | +0.011 |
cater | +0.011 |
cent | +0.011 |
Neg logit contributions | |
anne | -0.023 |
beard | -0.023 |
rina | -0.023 |
helicopters | -0.023 |
jo | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
lipstick | +0.006 |
cater | +0.006 |
P | +0.006 |
cent | +0.005 |
Fro | +0.005 |
Neg logit contributions | |
rockets | -0.008 |
beard | -0.008 |
helicopters | -0.008 |
aliens | -0.008 |
motors | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
lipstick | +0.003 |
P | +0.003 |
pin | +0.003 |
cater | +0.003 |
Pam | +0.003 |
Neg logit contributions | |
helicopters | -0.006 |
rockets | -0.006 |
beard | -0.006 |
rina | -0.006 |
motors | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
lipstick | +0.013 |
P | +0.012 |
Pam | +0.011 |
Fro | +0.011 |
pin | +0.011 |
Neg logit contributions | |
helicopters | -0.014 |
rockets | -0.014 |
beard | -0.013 |
rina | -0.013 |
anne | -0.013 |
Token | tr |
Token ID | 491 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
anne | +0.006 |
helicopters | +0.006 |
jo | +0.006 |
rockets | +0.006 |
beard | +0.006 |
Neg logit contributions | |
lipstick | -0.006 |
P | -0.005 |
pin | -0.005 |
Fro | -0.005 |
cater | -0.005 |
Token | amp |
Token ID | 696 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
rina | +0.071 |
anne | +0.070 |
beard | +0.069 |
jo | +0.068 |
helicopters | +0.067 |
Neg logit contributions | |
lipstick | -0.059 |
P | -0.053 |
pin | -0.048 |
cater | -0.048 |
first | -0.046 |
Token | oline |
Token ID | 14453 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
rina | +0.031 |
anne | +0.030 |
beard | +0.030 |
jo | +0.029 |
helicopters | +0.028 |
Neg logit contributions | |
lipstick | -0.079 |
P | -0.074 |
pin | -0.071 |
cater | -0.070 |
first | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
anne | +0.016 |
jo | +0.016 |
beard | +0.016 |
rockets | +0.016 |
rina | +0.016 |
Neg logit contributions | |
lipstick | -0.019 |
P | -0.017 |
cater | -0.016 |
pin | -0.016 |
Fro | -0.016 |
Token | their |
Token ID | 511 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
lipstick | +0.002 |
P | +0.002 |
pin | +0.002 |
cater | +0.002 |
first | +0.002 |
Neg logit contributions | |
anne | -0.005 |
rina | -0.005 |
jo | -0.004 |
beard | -0.004 |
helicopters | -0.004 |
Token | backyard |
Token ID | 24296 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
anne | +0.017 |
rockets | +0.017 |
jo | +0.017 |
rina | +0.016 |
helicopters | +0.016 |
Neg logit contributions | |
lipstick | -0.018 |
P | -0.016 |
pin | -0.015 |
cater | -0.015 |
Fro | -0.015 |
Token | there |
Token ID | 612 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
lipstick | +0.009 |
P | +0.009 |
first | +0.007 |
but | +0.007 |
Fro | +0.006 |
Neg logit contributions | |
rina | -0.051 |
helicopters | -0.050 |
anne | -0.050 |
beard | -0.050 |
rockets | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
lipstick | +0.028 |
P | +0.026 |
pin | +0.024 |
cater | +0.023 |
but | +0.023 |
Neg logit contributions | |
rina | -0.037 |
anne | -0.037 |
beard | -0.036 |
jo | -0.036 |
helicopters | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
rina | +0.014 |
anne | +0.014 |
jo | +0.014 |
beard | +0.014 |
helicopters | +0.013 |
Neg logit contributions | |
lipstick | -0.005 |
P | -0.005 |
cater | -0.004 |
pin | -0.004 |
Fro | -0.004 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
anne | +0.027 |
rina | +0.027 |
jo | +0.026 |
beard | +0.026 |
helicopters | +0.026 |
Neg logit contributions | |
lipstick | -0.014 |
P | -0.012 |
pin | -0.011 |
cater | -0.011 |
first | -0.010 |
Token | called |
Token ID | 1444 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
lipstick | +0.027 |
P | +0.022 |
pin | +0.022 |
unst | +0.021 |
cent | +0.021 |
Neg logit contributions | |
jo | -0.030 |
anne | -0.030 |
helicopters | -0.029 |
rina | -0.029 |
beard | -0.028 |
Token | Motor |
Token ID | 12533 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
lipstick | +0.005 |
pin | +0.004 |
P | +0.004 |
cater | +0.004 |
cent | +0.004 |
Neg logit contributions | |
anne | -0.008 |
rina | -0.008 |
jo | -0.008 |
beard | -0.008 |
helicopters | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
helicopters | +0.072 |
rockets | +0.071 |
rina | +0.069 |
aliens | +0.068 |
beard | +0.067 |
Neg logit contributions | |
lipstick | -0.050 |
P | -0.046 |
cater | -0.044 |
first | -0.043 |
pin | -0.042 |
Token | Motor |
Token ID | 12533 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
jo | +0.020 |
anne | +0.019 |
helicopters | +0.019 |
rina | +0.019 |
rockets | +0.019 |
Neg logit contributions | |
lipstick | -0.021 |
pin | -0.019 |
P | -0.018 |
cater | -0.018 |
first | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
helicopters | +0.054 |
rockets | +0.054 |
rina | +0.052 |
anne | +0.051 |
beard | +0.051 |
Neg logit contributions | |
lipstick | -0.044 |
P | -0.040 |
pin | -0.039 |
cater | -0.037 |
first | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
helicopters | +0.007 |
rockets | +0.007 |
aliens | +0.006 |
gor | +0.006 |
Frost | +0.006 |
Neg logit contributions | |
lipstick | -0.009 |
but | -0.008 |
issors | -0.007 |
cent | -0.007 |
pin | -0.007 |
Token | poor |
Token ID | 3595 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
anne | +0.005 |
beard | +0.004 |
helicopters | +0.004 |
jo | +0.004 |
rockets | +0.004 |
Neg logit contributions | |
lipstick | -0.004 |
P | -0.004 |
issors | -0.003 |
Jade | -0.003 |
Pam | -0.003 |