Token | help |
Token ID | 1037 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
sure | +0.004 |
happy | +0.004 |
disl | +0.004 |
Happy | +0.004 |
caring | +0.003 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.014 |
igs | -0.014 |
icer | -0.014 |
loft | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
Happy | +0.005 |
happy | +0.005 |
free | +0.005 |
Neg logit contributions | |
ditch | -0.009 |
unks | -0.009 |
igs | -0.009 |
alk | -0.008 |
icer | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +9.62e-03 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.003 |
happy | +0.003 |
Happy | +0.002 |
free | +0.002 |
Neg logit contributions | |
ditch | -0.004 |
unks | -0.004 |
igs | -0.004 |
stack | -0.004 |
loft | -0.004 |
Token | used |
Token ID | 973 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
unks | +0.026 |
ditch | +0.025 |
icer | +0.024 |
igs | +0.024 |
alk | +0.024 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.007 |
forg | -0.006 |
listened | -0.006 |
caring | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
unks | +0.083 |
ditch | +0.081 |
icer | +0.078 |
stack | +0.077 |
loft | +0.077 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.018 |
excited | -0.015 |
caring | -0.015 |
kind | -0.014 |
Token | long |
Token ID | 890 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
ditch | +0.057 |
unks | +0.057 |
stack | +0.053 |
igs | +0.052 |
loft | +0.052 |
Neg logit contributions | |
sure | -0.046 |
happy | -0.046 |
nos | -0.043 |
disl | -0.042 |
caring | -0.042 |
Token | neck |
Token ID | 7393 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
unks | +0.141 |
ditch | +0.138 |
stack | +0.136 |
ifier | +0.134 |
loft | +0.131 |
Neg logit contributions | |
happy | -0.080 |
gr | -0.071 |
sure | -0.071 |
nos | -0.071 |
excited | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
unks | +0.080 |
ditch | +0.079 |
igs | +0.076 |
icer | +0.076 |
stack | +0.075 |
Neg logit contributions | |
sure | -0.016 |
happy | -0.014 |
disl | -0.012 |
free | -0.012 |
caring | -0.012 |
Token | get |
Token ID | 651 |
Feature activation | -9.21e-04 |
Pos logit contributions | |
unks | +0.023 |
ditch | +0.023 |
icer | +0.021 |
ifier | +0.021 |
igs | +0.021 |
Neg logit contributions | |
happy | -0.012 |
sure | -0.012 |
kind | -0.011 |
caring | -0.011 |
listen | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
disl | +0.001 |
sure | +0.001 |
Happy | +0.001 |
listening | +0.001 |
free | +0.001 |
Neg logit contributions | |
igs | -0.002 |
unks | -0.002 |
ditch | -0.002 |
icer | -0.002 |
alk | -0.002 |
Token | pear |
Token ID | 25286 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
unks | +0.027 |
ditch | +0.027 |
igs | +0.025 |
icer | +0.025 |
stack | +0.024 |
Neg logit contributions | |
sure | -0.031 |
happy | -0.030 |
disl | -0.029 |
caring | -0.029 |
Happy | -0.029 |
Token | gorilla |
Token ID | 45314 |
Feature activation | -2.72e-05 |
Pos logit contributions | |
unks | +0.030 |
ditch | +0.029 |
igs | +0.029 |
alk | +0.027 |
ifier | +0.027 |
Neg logit contributions | |
happy | -0.022 |
Happy | -0.021 |
sure | -0.021 |
nos | -0.021 |
kind | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
sure | +0.000 |
disl | +0.000 |
free | +0.000 |
Happy | +0.000 |
caring | +0.000 |
Neg logit contributions | |
unks | -0.000 |
ditch | -0.000 |
igs | -0.000 |
enclosure | -0.000 |
icer | -0.000 |
Token | The |
Token ID | 383 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
unks | +0.024 |
igs | +0.024 |
ditch | +0.024 |
alk | +0.023 |
stack | +0.023 |
Neg logit contributions | |
Happy | -0.012 |
happy | -0.012 |
sure | -0.011 |
excited | -0.010 |
nos | -0.010 |
Token | gorilla |
Token ID | 45314 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
unks | +0.005 |
ditch | +0.005 |
igs | +0.005 |
alk | +0.005 |
icer | +0.005 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.007 |
disl | -0.007 |
Happy | -0.006 |
caring | -0.006 |
Token | has |
Token ID | 468 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ditch | +0.003 |
unks | +0.003 |
igs | +0.003 |
icer | +0.003 |
alk | +0.003 |
Neg logit contributions | |
sure | -0.002 |
happy | -0.002 |
disl | -0.002 |
Happy | -0.002 |
caring | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
unks | +0.055 |
ditch | +0.054 |
igs | +0.053 |
alk | +0.052 |
icer | +0.052 |
Neg logit contributions | |
sure | -0.024 |
happy | -0.023 |
nos | -0.021 |
Happy | -0.021 |
kind | -0.021 |
Token | arms |
Token ID | 5101 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
stack | +0.124 |
ditch | +0.124 |
unks | +0.123 |
ifier | +0.119 |
icer | +0.117 |
Neg logit contributions | |
happy | -0.082 |
nos | -0.077 |
excited | -0.077 |
kind | -0.076 |
gr | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ditch | +0.079 |
unks | +0.079 |
igs | +0.077 |
icer | +0.075 |
stack | +0.075 |
Neg logit contributions | |
sure | -0.034 |
happy | -0.031 |
disl | -0.029 |
free | -0.029 |
Happy | -0.029 |
Token | long |
Token ID | 890 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
unks | +0.029 |
ditch | +0.029 |
igs | +0.027 |
ses | +0.026 |
stack | +0.026 |
Neg logit contributions | |
sure | -0.038 |
disl | -0.036 |
free | -0.036 |
happy | -0.035 |
caring | -0.035 |
Token | hair |
Token ID | 4190 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ditch | +0.067 |
unks | +0.067 |
stack | +0.064 |
icer | +0.063 |
igs | +0.063 |
Neg logit contributions | |
sure | -0.077 |
happy | -0.076 |
disl | -0.074 |
nos | -0.073 |
Happy | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
unks | +0.016 |
ditch | +0.015 |
igs | +0.015 |
stack | +0.014 |
loft | +0.014 |
Neg logit contributions | |
sure | -0.006 |
disl | -0.005 |
Happy | -0.005 |
caring | -0.005 |
happy | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
ditch | +0.038 |
unks | +0.038 |
igs | +0.036 |
icer | +0.035 |
stack | +0.035 |
Neg logit contributions | |
sure | -0.023 |
disl | -0.022 |
Happy | -0.021 |
happy | -0.021 |
caring | -0.021 |
Token | So |
Token ID | 1406 |
Feature activation | +2.66e-04 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.003 |
happy | +0.003 |
caring | +0.003 |
free | +0.003 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
stack | -0.004 |
igs | -0.004 |
enclosure | -0.004 |
Token | Bob |
Token ID | 5811 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
ditch | +0.000 |
unks | +0.000 |
stack | +0.000 |
igs | +0.000 |
enclosure | +0.000 |
Neg logit contributions | |
disl | -0.000 |
responsible | -0.000 |
good | -0.000 |
free | -0.000 |
handsome | -0.000 |
Token | used |
Token ID | 973 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
unks | +0.014 |
ditch | +0.013 |
enclosure | +0.013 |
stack | +0.013 |
igs | +0.013 |
Neg logit contributions | |
free | -0.006 |
disl | -0.006 |
Happy | -0.005 |
sure | -0.005 |
handsome | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
unks | +0.057 |
ditch | +0.057 |
igs | +0.055 |
icer | +0.054 |
stack | +0.054 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.018 |
Happy | -0.017 |
disl | -0.017 |
caring | -0.017 |
Token | long |
Token ID | 890 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
unks | +0.046 |
ditch | +0.046 |
igs | +0.044 |
icer | +0.043 |
alk | +0.042 |
Neg logit contributions | |
sure | -0.039 |
disl | -0.037 |
happy | -0.037 |
Happy | -0.036 |
caring | -0.036 |
Token | be |
Token ID | 307 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
unks | +0.106 |
stack | +0.103 |
icer | +0.101 |
loft | +0.101 |
ditch | +0.099 |
Neg logit contributions | |
happy | -0.098 |
sure | -0.094 |
excited | -0.091 |
kind | -0.091 |
nos | -0.089 |
Token | ak |
Token ID | 461 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
unks | +0.002 |
ditch | +0.002 |
igs | +0.002 |
icer | +0.002 |
alk | +0.002 |
Neg logit contributions | |
sure | -0.009 |
disl | -0.008 |
happy | -0.008 |
Happy | -0.008 |
free | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
ditch | +0.026 |
unks | +0.026 |
igs | +0.026 |
alk | +0.025 |
stack | +0.025 |
Neg logit contributions | |
disl | -0.011 |
sure | -0.011 |
Happy | -0.011 |
Happy | -0.010 |
handsome | -0.010 |
Token | passed |
Token ID | 3804 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
free | +0.004 |
disl | +0.003 |
you | +0.003 |
handsome | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
ditch | -0.005 |
igs | -0.005 |
stack | -0.005 |
unks | -0.005 |
trailer | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
disl | +0.020 |
caring | +0.016 |
forg | +0.016 |
sure | +0.016 |
handsome | +0.016 |
Neg logit contributions | |
ditch | -0.033 |
unks | -0.033 |
icer | -0.032 |
igs | -0.032 |
enclosure | -0.031 |
Token | weird |
Token ID | 7650 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
sure | +0.009 |
happy | +0.008 |
disl | +0.008 |
Happy | +0.008 |
caring | +0.008 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.013 |
igs | -0.013 |
icer | -0.013 |
alk | -0.013 |
Token | animal |
Token ID | 5044 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
unks | +0.012 |
ditch | +0.011 |
igs | +0.011 |
icer | +0.010 |
alk | +0.010 |
Neg logit contributions | |
sure | -0.009 |
happy | -0.009 |
disl | -0.009 |
nos | -0.009 |
Happy | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
unks | +0.014 |
ditch | +0.014 |
igs | +0.013 |
icer | +0.013 |
alk | +0.013 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
Happy | -0.004 |
disl | -0.004 |
nos | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
unks | +0.023 |
ditch | +0.023 |
igs | +0.022 |
alk | +0.021 |
icer | +0.021 |
Neg logit contributions | |
sure | -0.012 |
Happy | -0.012 |
happy | -0.012 |
disl | -0.011 |
excited | -0.011 |
Token | has |
Token ID | 468 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
unks | +0.015 |
ditch | +0.015 |
igs | +0.014 |
alk | +0.014 |
icer | +0.014 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.007 |
Happy | -0.007 |
disl | -0.007 |
nos | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
unks | +0.078 |
igs | +0.075 |
icer | +0.073 |
ditch | +0.073 |
alk | +0.072 |
Neg logit contributions | |
sure | -0.027 |
happy | -0.025 |
nos | -0.024 |
kind | -0.023 |
Happy | -0.022 |
Token | ears |
Token ID | 11368 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
unks | +0.107 |
icer | +0.107 |
stack | +0.103 |
ditch | +0.103 |
ifier | +0.102 |
Neg logit contributions | |
happy | -0.092 |
nos | -0.088 |
excited | -0.088 |
listening | -0.086 |
kind | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ditch | +0.058 |
unks | +0.058 |
igs | +0.056 |
icer | +0.056 |
stack | +0.054 |
Neg logit contributions | |
sure | -0.024 |
happy | -0.022 |
disl | -0.021 |
free | -0.021 |
Happy | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +6.60e-04 |
Pos logit contributions | |
unks | +0.055 |
ditch | +0.055 |
igs | +0.053 |
icer | +0.051 |
stack | +0.051 |
Neg logit contributions | |
sure | -0.048 |
disl | -0.045 |
happy | -0.045 |
Happy | -0.045 |
caring | -0.044 |
Token | fluffy |
Token ID | 39145 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
unks | +0.001 |
ditch | +0.001 |
igs | +0.001 |
icer | +0.001 |
alk | +0.001 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.001 |
nos | -0.001 |
disl | -0.001 |
caring | -0.001 |
Token | tail |
Token ID | 7894 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
unks | +0.036 |
igs | +0.034 |
ditch | +0.032 |
icer | +0.032 |
loft | +0.031 |
Neg logit contributions | |
happy | -0.047 |
nos | -0.045 |
sure | -0.045 |
Happy | -0.044 |
kind | -0.044 |
Token | new |
Token ID | 649 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
unks | +0.010 |
ditch | +0.009 |
igs | +0.009 |
icer | +0.009 |
stack | +0.009 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.005 |
caring | -0.004 |
nos | -0.004 |
kind | -0.004 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
unks | +0.018 |
ditch | +0.018 |
igs | +0.017 |
icer | +0.017 |
loft | +0.016 |
Neg logit contributions | |
happy | -0.011 |
sure | -0.010 |
kind | -0.010 |
disl | -0.010 |
Happy | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
unks | +0.025 |
ditch | +0.024 |
igs | +0.024 |
stack | +0.023 |
icer | +0.023 |
Neg logit contributions | |
sure | -0.010 |
disl | -0.009 |
happy | -0.009 |
Happy | -0.009 |
caring | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
unks | +0.013 |
ditch | +0.013 |
igs | +0.012 |
icer | +0.012 |
stack | +0.012 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.007 |
Happy | -0.007 |
disl | -0.007 |
free | -0.007 |
Token | has |
Token ID | 468 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ditch | +0.007 |
unks | +0.007 |
igs | +0.007 |
icer | +0.007 |
alk | +0.007 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.003 |
Happy | -0.003 |
disl | -0.003 |
caring | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
unks | +0.066 |
ditch | +0.064 |
igs | +0.063 |
stack | +0.062 |
icer | +0.062 |
Neg logit contributions | |
sure | -0.024 |
happy | -0.022 |
Happy | -0.021 |
nos | -0.019 |
handsome | -0.019 |
Token | hair |
Token ID | 4190 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
unks | +0.125 |
ditch | +0.123 |
stack | +0.122 |
icer | +0.119 |
ifi | +0.116 |
Neg logit contributions | |
happy | -0.076 |
excited | -0.070 |
kind | -0.069 |
nos | -0.069 |
sure | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
ditch | +0.043 |
unks | +0.043 |
igs | +0.041 |
stack | +0.041 |
icer | +0.041 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.016 |
free | -0.014 |
Happy | -0.014 |
disl | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e-05 |
Pos logit contributions | |
unks | +0.016 |
ditch | +0.016 |
igs | +0.015 |
icer | +0.015 |
alk | +0.015 |
Neg logit contributions | |
sure | -0.010 |
disl | -0.009 |
happy | -0.009 |
caring | -0.009 |
free | -0.009 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
unks | +0.000 |
ditch | +0.000 |
igs | +0.000 |
icer | +0.000 |
alk | +0.000 |
Neg logit contributions | |
sure | -0.000 |
happy | -0.000 |
nos | -0.000 |
handsome | -0.000 |
Happy | -0.000 |
Token | dress |
Token ID | 6576 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
unks | +0.020 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.018 |
stack | +0.018 |
Neg logit contributions | |
sure | -0.016 |
happy | -0.016 |
disl | -0.015 |
Happy | -0.015 |
handsome | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ditch | +0.023 |
unks | +0.023 |
igs | +0.022 |
icer | +0.022 |
stack | +0.022 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.006 |
Happy | -0.005 |
disl | -0.005 |
free | -0.005 |
Token | E |
Token ID | 36 |
Feature activation | +8.02e-04 |
Pos logit contributions | |
unks | +0.027 |
ditch | +0.027 |
igs | +0.026 |
icer | +0.025 |
stack | +0.025 |
Neg logit contributions | |
sure | -0.019 |
disl | -0.018 |
happy | -0.018 |
Happy | -0.018 |
caring | -0.018 |
Token | lla |
Token ID | 8466 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
ditch | +0.001 |
unks | +0.001 |
igs | +0.001 |
icer | +0.001 |
stack | +0.001 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.001 |
disl | -0.001 |
Happy | -0.001 |
caring | -0.001 |
Token | used |
Token ID | 973 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
unks | +0.003 |
ditch | +0.003 |
igs | +0.003 |
alk | +0.003 |
stack | +0.003 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
Happy | -0.001 |
free | -0.001 |
happy | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
unks | +0.095 |
ditch | +0.093 |
icer | +0.092 |
stack | +0.089 |
enclosure | +0.089 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.015 |
excited | -0.013 |
caring | -0.012 |
kind | -0.012 |
Token | long |
Token ID | 890 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
unks | +0.047 |
ditch | +0.046 |
stack | +0.044 |
icer | +0.043 |
ifier | +0.042 |
Neg logit contributions | |
sure | -0.043 |
happy | -0.042 |
nos | -0.040 |
kind | -0.039 |
caring | -0.038 |
Token | nose |
Token ID | 9686 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
unks | +0.105 |
stack | +0.101 |
ditch | +0.096 |
icer | +0.096 |
ifier | +0.095 |
Neg logit contributions | |
happy | -0.100 |
sure | -0.096 |
kind | -0.093 |
excited | -0.091 |
nos | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
unks | +0.088 |
ditch | +0.088 |
igs | +0.085 |
icer | +0.084 |
stack | +0.083 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.020 |
disl | -0.019 |
Happy | -0.019 |
caring | -0.018 |
Token | gather |
Token ID | 6431 |
Feature activation | -8.48e-04 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.018 |
icer | +0.018 |
ippy | +0.017 |
ses | +0.017 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.010 |
kind | -0.009 |
caring | -0.009 |
listen | -0.009 |
Token | sticks |
Token ID | 16461 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
caring | +0.001 |
Happy | +0.001 |
free | +0.001 |
Neg logit contributions | |
unks | -0.002 |
ditch | -0.002 |
icer | -0.001 |
stack | -0.001 |
igs | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
unks | +0.086 |
ditch | +0.086 |
icer | +0.083 |
igs | +0.082 |
loft | +0.080 |
Neg logit contributions | |
sure | -0.026 |
happy | -0.023 |
free | -0.021 |
caring | -0.020 |
excited | -0.020 |
Token | can |
Token ID | 460 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
sure | +0.018 |
happy | +0.016 |
don | +0.015 |
free | +0.015 |
nos | +0.015 |
Neg logit contributions | |
unks | -0.041 |
ditch | -0.040 |
igs | -0.039 |
stack | -0.039 |
icer | -0.038 |
Token | use |
Token ID | 779 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
ditch | +0.012 |
unks | +0.012 |
icer | +0.012 |
igs | +0.012 |
loft | +0.012 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.005 |
listen | -0.004 |
disl | -0.004 |
don | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ditch | +0.067 |
unks | +0.067 |
stack | +0.066 |
ippy | +0.066 |
loft | +0.065 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.018 |
caring | -0.016 |
Happy | -0.015 |
you | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
unks | +0.035 |
ippy | +0.033 |
icer | +0.033 |
stack | +0.033 |
ditch | +0.033 |
Neg logit contributions | |
happy | -0.043 |
sure | -0.043 |
kind | -0.042 |
nos | -0.041 |
caring | -0.041 |
Token | my |
Token ID | 616 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ditch | +0.048 |
unks | +0.048 |
icer | +0.046 |
loft | +0.045 |
stack | +0.045 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.015 |
caring | -0.015 |
disl | -0.014 |
Happy | -0.013 |
Token | green |
Token ID | 4077 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
unks | +0.039 |
ditch | +0.039 |
icer | +0.036 |
igs | +0.036 |
ippy | +0.035 |
Neg logit contributions | |
happy | -0.049 |
sure | -0.048 |
nos | -0.046 |
kind | -0.045 |
disl | -0.045 |
Token | clay |
Token ID | 21558 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ditch | +0.098 |
unks | +0.097 |
ogo | +0.093 |
ippy | +0.093 |
ifi | +0.092 |
Neg logit contributions | |
happy | -0.088 |
nos | -0.087 |
gr | -0.086 |
's | -0.086 |
kind | -0.086 |
Token | ." |
Token ID | 526 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
unks | +0.047 |
ditch | +0.046 |
igs | +0.045 |
icer | +0.044 |
alk | +0.043 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.021 |
disl | -0.021 |
Happy | -0.021 |
caring | -0.020 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
ditch | +0.017 |
unks | +0.017 |
igs | +0.016 |
stack | +0.016 |
alk | +0.016 |
Neg logit contributions | |
sure | -0.008 |
disl | -0.008 |
free | -0.007 |
happy | -0.007 |
caring | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
ditch | +0.014 |
unks | +0.013 |
igs | +0.013 |
enclosure | +0.013 |
icer | +0.013 |
Neg logit contributions | |
free | -0.007 |
disl | -0.007 |
sure | -0.007 |
caring | -0.007 |
happy | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
igs | +0.006 |
ids | +0.006 |
alk | +0.006 |
inn | +0.006 |
ditch | +0.006 |
Neg logit contributions | |
disl | -0.006 |
talented | -0.006 |
Good | -0.005 |
Happy | -0.005 |
good | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
unks | +0.036 |
ditch | +0.036 |
igs | +0.035 |
icer | +0.034 |
alk | +0.034 |
Neg logit contributions | |
sure | -0.014 |
happy | -0.012 |
disl | -0.012 |
Happy | -0.012 |
caring | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
sure | +0.006 |
happy | +0.005 |
caring | +0.005 |
listening | +0.004 |
kind | +0.004 |
Neg logit contributions | |
unks | -0.020 |
ditch | -0.020 |
igs | -0.019 |
icer | -0.019 |
alk | -0.019 |
Token | thief |
Token ID | 25906 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
Happy | +0.005 |
free | +0.004 |
happy | +0.004 |
Neg logit contributions | |
ditch | -0.009 |
unks | -0.008 |
igs | -0.008 |
icer | -0.008 |
loft | -0.008 |
Token | take |
Token ID | 1011 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
sure | +0.011 |
happy | +0.010 |
disl | +0.010 |
Happy | +0.010 |
free | +0.009 |
Neg logit contributions | |
unks | -0.020 |
ditch | -0.020 |
igs | -0.019 |
icer | -0.019 |
alk | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ditch | +0.017 |
unks | +0.016 |
igs | +0.016 |
icer | +0.016 |
enclosure | +0.015 |
Neg logit contributions | |
disl | -0.010 |
sure | -0.009 |
caring | -0.009 |
pleased | -0.009 |
handsome | -0.009 |
Token | red |
Token ID | 2266 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
unks | +0.053 |
ditch | +0.052 |
igs | +0.051 |
icer | +0.049 |
stack | +0.049 |
Neg logit contributions | |
sure | -0.047 |
happy | -0.046 |
disl | -0.044 |
caring | -0.043 |
Happy | -0.043 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
unks | +0.125 |
igs | +0.120 |
icer | +0.113 |
ifi | +0.112 |
loft | +0.111 |
Neg logit contributions | |
kind | -0.069 |
happy | -0.069 |
nos | -0.069 |
's | -0.066 |
gr | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
unks | +0.085 |
igs | +0.082 |
icer | +0.081 |
ditch | +0.080 |
stack | +0.079 |
Neg logit contributions | |
sure | -0.019 |
happy | -0.018 |
excited | -0.015 |
free | -0.015 |
if | -0.015 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
sure | +0.004 |
disl | +0.004 |
caring | +0.004 |
free | +0.004 |
happy | +0.004 |
Neg logit contributions | |
ditch | -0.006 |
unks | -0.005 |
icer | -0.005 |
igs | -0.005 |
stack | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.010 |
igs | +0.010 |
icer | +0.010 |
stack | +0.010 |
Neg logit contributions | |
sure | -0.003 |
disl | -0.003 |
Happy | -0.003 |
free | -0.003 |
caring | -0.003 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.033 |
igs | +0.033 |
icer | +0.032 |
alk | +0.032 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.008 |
nos | -0.007 |
caring | -0.006 |
disl | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
disl | +0.002 |
talented | +0.001 |
Good | +0.001 |
minded | +0.001 |
beh | +0.001 |
Neg logit contributions | |
stack | -0.001 |
ids | -0.001 |
igs | -0.001 |
inn | -0.001 |
ates | -0.001 |
Token | Ell |
Token ID | 7122 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
disl | +0.008 |
sure | +0.008 |
free | +0.008 |
caring | +0.007 |
handsome | +0.007 |
Neg logit contributions | |
ditch | -0.017 |
unks | -0.017 |
stack | -0.016 |
enclosure | -0.016 |
loft | -0.016 |
Token | a |
Token ID | 64 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
disl | +0.014 |
sure | +0.013 |
Happy | +0.013 |
caring | +0.013 |
listening | +0.013 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.013 |
icer | -0.013 |
igs | -0.013 |
ippy | -0.013 |
Token | used |
Token ID | 973 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
disl | +0.010 |
free | +0.010 |
sure | +0.009 |
Happy | +0.009 |
caring | +0.009 |
Neg logit contributions | |
unks | -0.023 |
ditch | -0.023 |
igs | -0.023 |
enclosure | -0.022 |
alk | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
unks | +0.049 |
ditch | +0.049 |
icer | +0.047 |
igs | +0.047 |
stack | +0.046 |
Neg logit contributions | |
sure | -0.015 |
happy | -0.013 |
caring | -0.011 |
Happy | -0.011 |
excited | -0.011 |
Token | long |
Token ID | 890 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.034 |
igs | +0.032 |
icer | +0.032 |
loft | +0.031 |
Neg logit contributions | |
sure | -0.035 |
happy | -0.034 |
disl | -0.033 |
caring | -0.032 |
Happy | -0.032 |
Token | trunk |
Token ID | 21427 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
stack | +0.112 |
unks | +0.111 |
icer | +0.109 |
loft | +0.109 |
ditch | +0.103 |
Neg logit contributions | |
happy | -0.091 |
excited | -0.084 |
kind | -0.082 |
's | -0.081 |
sure | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
unks | +0.068 |
ditch | +0.068 |
igs | +0.066 |
icer | +0.065 |
stack | +0.064 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.015 |
disl | -0.014 |
Happy | -0.014 |
free | -0.014 |
Token | open |
Token ID | 1280 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
unks | +0.006 |
ditch | +0.005 |
icer | +0.005 |
igs | +0.005 |
loft | +0.005 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
disl | -0.004 |
free | -0.004 |
caring | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
unks | +0.006 |
ditch | +0.006 |
igs | +0.006 |
ses | +0.006 |
ifi | +0.006 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.001 |
Happy | -0.001 |
if | -0.001 |
excited | -0.001 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
unks | +0.026 |
igs | +0.026 |
ifi | +0.024 |
alk | +0.023 |
ogo | +0.023 |
Neg logit contributions | |
happy | -0.032 |
kind | -0.030 |
nos | -0.030 |
gr | -0.029 |
sure | -0.029 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
unks | +0.024 |
icer | +0.023 |
ifier | +0.022 |
igs | +0.022 |
loft | +0.021 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.006 |
excited | -0.006 |
kind | -0.005 |
enthusiastic | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
ditch | +0.038 |
unks | +0.038 |
stack | +0.037 |
alk | +0.036 |
igs | +0.036 |
Neg logit contributions | |
handsome | -0.017 |
disl | -0.017 |
sure | -0.016 |
happy | -0.015 |
caring | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.003 |
happy | +0.003 |
caring | +0.003 |
free | +0.003 |
Neg logit contributions | |
ditch | -0.006 |
unks | -0.006 |
igs | -0.005 |
stack | -0.005 |
alk | -0.005 |
Token | used |
Token ID | 973 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
disl | +0.008 |
sure | +0.008 |
Happy | +0.008 |
free | +0.007 |
happy | +0.007 |
Neg logit contributions | |
ditch | -0.016 |
unks | -0.016 |
igs | -0.015 |
stack | -0.015 |
alk | -0.015 |
Token | its |
Token ID | 663 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
unks | +0.072 |
ditch | +0.070 |
icer | +0.069 |
igs | +0.067 |
loft | +0.067 |
Neg logit contributions | |
sure | -0.033 |
happy | -0.030 |
caring | -0.029 |
disl | -0.027 |
excited | -0.027 |
Token | long |
Token ID | 890 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
unks | +0.044 |
ditch | +0.043 |
icer | +0.042 |
igs | +0.041 |
stack | +0.040 |
Neg logit contributions | |
sure | -0.044 |
happy | -0.043 |
nos | -0.041 |
caring | -0.040 |
kind | -0.040 |
Token | legs |
Token ID | 7405 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
unks | +0.095 |
icer | +0.092 |
stack | +0.087 |
ditch | +0.085 |
ifier | +0.084 |
Neg logit contributions | |
happy | -0.107 |
sure | -0.105 |
kind | -0.101 |
excited | -0.101 |
nos | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
unks | +0.089 |
ditch | +0.088 |
igs | +0.086 |
alk | +0.084 |
stack | +0.084 |
Neg logit contributions | |
sure | -0.029 |
disl | -0.027 |
Happy | -0.027 |
happy | -0.026 |
caring | -0.026 |
Token | climb |
Token ID | 12080 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
unks | +0.011 |
ditch | +0.011 |
icer | +0.011 |
igs | +0.010 |
loft | +0.010 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.007 |
free | -0.007 |
disl | -0.007 |
caring | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
unks | +0.011 |
ditch | +0.011 |
igs | +0.011 |
icer | +0.011 |
ifier | +0.010 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
Happy | -0.004 |
free | -0.004 |
caring | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.033 |
igs | +0.032 |
icer | +0.032 |
stack | +0.031 |
Neg logit contributions | |
sure | -0.013 |
happy | -0.012 |
Happy | -0.011 |
free | -0.011 |
disl | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ditch | +0.023 |
unks | +0.023 |
igs | +0.022 |
icer | +0.022 |
stack | +0.022 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.005 |
Happy | -0.005 |
disl | -0.005 |
caring | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ditch | +0.028 |
unks | +0.028 |
igs | +0.026 |
alk | +0.026 |
icer | +0.026 |
Neg logit contributions | |
sure | -0.015 |
disl | -0.014 |
happy | -0.014 |
Happy | -0.014 |
free | -0.014 |
Token | bird |
Token ID | 6512 |
Feature activation | -4.51e-03 |
Pos logit contributions | |
sure | +0.018 |
happy | +0.017 |
disl | +0.017 |
Happy | +0.017 |
caring | +0.016 |
Neg logit contributions | |
unks | -0.027 |
ditch | -0.026 |
igs | -0.025 |
icer | -0.025 |
alk | -0.024 |
Token | used |
Token ID | 973 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
happy | +0.004 |
Happy | +0.004 |
caring | +0.004 |
Neg logit contributions | |
unks | -0.010 |
ditch | -0.010 |
igs | -0.010 |
icer | -0.009 |
stack | -0.009 |
Token | its |
Token ID | 663 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
unks | +0.077 |
ditch | +0.075 |
icer | +0.075 |
igs | +0.073 |
loft | +0.073 |
Neg logit contributions | |
sure | -0.030 |
happy | -0.028 |
caring | -0.025 |
excited | -0.024 |
disl | -0.024 |
Token | long |
Token ID | 890 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ditch | +0.066 |
loft | +0.066 |
stack | +0.064 |
unks | +0.064 |
icer | +0.063 |
Neg logit contributions | |
happy | -0.062 |
sure | -0.061 |
nos | -0.057 |
kind | -0.057 |
gr | -0.056 |
Token | be |
Token ID | 307 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
stack | +0.113 |
loft | +0.110 |
unks | +0.107 |
icer | +0.105 |
ditch | +0.105 |
Neg logit contributions | |
happy | -0.093 |
sure | -0.085 |
kind | -0.084 |
gr | -0.083 |
excited | -0.083 |
Token | ak |
Token ID | 461 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ditch | +0.009 |
icer | +0.009 |
stack | +0.009 |
unks | +0.008 |
loft | +0.008 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.022 |
kind | -0.021 |
excited | -0.021 |
caring | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.034 |
igs | +0.033 |
alk | +0.032 |
stack | +0.032 |
Neg logit contributions | |
sure | -0.013 |
disl | -0.012 |
Happy | -0.012 |
happy | -0.012 |
caring | -0.011 |
Token | get |
Token ID | 651 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
disl | +0.002 |
caring | +0.002 |
kind | +0.002 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
icer | -0.003 |
igs | -0.003 |
loft | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
disl | +0.004 |
sure | +0.003 |
Happy | +0.003 |
caring | +0.003 |
free | +0.003 |
Neg logit contributions | |
unks | -0.006 |
ditch | -0.006 |
igs | -0.006 |
alk | -0.006 |
ifier | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
unks | +0.052 |
ditch | +0.050 |
stack | +0.049 |
alk | +0.049 |
alks | +0.049 |
Neg logit contributions | |
sure | -0.012 |
listened | -0.012 |
happy | -0.011 |
excited | -0.011 |
didn | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
unks | +0.041 |
ditch | +0.040 |
stack | +0.040 |
icer | +0.040 |
igs | +0.039 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.004 |
listening | -0.004 |
nos | -0.003 |
kind | -0.003 |
Token | use |
Token ID | 779 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
unks | +0.022 |
ditch | +0.021 |
icer | +0.021 |
igs | +0.021 |
stack | +0.020 |
Neg logit contributions | |
sure | -0.010 |
happy | -0.009 |
disl | -0.009 |
Happy | -0.008 |
caring | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
unks | +0.067 |
stack | +0.067 |
ditch | +0.065 |
ifi | +0.065 |
icer | +0.064 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.016 |
kind | -0.012 |
excited | -0.012 |
caring | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
unks | +0.038 |
ditch | +0.038 |
icer | +0.037 |
stack | +0.036 |
igs | +0.035 |
Neg logit contributions | |
happy | -0.033 |
sure | -0.032 |
nos | -0.032 |
kind | -0.030 |
excited | -0.030 |
Token | red |
Token ID | 2266 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
unks | +0.055 |
ditch | +0.054 |
icer | +0.053 |
stack | +0.051 |
ifier | +0.050 |
Neg logit contributions | |
happy | -0.047 |
nos | -0.045 |
sure | -0.045 |
kind | -0.044 |
excited | -0.043 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ditch | +0.118 |
unks | +0.117 |
ifi | +0.114 |
icer | +0.113 |
inger | +0.111 |
Neg logit contributions | |
's | -0.068 |
happy | -0.067 |
to | -0.067 |
kind | -0.066 |
nos | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
unks | +0.087 |
ditch | +0.087 |
icer | +0.084 |
igs | +0.084 |
loft | +0.082 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.018 |
excited | -0.016 |
free | -0.015 |
if | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.002 |
caring | +0.002 |
happy | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
ditch | -0.005 |
unks | -0.005 |
igs | -0.005 |
icer | -0.005 |
alk | -0.005 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
unks | +0.043 |
ditch | +0.042 |
alk | +0.041 |
stack | +0.041 |
alks | +0.040 |
Neg logit contributions | |
sure | -0.011 |
listened | -0.010 |
happy | -0.010 |
excited | -0.009 |
didn | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.018 |
stack | +0.018 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.007 |
disl | -0.007 |
Happy | -0.007 |
caring | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
ditch | +0.025 |
unks | +0.025 |
igs | +0.024 |
ses | +0.024 |
icer | +0.024 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.005 |
caring | -0.004 |
Happy | -0.004 |
free | -0.004 |
Token | E |
Token ID | 36 |
Feature activation | -6.53e-03 |
Pos logit contributions | |
unks | +0.018 |
ditch | +0.018 |
igs | +0.017 |
icer | +0.017 |
alk | +0.017 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.010 |
disl | -0.010 |
caring | -0.010 |
Happy | -0.010 |
Token | lla |
Token ID | 8466 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
sure | +0.011 |
happy | +0.010 |
disl | +0.010 |
Happy | +0.010 |
caring | +0.010 |
Neg logit contributions | |
ditch | -0.011 |
unks | -0.011 |
igs | -0.010 |
icer | -0.010 |
alk | -0.010 |
Token | used |
Token ID | 973 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
disl | +0.004 |
sure | +0.003 |
Happy | +0.003 |
free | +0.003 |
caring | +0.003 |
Neg logit contributions | |
unks | -0.009 |
ditch | -0.009 |
igs | -0.008 |
stack | -0.008 |
alk | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
unks | +0.059 |
ditch | +0.058 |
icer | +0.056 |
stack | +0.055 |
enclosure | +0.054 |
Neg logit contributions | |
sure | -0.015 |
happy | -0.014 |
caring | -0.012 |
excited | -0.011 |
kind | -0.011 |
Token | long |
Token ID | 890 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
unks | +0.042 |
ditch | +0.041 |
icer | +0.039 |
stack | +0.039 |
ippy | +0.038 |
Neg logit contributions | |
sure | -0.042 |
happy | -0.041 |
kind | -0.038 |
nos | -0.038 |
caring | -0.038 |
Token | nose |
Token ID | 9686 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
unks | +0.108 |
stack | +0.107 |
ifier | +0.104 |
icer | +0.102 |
ippy | +0.101 |
Neg logit contributions | |
happy | -0.090 |
kind | -0.083 |
sure | -0.083 |
's | -0.081 |
gr | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
unks | +0.059 |
ditch | +0.059 |
igs | +0.057 |
alk | +0.056 |
stack | +0.056 |
Neg logit contributions | |
sure | -0.018 |
disl | -0.017 |
Happy | -0.016 |
happy | -0.016 |
caring | -0.016 |
Token | pick |
Token ID | 2298 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
unks | +0.011 |
icer | +0.011 |
ditch | +0.011 |
ippy | +0.010 |
ifier | +0.010 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.007 |
caring | -0.006 |
free | -0.006 |
kind | -0.006 |
Token | up |
Token ID | 510 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
sure | +0.022 |
disl | +0.020 |
happy | +0.020 |
Happy | +0.019 |
caring | +0.019 |
Neg logit contributions | |
unks | -0.044 |
ditch | -0.043 |
igs | -0.042 |
icer | -0.041 |
alk | -0.041 |
Token | sticks |
Token ID | 16461 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.029 |
igs | +0.029 |
loft | +0.027 |
icer | +0.027 |
Neg logit contributions | |
sure | -0.016 |
disl | -0.016 |
Happy | -0.015 |
free | -0.015 |
happy | -0.015 |
Token | new |
Token ID | 649 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
unks | +0.032 |
ditch | +0.031 |
igs | +0.030 |
stack | +0.030 |
alk | +0.030 |
Neg logit contributions | |
happy | -0.015 |
sure | -0.014 |
handsome | -0.013 |
kind | -0.013 |
nos | -0.013 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
unks | +0.035 |
ditch | +0.033 |
igs | +0.033 |
icer | +0.031 |
ogo | +0.031 |
Neg logit contributions | |
happy | -0.016 |
kind | -0.015 |
sure | -0.013 |
nos | -0.013 |
excited | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.029 |
igs | +0.029 |
icer | +0.028 |
alk | +0.027 |
Neg logit contributions | |
sure | -0.007 |
happy | -0.007 |
Happy | -0.006 |
free | -0.006 |
listening | -0.006 |
Token | It |
Token ID | 632 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
ditch | +0.021 |
unks | +0.021 |
igs | +0.021 |
icer | +0.020 |
stack | +0.020 |
Neg logit contributions | |
sure | -0.010 |
Happy | -0.010 |
happy | -0.010 |
excited | -0.009 |
disl | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ditch | +0.007 |
unks | +0.007 |
igs | +0.006 |
alk | +0.006 |
icer | +0.006 |
Neg logit contributions | |
sure | -0.002 |
happy | -0.001 |
Happy | -0.001 |
disl | -0.001 |
caring | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
unks | +0.087 |
ditch | +0.084 |
stack | +0.083 |
igs | +0.083 |
icer | +0.082 |
Neg logit contributions | |
sure | -0.027 |
happy | -0.026 |
kind | -0.024 |
Happy | -0.023 |
nos | -0.023 |
Token | hair |
Token ID | 4190 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
unks | +0.131 |
ditch | +0.128 |
stack | +0.127 |
icer | +0.126 |
ifi | +0.122 |
Neg logit contributions | |
happy | -0.069 |
excited | -0.062 |
kind | -0.061 |
sweet | -0.061 |
nos | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
ditch | +0.046 |
unks | +0.045 |
igs | +0.044 |
stack | +0.043 |
alk | +0.043 |
Neg logit contributions | |
sure | -0.014 |
happy | -0.013 |
free | -0.011 |
Happy | -0.011 |
listening | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.018 |
igs | +0.018 |
icer | +0.017 |
alk | +0.017 |
Neg logit contributions | |
sure | -0.010 |
happy | -0.009 |
disl | -0.009 |
Happy | -0.009 |
caring | -0.009 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
happy | +0.003 |
sure | +0.002 |
nos | +0.002 |
handsome | +0.002 |
kind | +0.002 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.004 |
alk | -0.004 |
icer | -0.004 |
Token | dress |
Token ID | 6576 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
unks | +0.020 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.018 |
loft | +0.018 |
Neg logit contributions | |
happy | -0.015 |
sure | -0.014 |
handsome | -0.014 |
Happy | -0.014 |
kind | -0.014 |
Token | es |
Token ID | 274 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
sure | +0.011 |
disl | +0.011 |
caring | +0.010 |
handsome | +0.010 |
Happy | +0.010 |
Neg logit contributions | |
unks | -0.013 |
igs | -0.012 |
ditch | -0.012 |
alk | -0.012 |
icer | -0.011 |
Token | best |
Token ID | 1266 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
Happy | +0.002 |
free | +0.002 |
happy | +0.002 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
igs | -0.005 |
stack | -0.005 |
loft | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -9.99e-04 |
Pos logit contributions | |
unks | +0.022 |
ditch | +0.022 |
igs | +0.022 |
alk | +0.021 |
icer | +0.021 |
Neg logit contributions | |
sure | -0.010 |
disl | -0.010 |
happy | -0.009 |
Happy | -0.009 |
caring | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
Happy | +0.001 |
disl | +0.001 |
excited | +0.001 |
Neg logit contributions | |
ditch | -0.002 |
unks | -0.002 |
igs | -0.002 |
stack | -0.002 |
icer | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
unks | +0.017 |
ditch | +0.017 |
igs | +0.017 |
icer | +0.017 |
alk | +0.016 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.006 |
Happy | -0.005 |
listened | -0.005 |
caring | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
unks | +0.044 |
ditch | +0.044 |
igs | +0.043 |
icer | +0.042 |
stack | +0.042 |
Neg logit contributions | |
sure | -0.018 |
happy | -0.017 |
Happy | -0.015 |
caring | -0.015 |
disl | -0.015 |
Token | necks |
Token ID | 44184 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
ditch | +0.123 |
stack | +0.123 |
unks | +0.121 |
ifier | +0.119 |
icer | +0.116 |
Neg logit contributions | |
happy | -0.076 |
sure | -0.071 |
excited | -0.068 |
kind | -0.068 |
nos | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
ditch | +0.074 |
unks | +0.072 |
igs | +0.070 |
icer | +0.070 |
stack | +0.069 |
Neg logit contributions | |
sure | -0.028 |
happy | -0.026 |
disl | -0.024 |
caring | -0.024 |
listening | -0.024 |
Token | spots |
Token ID | 10222 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.017 |
stack | +0.017 |
Neg logit contributions | |
sure | -0.014 |
happy | -0.013 |
disl | -0.013 |
Happy | -0.013 |
caring | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -9.99e-04 |
Pos logit contributions | |
unks | +0.044 |
ditch | +0.044 |
igs | +0.042 |
icer | +0.042 |
stack | +0.041 |
Neg logit contributions | |
sure | -0.013 |
happy | -0.012 |
disl | -0.012 |
Happy | -0.011 |
caring | -0.011 |
Token | Sam |
Token ID | 3409 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
sure | +0.001 |
Happy | +0.001 |
happy | +0.001 |
disl | +0.001 |
excited | +0.001 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.002 |
igs | -0.002 |
stack | -0.002 |
loft | -0.002 |
Token | Can |
Token ID | 6090 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
Happy | +0.002 |
free | +0.002 |
caring | +0.002 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
igs | -0.005 |
alk | -0.005 |
ses | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.018 |
igs | +0.018 |
icer | +0.018 |
stack | +0.018 |
Neg logit contributions | |
sure | -0.007 |
disl | -0.007 |
happy | -0.006 |
free | -0.006 |
Happy | -0.006 |
Token | play |
Token ID | 711 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
ditch | +0.065 |
unks | +0.064 |
icer | +0.063 |
stack | +0.062 |
loft | +0.062 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.022 |
Happy | -0.019 |
kind | -0.019 |
nos | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
sure | +0.003 |
happy | +0.003 |
Happy | +0.003 |
disl | +0.003 |
caring | +0.003 |
Neg logit contributions | |
unks | -0.012 |
ditch | -0.012 |
igs | -0.011 |
icer | -0.011 |
stack | -0.011 |
Token | my |
Token ID | 616 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
ditch | +0.054 |
unks | +0.053 |
stack | +0.051 |
loft | +0.051 |
alk | +0.051 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.019 |
Happy | -0.018 |
disl | -0.018 |
caring | -0.017 |
Token | red |
Token ID | 2266 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
unks | +0.015 |
ditch | +0.015 |
igs | +0.015 |
stack | +0.014 |
icer | +0.014 |
Neg logit contributions | |
sure | -0.012 |
happy | -0.012 |
Happy | -0.012 |
disl | -0.012 |
nos | -0.012 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
unks | +0.118 |
ditch | +0.116 |
loft | +0.116 |
igs | +0.115 |
ifi | +0.114 |
Neg logit contributions | |
happy | -0.071 |
nos | -0.066 |
kind | -0.066 |
's | -0.065 |
gr | -0.064 |
Token | in |
Token ID | 287 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
unks | +0.075 |
ditch | +0.074 |
igs | +0.072 |
loft | +0.070 |
alk | +0.069 |
Neg logit contributions | |
sure | -0.034 |
happy | -0.033 |
Happy | -0.031 |
nos | -0.030 |
free | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
ses | +0.034 |
unks | +0.034 |
stack | +0.033 |
sed | +0.033 |
loft | +0.033 |
Neg logit contributions | |
happy | -0.005 |
sure | -0.005 |
kind | -0.004 |
you | -0.003 |
if | -0.003 |
Token | backyard |
Token ID | 24296 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
unks | +0.003 |
igs | +0.003 |
ditch | +0.003 |
icer | +0.003 |
ippy | +0.003 |
Neg logit contributions | |
happy | -0.005 |
sure | -0.005 |
kind | -0.005 |
nos | -0.005 |
Happy | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
ditch | +0.035 |
unks | +0.035 |
igs | +0.034 |
icer | +0.034 |
stack | +0.033 |
Neg logit contributions | |
sure | -0.024 |
disl | -0.023 |
Happy | -0.022 |
happy | -0.022 |
caring | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
disl | +0.006 |
sure | +0.006 |
Happy | +0.005 |
Happy | +0.005 |
free | +0.005 |
Neg logit contributions | |
unks | -0.010 |
ditch | -0.010 |
igs | -0.010 |
enclosure | -0.010 |
stack | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
unks | +0.018 |
ditch | +0.018 |
igs | +0.018 |
icer | +0.017 |
alk | +0.017 |
Neg logit contributions | |
sure | -0.009 |
happy | -0.009 |
disl | -0.008 |
Happy | -0.008 |
caring | -0.008 |
Token | put |
Token ID | 1234 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
unks | +0.014 |
ditch | +0.014 |
igs | +0.014 |
icer | +0.013 |
alk | +0.013 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.005 |
Happy | -0.005 |
listened | -0.005 |
excited | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
unks | +0.008 |
ditch | +0.008 |
igs | +0.007 |
alk | +0.007 |
icer | +0.007 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.005 |
Happy | -0.005 |
disl | -0.005 |
caring | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
unks | +0.015 |
ditch | +0.015 |
igs | +0.014 |
stack | +0.014 |
alk | +0.014 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.007 |
Happy | -0.007 |
disl | -0.007 |
caring | -0.007 |
Token | brown |
Token ID | 7586 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
unks | +0.008 |
ditch | +0.008 |
igs | +0.008 |
icer | +0.008 |
stack | +0.008 |
Neg logit contributions | |
sure | -0.010 |
happy | -0.010 |
disl | -0.009 |
Happy | -0.009 |
caring | -0.009 |
Token | coats |
Token ID | 30720 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
unks | +0.096 |
ditch | +0.095 |
stack | +0.090 |
ifi | +0.089 |
igs | +0.089 |
Neg logit contributions | |
happy | -0.089 |
Happy | -0.088 |
nos | -0.088 |
gr | -0.087 |
disl | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ditch | +0.046 |
unks | +0.046 |
igs | +0.045 |
icer | +0.044 |
alk | +0.043 |
Neg logit contributions | |
sure | -0.019 |
happy | -0.017 |
Happy | -0.016 |
free | -0.016 |
disl | -0.015 |
Token | hats |
Token ID | 23910 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
unks | +0.031 |
ditch | +0.031 |
igs | +0.030 |
icer | +0.029 |
stack | +0.028 |
Neg logit contributions | |
sure | -0.033 |
happy | -0.031 |
disl | -0.031 |
Happy | -0.031 |
caring | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
unks | +0.010 |
ditch | +0.010 |
igs | +0.009 |
stack | +0.009 |
alk | +0.009 |
Neg logit contributions | |
disl | -0.006 |
sure | -0.006 |
caring | -0.005 |
Happy | -0.005 |
happy | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
ditch | +0.016 |
unks | +0.016 |
igs | +0.015 |
icer | +0.014 |
alk | +0.014 |
Neg logit contributions | |
sure | -0.018 |
disl | -0.017 |
happy | -0.017 |
Happy | -0.016 |
caring | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ditch | +0.005 |
unks | +0.005 |
igs | +0.005 |
icer | +0.005 |
alk | +0.005 |
Neg logit contributions | |
sure | -0.004 |
disl | -0.004 |
happy | -0.004 |
caring | -0.004 |
free | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.034 |
igs | +0.033 |
icer | +0.032 |
alk | +0.032 |
Neg logit contributions | |
sure | -0.012 |
happy | -0.011 |
disl | -0.010 |
Happy | -0.010 |
caring | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.034 |
igs | +0.033 |
stack | +0.032 |
alk | +0.032 |
Neg logit contributions | |
sure | -0.011 |
disl | -0.010 |
free | -0.010 |
Happy | -0.010 |
happy | -0.009 |
Token | use |
Token ID | 779 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
sure | +0.016 |
happy | +0.015 |
disl | +0.015 |
Happy | +0.015 |
caring | +0.014 |
Neg logit contributions | |
unks | -0.029 |
ditch | -0.029 |
igs | -0.028 |
icer | -0.027 |
stack | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
unks | +0.054 |
ditch | +0.053 |
icer | +0.051 |
stack | +0.050 |
igs | +0.050 |
Neg logit contributions | |
sure | -0.025 |
happy | -0.023 |
disl | -0.022 |
Happy | -0.022 |
caring | -0.022 |
Token | long |
Token ID | 890 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
unks | +0.043 |
ditch | +0.043 |
igs | +0.041 |
icer | +0.040 |
stack | +0.040 |
Neg logit contributions | |
happy | -0.036 |
sure | -0.036 |
disl | -0.034 |
nos | -0.034 |
Happy | -0.034 |
Token | tail |
Token ID | 7894 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
unks | +0.090 |
ifier | +0.085 |
stack | +0.085 |
ditch | +0.084 |
icer | +0.082 |
Neg logit contributions | |
happy | -0.103 |
kind | -0.097 |
gr | -0.097 |
nos | -0.097 |
disl | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
unks | +0.088 |
ditch | +0.088 |
icer | +0.085 |
igs | +0.085 |
stack | +0.083 |
Neg logit contributions | |
sure | -0.021 |
happy | -0.019 |
nos | -0.016 |
free | -0.016 |
disl | -0.016 |
Token | swing |
Token ID | 9628 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
happy | +0.003 |
sure | +0.003 |
kind | +0.003 |
disl | +0.003 |
listen | +0.003 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
icer | -0.005 |
igs | -0.005 |
ifier | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
unks | +0.023 |
ditch | +0.023 |
igs | +0.023 |
icer | +0.022 |
alk | +0.022 |
Neg logit contributions | |
sure | -0.012 |
disl | -0.011 |
happy | -0.011 |
Happy | -0.010 |
caring | -0.010 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
unks | +0.012 |
ditch | +0.011 |
igs | +0.011 |
ifier | +0.011 |
icer | +0.011 |
Neg logit contributions | |
happy | -0.007 |
sure | -0.007 |
nos | -0.007 |
Happy | -0.007 |
disl | -0.007 |
Token | game |
Token ID | 983 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
unks | +0.032 |
ditch | +0.031 |
icer | +0.030 |
stack | +0.030 |
igs | +0.029 |
Neg logit contributions | |
sure | -0.020 |
happy | -0.020 |
kind | -0.019 |
caring | -0.019 |
nos | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.74e-03 |
Pos logit contributions | |
unks | +0.039 |
ditch | +0.039 |
igs | +0.038 |
icer | +0.037 |
stack | +0.037 |
Neg logit contributions | |
sure | -0.009 |
happy | -0.008 |
disl | -0.008 |
Happy | -0.008 |
caring | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
unks | +0.020 |
ditch | +0.020 |
igs | +0.019 |
icer | +0.019 |
alk | +0.019 |
Neg logit contributions | |
sure | -0.012 |
happy | -0.011 |
disl | -0.011 |
Happy | -0.011 |
caring | -0.011 |
Token | took |
Token ID | 1718 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
ditch | +0.032 |
unks | +0.032 |
igs | +0.030 |
icer | +0.030 |
alk | +0.030 |
Neg logit contributions | |
sure | -0.010 |
happy | -0.009 |
listened | -0.009 |
excited | -0.008 |
Happy | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ditch | +0.021 |
igs | +0.021 |
unks | +0.021 |
alk | +0.020 |
loft | +0.020 |
Neg logit contributions | |
disl | -0.010 |
sure | -0.009 |
caring | -0.009 |
free | -0.008 |
listening | -0.008 |
Token | red |
Token ID | 2266 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
ditch | +0.041 |
unks | +0.041 |
stack | +0.039 |
icer | +0.038 |
igs | +0.038 |
Neg logit contributions | |
sure | -0.047 |
happy | -0.047 |
nos | -0.044 |
caring | -0.044 |
Happy | -0.044 |
Token | yarn |
Token ID | 21181 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
unks | +0.101 |
ditch | +0.101 |
ifi | +0.100 |
stack | +0.099 |
loft | +0.098 |
Neg logit contributions | |
's | -0.088 |
happy | -0.083 |
when | -0.082 |
Happy | -0.081 |
gr | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
unks | +0.058 |
ditch | +0.057 |
icer | +0.055 |
igs | +0.055 |
ifi | +0.053 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.021 |
Happy | -0.019 |
excited | -0.019 |
caring | -0.019 |
Token | began |
Token ID | 2540 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ditch | +0.015 |
unks | +0.015 |
igs | +0.014 |
loft | +0.014 |
stack | +0.014 |
Neg logit contributions | |
sure | -0.009 |
disl | -0.009 |
free | -0.009 |
happy | -0.008 |
caring | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
igs | +0.038 |
unks | +0.038 |
ditch | +0.038 |
alk | +0.036 |
loft | +0.035 |
Neg logit contributions | |
sure | -0.019 |
disl | -0.019 |
handsome | -0.019 |
Happy | -0.019 |
Happy | -0.017 |
Token | roll |
Token ID | 4836 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ditch | +0.003 |
unks | +0.003 |
igs | +0.003 |
alk | +0.003 |
stack | +0.003 |
Neg logit contributions | |
sure | -0.003 |
disl | -0.002 |
Happy | -0.002 |
you | -0.002 |
caring | -0.002 |
Token | I |
Token ID | 40 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
sure | +0.014 |
disl | +0.014 |
happy | +0.013 |
Happy | +0.013 |
listening | +0.013 |
Neg logit contributions | |
ditch | -0.021 |
icer | -0.020 |
ifier | -0.020 |
stack | -0.020 |
unks | -0.020 |
Token | will |
Token ID | 481 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
ditch | +0.030 |
unks | +0.029 |
igs | +0.028 |
alk | +0.028 |
icer | +0.028 |
Neg logit contributions | |
disl | -0.017 |
sure | -0.017 |
Happy | -0.017 |
listening | -0.016 |
caring | -0.016 |
Token | lend |
Token ID | 22096 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ditch | +0.017 |
unks | +0.017 |
igs | +0.016 |
stack | +0.016 |
alk | +0.016 |
Neg logit contributions | |
sure | -0.007 |
disl | -0.006 |
happy | -0.006 |
Happy | -0.006 |
caring | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
unks | +0.048 |
ditch | +0.048 |
igs | +0.047 |
icer | +0.045 |
ifier | +0.045 |
Neg logit contributions | |
disl | -0.019 |
sure | -0.019 |
free | -0.017 |
pleased | -0.017 |
happy | -0.016 |
Token | my |
Token ID | 616 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.008 |
Happy | +0.008 |
free | +0.008 |
happy | +0.008 |
Neg logit contributions | |
ditch | -0.017 |
unks | -0.017 |
igs | -0.016 |
icer | -0.016 |
enclosure | -0.016 |
Token | red |
Token ID | 2266 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
unks | +0.031 |
ditch | +0.031 |
igs | +0.030 |
icer | +0.029 |
alk | +0.029 |
Neg logit contributions | |
sure | -0.032 |
disl | -0.030 |
happy | -0.030 |
Happy | -0.030 |
caring | -0.029 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
unks | +0.110 |
ditch | +0.108 |
igs | +0.107 |
loft | +0.107 |
stack | +0.104 |
Neg logit contributions | |
happy | -0.080 |
nos | -0.074 |
kind | -0.074 |
Happy | -0.073 |
disl | -0.072 |
Token | ." |
Token ID | 526 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
unks | +0.053 |
ditch | +0.053 |
igs | +0.051 |
icer | +0.050 |
alk | +0.050 |
Neg logit contributions | |
sure | -0.018 |
happy | -0.016 |
disl | -0.016 |
Happy | -0.015 |
caring | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
caring | +0.002 |
happy | +0.002 |
handsome | +0.002 |
Neg logit contributions | |
ditch | -0.002 |
unks | -0.002 |
igs | -0.002 |
alk | -0.002 |
stack | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
unks | +0.014 |
ditch | +0.014 |
igs | +0.014 |
icer | +0.013 |
stack | +0.013 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
Happy | -0.003 |
disl | -0.003 |
caring | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
unks | +0.021 |
ditch | +0.021 |
igs | +0.020 |
icer | +0.020 |
stack | +0.020 |
Neg logit contributions | |
sure | -0.012 |
happy | -0.011 |
disl | -0.011 |
caring | -0.011 |
Happy | -0.011 |
Token | be |
Token ID | 307 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
free | +0.010 |
Happy | +0.010 |
sure | +0.010 |
disl | +0.010 |
Happy | +0.010 |
Neg logit contributions | |
ditch | -0.015 |
igs | -0.015 |
unks | -0.015 |
alk | -0.014 |
stack | -0.014 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
rav | +0.009 |
disl | +0.009 |
Happy | +0.008 |
Sorry | +0.008 |
good | +0.008 |
Neg logit contributions | |
ditch | -0.015 |
igs | -0.014 |
dam | -0.014 |
unks | -0.014 |
trailer | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
disl | +0.012 |
free | +0.011 |
Happy | +0.011 |
rav | +0.011 |
beh | +0.011 |
Neg logit contributions | |
unks | -0.017 |
ditch | -0.017 |
igs | -0.016 |
alk | -0.016 |
loft | -0.016 |
Token | well |
Token ID | 880 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
minded | +0.014 |
heart | +0.014 |
Happy | +0.014 |
good | +0.014 |
don | +0.014 |
Neg logit contributions | |
stack | -0.024 |
ditch | -0.022 |
igs | -0.022 |
pocket | -0.022 |
ses | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
disl | +0.008 |
Of | +0.007 |
Happy | +0.007 |
rav | +0.007 |
Happy | +0.007 |
Neg logit contributions | |
igs | -0.012 |
unks | -0.011 |
ditch | -0.011 |
alk | -0.011 |
stack | -0.011 |
Token | beh |
Token ID | 20709 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
Happy | +0.048 |
happy | +0.042 |
amused | +0.041 |
worry | +0.040 |
hello | +0.040 |
Neg logit contributions | |
igs | -0.061 |
unks | -0.057 |
ool | -0.056 |
inger | -0.054 |
ales | -0.054 |
Token | aved |
Token ID | 9586 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
sure | +0.133 |
disl | +0.127 |
happy | +0.127 |
free | +0.126 |
Happy | +0.126 |
Neg logit contributions | |
unks | -0.077 |
ditch | -0.077 |
igs | -0.073 |
icer | -0.069 |
stack | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ditch | +0.004 |
stack | +0.004 |
alk | +0.004 |
unks | +0.004 |
loft | +0.004 |
Neg logit contributions | |
disl | -0.002 |
sure | -0.002 |
handsome | -0.002 |
caring | -0.002 |
nos | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
sure | +0.012 |
handsome | +0.011 |
nos | +0.011 |
disl | +0.011 |
caring | +0.011 |
Neg logit contributions | |
unks | -0.021 |
ditch | -0.021 |
icer | -0.021 |
stack | -0.021 |
alk | -0.020 |
Token | end |
Token ID | 886 |
Feature activation | -1.67e-04 |
Pos logit contributions | |
sure | +0.011 |
disl | +0.011 |
Happy | +0.010 |
free | +0.010 |
you | +0.010 |
Neg logit contributions | |
ditch | -0.013 |
icer | -0.012 |
loft | -0.012 |
unks | -0.011 |
igs | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
handsome | +0.000 |
disl | +0.000 |
sure | +0.000 |
nos | +0.000 |
beh | +0.000 |
Neg logit contributions | |
unks | -0.000 |
ool | -0.000 |
ditch | -0.000 |
igs | -0.000 |
loft | -0.000 |
Token | could |
Token ID | 714 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
unks | +0.030 |
ditch | +0.027 |
stack | +0.027 |
igs | +0.026 |
alk | +0.026 |
Neg logit contributions | |
disl | -0.032 |
caring | -0.029 |
Sorry | -0.029 |
comments | -0.028 |
handsome | -0.028 |
Token | be |
Token ID | 307 |
Feature activation | +2.71e-04 |
Pos logit contributions | |
ditch | +0.035 |
unks | +0.035 |
igs | +0.034 |
alk | +0.034 |
stack | +0.033 |
Neg logit contributions | |
Happy | -0.019 |
disl | -0.019 |
handsome | -0.019 |
sure | -0.018 |
free | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ditch | +0.001 |
igs | +0.001 |
unks | +0.000 |
dam | +0.000 |
alk | +0.000 |
Neg logit contributions | |
rav | -0.000 |
Happy | -0.000 |
Sorry | -0.000 |
Of | -0.000 |
you | -0.000 |
Token | never |
Token ID | 1239 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
Happy | +0.019 |
Happy | +0.018 |
rav | +0.017 |
good | +0.017 |
free | +0.017 |
Neg logit contributions | |
stack | -0.028 |
ditch | -0.027 |
alk | -0.027 |
igs | -0.027 |
unks | -0.026 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
Happy | +0.013 |
you | +0.012 |
Happy | +0.012 |
good | +0.011 |
free | +0.011 |
Neg logit contributions | |
ditch | -0.012 |
alk | -0.012 |
grasp | -0.012 |
dam | -0.012 |
grip | -0.011 |
Token | beh |
Token ID | 20709 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
Happy | +0.068 |
disl | +0.068 |
sure | +0.067 |
happy | +0.065 |
caring | +0.062 |
Neg logit contributions | |
ditch | -0.108 |
unks | -0.105 |
igs | -0.101 |
alk | -0.097 |
icer | -0.096 |
Token | aved |
Token ID | 9586 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
sure | +0.112 |
happy | +0.105 |
free | +0.105 |
disl | +0.105 |
Happy | +0.104 |
Neg logit contributions | |
unks | -0.094 |
ditch | -0.093 |
igs | -0.091 |
stack | -0.087 |
icer | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
disl | +0.002 |
Happy | +0.002 |
sure | +0.002 |
caring | +0.002 |
Of | +0.002 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
stack | -0.003 |
alk | -0.003 |
igs | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
sure | +0.004 |
handsome | +0.004 |
nos | +0.004 |
disl | +0.004 |
happy | +0.004 |
Neg logit contributions | |
unks | -0.007 |
ditch | -0.007 |
icer | -0.007 |
alk | -0.007 |
stack | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
sure | +0.025 |
disl | +0.024 |
happy | +0.023 |
caring | +0.023 |
free | +0.022 |
Neg logit contributions | |
unks | -0.058 |
ditch | -0.057 |
igs | -0.055 |
icer | -0.055 |
alk | -0.054 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
unks | +0.014 |
ditch | +0.014 |
igs | +0.014 |
icer | +0.013 |
alk | +0.013 |
Neg logit contributions | |
sure | -0.010 |
disl | -0.010 |
happy | -0.009 |
Happy | -0.009 |
caring | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
unks | +0.015 |
ditch | +0.015 |
igs | +0.014 |
alk | +0.014 |
icer | +0.014 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.004 |
disl | -0.004 |
Happy | -0.004 |
caring | -0.004 |
Token | naughty |
Token ID | 45128 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
sure | +0.002 |
Happy | +0.002 |
disl | +0.002 |
good | +0.002 |
you | +0.002 |
Neg logit contributions | |
unks | -0.006 |
igs | -0.006 |
ditch | -0.006 |
ses | -0.005 |
icer | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
disl | +0.024 |
Happy | +0.022 |
sure | +0.021 |
caring | +0.021 |
good | +0.021 |
Neg logit contributions | |
ditch | -0.024 |
unks | -0.024 |
loft | -0.023 |
igs | -0.022 |
ippy | -0.022 |
Token | always |
Token ID | 1464 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Happy | +0.015 |
Happy | +0.014 |
disl | +0.014 |
rav | +0.014 |
minded | +0.014 |
Neg logit contributions | |
igs | -0.022 |
stack | -0.022 |
ifi | -0.021 |
loft | -0.021 |
ditch | -0.021 |
Token | mis |
Token ID | 2984 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
Happy | +0.025 |
you | +0.023 |
minded | +0.023 |
Happy | +0.022 |
disl | +0.022 |
Neg logit contributions | |
ditch | -0.036 |
ses | -0.035 |
unks | -0.034 |
stack | -0.033 |
sed | -0.033 |
Token | beh |
Token ID | 20709 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
sure | +0.044 |
happy | +0.041 |
disl | +0.041 |
Happy | +0.040 |
caring | +0.038 |
Neg logit contributions | |
unks | -0.105 |
ditch | -0.105 |
igs | -0.102 |
icer | -0.099 |
alk | -0.098 |
Token | aving |
Token ID | 2703 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
free | +0.110 |
sure | +0.109 |
disl | +0.101 |
Happy | +0.101 |
happy | +0.100 |
Neg logit contributions | |
igs | -0.094 |
ditch | -0.093 |
unks | -0.092 |
stack | -0.089 |
loft | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
disl | +0.013 |
Happy | +0.013 |
sure | +0.013 |
Happy | +0.012 |
handsome | +0.012 |
Neg logit contributions | |
unks | -0.024 |
ditch | -0.024 |
igs | -0.024 |
alk | -0.023 |
loft | -0.023 |
Token | One |
Token ID | 1881 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
sure | +0.012 |
Happy | +0.011 |
happy | +0.011 |
disl | +0.011 |
free | +0.010 |
Neg logit contributions | |
ditch | -0.025 |
unks | -0.025 |
igs | -0.025 |
stack | -0.023 |
alk | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
disl | +0.004 |
sure | +0.004 |
Happy | +0.004 |
minded | +0.004 |
handsome | +0.004 |
Neg logit contributions | |
ditch | -0.006 |
ifi | -0.006 |
loft | -0.006 |
icer | -0.006 |
unks | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
igs | +0.006 |
unks | +0.006 |
ditch | +0.006 |
loft | +0.006 |
ifi | +0.006 |
Neg logit contributions | |
disl | -0.005 |
sure | -0.005 |
minded | -0.004 |
caring | -0.004 |
beh | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-04 |
Pos logit contributions | |
sure | +0.005 |
Happy | +0.005 |
Happy | +0.005 |
disl | +0.005 |
handsome | +0.005 |
Neg logit contributions | |
ditch | -0.009 |
unks | -0.009 |
ses | -0.008 |
alk | -0.008 |
stack | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +7.78e-04 |
Pos logit contributions | |
disl | +0.000 |
sure | +0.000 |
you | +0.000 |
good | +0.000 |
Happy | +0.000 |
Neg logit contributions | |
ditch | -0.000 |
loft | -0.000 |
unks | -0.000 |
alk | -0.000 |
funnel | -0.000 |
Token | bit |
Token ID | 1643 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
ditch | +0.002 |
ses | +0.001 |
loft | +0.001 |
stack | +0.001 |
alk | +0.001 |
Neg logit contributions | |
disl | -0.001 |
sure | -0.001 |
Happy | -0.001 |
free | -0.001 |
Happy | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
disl | +0.003 |
sure | +0.003 |
Happy | +0.003 |
Happy | +0.003 |
happy | +0.003 |
Neg logit contributions | |
ditch | -0.007 |
unks | -0.007 |
igs | -0.007 |
alk | -0.007 |
loft | -0.006 |
Token | mis |
Token ID | 2984 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
sure | +0.022 |
disl | +0.021 |
free | +0.021 |
Happy | +0.020 |
Happy | +0.020 |
Neg logit contributions | |
ditch | -0.038 |
unks | -0.037 |
igs | -0.036 |
alk | -0.035 |
icer | -0.035 |
Token | beh |
Token ID | 20709 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
Happy | +0.056 |
sure | +0.056 |
disl | +0.055 |
happy | +0.055 |
caring | +0.051 |
Neg logit contributions | |
ditch | -0.072 |
unks | -0.071 |
igs | -0.068 |
icer | -0.066 |
alk | -0.066 |
Token | aving |
Token ID | 2703 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
sure | +0.103 |
free | +0.099 |
disl | +0.096 |
happy | +0.096 |
Happy | +0.096 |
Neg logit contributions | |
unks | -0.097 |
ditch | -0.097 |
igs | -0.095 |
icer | -0.090 |
stack | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
disl | +0.005 |
sure | +0.005 |
handsome | +0.005 |
Happy | +0.005 |
caring | +0.005 |
Neg logit contributions | |
ditch | -0.011 |
unks | -0.011 |
alk | -0.011 |
igs | -0.011 |
stack | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
sure | +0.021 |
disl | +0.020 |
listening | +0.020 |
free | +0.020 |
handsome | +0.020 |
Neg logit contributions | |
unks | -0.035 |
ditch | -0.034 |
stack | -0.034 |
alk | -0.033 |
icer | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.011 |
igs | +0.010 |
icer | +0.010 |
loft | +0.010 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.003 |
Happy | -0.003 |
caring | -0.003 |
disl | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
unks | +0.013 |
ditch | +0.013 |
igs | +0.012 |
icer | +0.012 |
alk | +0.012 |
Neg logit contributions | |
sure | -0.009 |
disl | -0.009 |
happy | -0.009 |
Happy | -0.008 |
caring | -0.008 |
Token | It |
Token ID | 1026 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
sure | +0.011 |
happy | +0.010 |
Happy | +0.010 |
handsome | +0.010 |
nos | +0.009 |
Neg logit contributions | |
unks | -0.020 |
ditch | -0.018 |
igs | -0.018 |
icer | -0.018 |
alk | -0.018 |
Token | helps |
Token ID | 5419 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
yes | +0.018 |
free | +0.018 |
Happy | +0.018 |
handsome | +0.017 |
good | +0.017 |
Neg logit contributions | |
unks | -0.031 |
igs | -0.030 |
enclosure | -0.029 |
ses | -0.029 |
alk | -0.029 |
Token | us |
Token ID | 514 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
disl | +0.010 |
sure | +0.010 |
Happy | +0.010 |
handsome | +0.010 |
free | +0.009 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.013 |
igs | -0.013 |
alk | -0.012 |
icer | -0.012 |
Token | remember |
Token ID | 3505 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
Happy | +0.018 |
disl | +0.018 |
sure | +0.018 |
handsome | +0.017 |
caring | +0.017 |
Neg logit contributions | |
ditch | -0.030 |
unks | -0.030 |
igs | -0.029 |
alk | -0.029 |
stack | -0.028 |
Token | when |
Token ID | 618 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
unks | +0.004 |
igs | +0.003 |
ditch | +0.003 |
alk | +0.003 |
enclosure | +0.003 |
Neg logit contributions | |
sure | -0.001 |
free | -0.001 |
disl | -0.001 |
Happy | -0.001 |
Happy | -0.001 |
Token | birth |
Token ID | 4082 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
disl | +0.002 |
sure | +0.002 |
free | +0.002 |
good | +0.001 |
forg | +0.001 |
Neg logit contributions | |
unks | -0.005 |
igs | -0.005 |
ditch | -0.005 |
alk | -0.004 |
loft | -0.004 |
Token | days |
Token ID | 12545 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
sure | +0.082 |
disl | +0.080 |
caring | +0.079 |
happy | +0.076 |
nos | +0.074 |
Neg logit contributions | |
unks | -0.119 |
alk | -0.111 |
icer | -0.108 |
enclosure | -0.107 |
ditch | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
sure | +0.054 |
disl | +0.053 |
caring | +0.052 |
pleased | +0.051 |
observ | +0.049 |
Neg logit contributions | |
unks | -0.068 |
alk | -0.066 |
ditch | -0.065 |
igs | -0.064 |
enclosure | -0.063 |
Token | special |
Token ID | 2041 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Happy | +0.015 |
good | +0.015 |
Happy | +0.014 |
free | +0.014 |
sure | +0.014 |
Neg logit contributions | |
ditch | -0.027 |
igs | -0.026 |
unks | -0.026 |
stack | -0.026 |
alk | -0.025 |
Token | days |
Token ID | 1528 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
sure | +0.015 |
free | +0.015 |
disl | +0.014 |
handsome | +0.014 |
forg | +0.014 |
Neg logit contributions | |
igs | -0.025 |
unks | -0.025 |
alk | -0.024 |
ditch | -0.024 |
enclosure | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
disl | +0.014 |
sure | +0.014 |
caring | +0.013 |
forg | +0.013 |
happy | +0.013 |
Neg logit contributions | |
unks | -0.031 |
ditch | -0.030 |
igs | -0.029 |
alk | -0.029 |
loft | -0.028 |
Token | became |
Token ID | 2627 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
nos | +0.025 |
accidents | +0.024 |
disl | +0.024 |
handsome | +0.024 |
you | +0.024 |
Neg logit contributions | |
stack | -0.034 |
alk | -0.034 |
ditch | -0.033 |
enclosure | -0.033 |
ifi | -0.032 |
Token | friendly |
Token ID | 8030 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
disl | +0.007 |
you | +0.006 |
free | +0.006 |
great | +0.005 |
don | +0.005 |
Neg logit contributions | |
ditch | -0.013 |
igs | -0.013 |
unks | -0.012 |
loft | -0.012 |
dam | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
unks | +0.013 |
ditch | +0.012 |
enclosure | +0.012 |
necks | +0.011 |
igs | +0.011 |
Neg logit contributions | |
disl | -0.013 |
sure | -0.012 |
free | -0.012 |
Happy | -0.012 |
beh | -0.011 |
Token | well |
Token ID | 880 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
heart | +0.010 |
you | +0.010 |
don | +0.010 |
discourage | +0.010 |
minded | +0.010 |
Neg logit contributions | |
stack | -0.016 |
ses | -0.016 |
ditch | -0.015 |
sed | -0.015 |
pouch | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
disl | +0.013 |
Happy | +0.012 |
you | +0.012 |
don | +0.012 |
Happy | +0.011 |
Neg logit contributions | |
unks | -0.020 |
igs | -0.019 |
ditch | -0.019 |
alk | -0.018 |
enclosure | -0.018 |
Token | beh |
Token ID | 20709 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
Happy | +0.045 |
sure | +0.042 |
nos | +0.040 |
bluff | +0.039 |
happy | +0.039 |
Neg logit contributions | |
igs | -0.047 |
unks | -0.047 |
enclosure | -0.045 |
ifi | -0.045 |
ippy | -0.044 |
Token | aved |
Token ID | 9586 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
sure | +0.123 |
disl | +0.118 |
happy | +0.118 |
free | +0.118 |
Happy | +0.117 |
Neg logit contributions | |
unks | -0.075 |
ditch | -0.075 |
igs | -0.072 |
icer | -0.068 |
stack | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-04 |
Pos logit contributions | |
ditch | +0.010 |
stack | +0.010 |
unks | +0.010 |
loft | +0.009 |
alk | +0.009 |
Neg logit contributions | |
disl | -0.006 |
sure | -0.005 |
handsome | -0.005 |
Happy | -0.005 |
caring | -0.005 |
Token | just |
Token ID | 655 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Happy | +0.000 |
disl | +0.000 |
free | +0.000 |
Happy | +0.000 |
minded | +0.000 |
Neg logit contributions | |
ditch | -0.000 |
unks | -0.000 |
stack | -0.000 |
igs | -0.000 |
loft | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
Happy | +0.024 |
you | +0.022 |
rav | +0.021 |
good | +0.021 |
handsome | +0.020 |
Neg logit contributions | |
ses | -0.022 |
stack | -0.020 |
ditch | -0.020 |
enclosure | -0.019 |
sed | -0.019 |
Token | Buddy |
Token ID | 36896 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
Happy | +0.001 |
disl | +0.001 |
free | +0.001 |
sure | +0.001 |
you | +0.001 |
Neg logit contributions | |
ditch | -0.001 |
unks | -0.001 |
igs | -0.001 |
stack | -0.001 |
loft | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
ditch | +0.028 |
unks | +0.027 |
stack | +0.027 |
igs | +0.027 |
loft | +0.026 |
Neg logit contributions | |
disl | -0.012 |
sure | -0.011 |
free | -0.011 |
Happy | -0.011 |
Happy | -0.011 |
Token | just |
Token ID | 655 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
sure | +0.006 |
disl | +0.006 |
Happy | +0.006 |
happy | +0.006 |
caring | +0.005 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.013 |
igs | -0.012 |
stack | -0.012 |
alk | -0.012 |
Token | kept |
Token ID | 4030 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
sure | +0.017 |
disl | +0.016 |
happy | +0.015 |
Happy | +0.015 |
caring | +0.015 |
Neg logit contributions | |
unks | -0.036 |
ditch | -0.035 |
igs | -0.034 |
stack | -0.034 |
alk | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
disl | +0.002 |
Happy | +0.002 |
Happy | +0.002 |
free | +0.002 |
sure | +0.002 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
igs | -0.003 |
alk | -0.003 |
stack | -0.003 |
Token | qu |
Token ID | 627 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Happy | +0.016 |
Happy | +0.015 |
rav | +0.015 |
disl | +0.015 |
you | +0.015 |
Neg logit contributions | |
ditch | -0.023 |
unks | -0.022 |
igs | -0.021 |
alk | -0.020 |
alks | -0.020 |
Token | arre |
Token ID | 9624 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
sure | +0.041 |
disl | +0.038 |
happy | +0.037 |
Happy | +0.036 |
caring | +0.036 |
Neg logit contributions | |
ditch | -0.069 |
unks | -0.069 |
igs | -0.066 |
stack | -0.065 |
icer | -0.064 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
disl | +0.097 |
Happy | +0.096 |
Of | +0.096 |
Thank | +0.095 |
Sorry | +0.091 |
Neg logit contributions | |
igs | -0.094 |
ditch | -0.093 |
alk | -0.087 |
unks | -0.087 |
icer | -0.081 |
Token | ! |
Token ID | 0 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
Happy | +0.014 |
disl | +0.014 |
handsome | +0.014 |
sure | +0.014 |
Happy | +0.014 |
Neg logit contributions | |
ditch | -0.026 |
unks | -0.025 |
alk | -0.025 |
stack | -0.024 |
igs | -0.024 |
Token | |
Token ID | 220 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.008 |
happy | +0.008 |
caring | +0.008 |
Happy | +0.008 |
Neg logit contributions | |
unks | -0.021 |
ditch | -0.021 |
igs | -0.020 |
icer | -0.020 |
stack | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
disl | +0.020 |
sure | +0.020 |
caring | +0.020 |
handsome | +0.019 |
happy | +0.019 |
Neg logit contributions | |
unks | -0.050 |
ditch | -0.049 |
igs | -0.047 |
alk | -0.047 |
icer | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
sure | +0.001 |
disl | +0.001 |
happy | +0.001 |
Happy | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
igs | -0.003 |
icer | -0.003 |
alk | -0.003 |
Token | listen |
Token ID | 6004 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Happy | +0.001 |
Happy | +0.001 |
sure | +0.001 |
you | +0.001 |
caring | +0.001 |
Neg logit contributions | |
ditch | -0.001 |
alk | -0.001 |
enclosure | -0.001 |
dam | -0.001 |
grip | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
disl | +0.015 |
Sorry | +0.014 |
Happy | +0.014 |
Happy | +0.013 |
rav | +0.013 |
Neg logit contributions | |
ditch | -0.018 |
unks | -0.018 |
igs | -0.018 |
alk | -0.018 |
enclosure | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
unks | +0.003 |
ditch | +0.003 |
igs | +0.003 |
icer | +0.003 |
alk | +0.003 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
Happy | -0.003 |
disl | -0.003 |
caring | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
unks | +0.028 |
ditch | +0.028 |
igs | +0.027 |
icer | +0.026 |
alk | +0.026 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.010 |
disl | -0.009 |
Happy | -0.009 |
caring | -0.009 |
Token | mis |
Token ID | 2984 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Happy | +0.012 |
you | +0.012 |
Happy | +0.012 |
sure | +0.012 |
free | +0.012 |
Neg logit contributions | |
unks | -0.023 |
ditch | -0.023 |
igs | -0.023 |
ses | -0.023 |
stack | -0.022 |
Token | beh |
Token ID | 20709 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
sure | +0.028 |
happy | +0.024 |
disl | +0.023 |
caring | +0.022 |
free | +0.022 |
Neg logit contributions | |
unks | -0.103 |
ditch | -0.102 |
igs | -0.099 |
icer | -0.098 |
stack | -0.098 |
Token | aved |
Token ID | 9586 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
sure | +0.098 |
free | +0.096 |
disl | +0.093 |
Happy | +0.091 |
happy | +0.089 |
Neg logit contributions | |
unks | -0.092 |
igs | -0.092 |
ditch | -0.092 |
icer | -0.088 |
stack | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
ditch | +0.022 |
unks | +0.022 |
igs | +0.021 |
stack | +0.021 |
alk | +0.020 |
Neg logit contributions | |
disl | -0.012 |
sure | -0.012 |
Happy | -0.012 |
Happy | -0.012 |
caring | -0.012 |
Token | caused |
Token ID | 4073 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
Happy | +0.008 |
Happy | +0.007 |
sure | +0.007 |
you | +0.007 |
handsome | +0.007 |
Neg logit contributions | |
ditch | -0.012 |
igs | -0.011 |
unks | -0.011 |
stack | -0.011 |
ses | -0.011 |
Token | trouble |
Token ID | 5876 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ditch | +0.007 |
unks | +0.007 |
igs | +0.007 |
icer | +0.007 |
alk | +0.006 |
Neg logit contributions | |
disl | -0.004 |
Happy | -0.004 |
free | -0.004 |
you | -0.004 |
Happy | -0.004 |
Token | wherever |
Token ID | 14530 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
Happy | +0.022 |
Of | +0.021 |
Sorry | +0.020 |
rav | +0.020 |
Happy | +0.020 |
Neg logit contributions | |
ditch | -0.029 |
unks | -0.027 |
igs | -0.026 |
enclosure | -0.025 |
alk | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
sure | +0.004 |
happy | +0.004 |
disl | +0.004 |
Happy | +0.004 |
caring | +0.004 |
Neg logit contributions | |
unks | -0.011 |
ditch | -0.011 |
igs | -0.011 |
icer | -0.011 |
stack | -0.010 |
Token | mess |
Token ID | 2085 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
nos | +0.002 |
disl | +0.002 |
caring | +0.002 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
igs | -0.003 |
alk | -0.002 |
stack | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
disl | +0.029 |
sure | +0.026 |
handsome | +0.025 |
caring | +0.025 |
Happy | +0.025 |
Neg logit contributions | |
unks | -0.042 |
ditch | -0.041 |
igs | -0.040 |
icer | -0.039 |
loft | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
free | +0.002 |
caring | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
unks | -0.006 |
ditch | -0.006 |
igs | -0.005 |
icer | -0.005 |
loft | -0.005 |
Token | qu |
Token ID | 627 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
sure | +0.010 |
disl | +0.010 |
happy | +0.010 |
Happy | +0.010 |
caring | +0.010 |
Neg logit contributions | |
ditch | -0.010 |
unks | -0.010 |
igs | -0.010 |
icer | -0.010 |
stack | -0.009 |
Token | arre |
Token ID | 9624 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
sure | +0.045 |
happy | +0.042 |
disl | +0.042 |
free | +0.041 |
Happy | +0.041 |
Neg logit contributions | |
ditch | -0.042 |
unks | -0.042 |
igs | -0.040 |
stack | -0.039 |
loft | -0.039 |
Token | ling |
Token ID | 1359 |
Feature activation | -7.72e-04 |
Pos logit contributions | |
disl | +0.089 |
Happy | +0.084 |
handsome | +0.080 |
forg | +0.080 |
nos | +0.080 |
Neg logit contributions | |
ditch | -0.103 |
igs | -0.100 |
unks | -0.096 |
icer | -0.096 |
alk | -0.094 |
Token | twins |
Token ID | 20345 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
sure | +0.001 |
disl | +0.001 |
Happy | +0.001 |
handsome | +0.001 |
caring | +0.001 |
Neg logit contributions | |
ditch | -0.001 |
unks | -0.001 |
alk | -0.001 |
igs | -0.001 |
icer | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
disl | +0.019 |
caring | +0.017 |
sure | +0.017 |
handsome | +0.016 |
Happy | +0.016 |
Neg logit contributions | |
ditch | -0.041 |
unks | -0.040 |
enclosure | -0.038 |
loft | -0.038 |
igs | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
unks | +0.012 |
ditch | +0.012 |
igs | +0.012 |
icer | +0.012 |
alk | +0.012 |
Neg logit contributions | |
sure | -0.007 |
disl | -0.006 |
happy | -0.006 |
caring | -0.006 |
Happy | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | -2.81e-03 |
Pos logit contributions | |
ditch | +0.035 |
unks | +0.034 |
igs | +0.033 |
stack | +0.033 |
alk | +0.033 |
Neg logit contributions | |
sure | -0.016 |
happy | -0.015 |
disl | -0.014 |
caring | -0.014 |
forg | -0.014 |
Token | |
Token ID | 220 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.011 |
igs | +0.011 |
ses | +0.011 |
enclosure | +0.011 |
Neg logit contributions | |
sure | -0.006 |
Happy | -0.005 |
happy | -0.005 |
you | -0.005 |
free | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.96e-04 |
Pos logit contributions | |
sure | +0.019 |
disl | +0.018 |
caring | +0.017 |
Happy | +0.017 |
listening | +0.017 |
Neg logit contributions | |
unks | -0.045 |
ditch | -0.043 |
alk | -0.043 |
igs | -0.043 |
icer | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +2.89e-03 |
Pos logit contributions | |
unks | +0.001 |
ditch | +0.001 |
igs | +0.001 |
icer | +0.001 |
stack | +0.001 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.000 |
disl | -0.000 |
Happy | -0.000 |
caring | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
unks | +0.006 |
ditch | +0.006 |
igs | +0.006 |
icer | +0.005 |
stack | +0.005 |
Neg logit contributions | |
sure | -0.004 |
disl | -0.004 |
happy | -0.004 |
Happy | -0.003 |
free | -0.003 |
Token | town |
Token ID | 3240 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
sure | +0.029 |
disl | +0.027 |
Happy | +0.026 |
free | +0.026 |
happy | +0.025 |
Neg logit contributions | |
ditch | -0.048 |
unks | -0.047 |
igs | -0.045 |
stack | -0.045 |
loft | -0.044 |
Token | spe |
Token ID | 4125 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
disl | +0.028 |
sure | +0.026 |
free | +0.026 |
Happy | +0.025 |
caring | +0.024 |
Neg logit contributions | |
ditch | -0.055 |
unks | -0.053 |
stack | -0.053 |
enclosure | -0.052 |
loft | -0.051 |
Token | ople |
Token ID | 643 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
sure | +0.109 |
caring | +0.101 |
disl | +0.101 |
happy | +0.099 |
handsome | +0.098 |
Neg logit contributions | |
unks | -0.084 |
ditch | -0.081 |
icer | -0.080 |
enclosure | -0.076 |
alk | -0.076 |
Token | had |
Token ID | 550 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
disl | +0.020 |
caring | +0.019 |
handsome | +0.018 |
Happy | +0.018 |
free | +0.018 |
Neg logit contributions | |
unks | -0.030 |
ditch | -0.030 |
stack | -0.029 |
enclosure | -0.029 |
alk | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.028 |
igs | +0.027 |
alk | +0.026 |
loft | +0.026 |
Neg logit contributions | |
free | -0.017 |
disl | -0.017 |
Happy | -0.016 |
sure | -0.016 |
you | -0.016 |
Token | find |
Token ID | 1064 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
free | +0.007 |
sure | +0.007 |
Happy | +0.007 |
handsome | +0.007 |
disl | +0.007 |
Neg logit contributions | |
ditch | -0.011 |
alk | -0.010 |
stack | -0.010 |
unks | -0.010 |
igs | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -3.50e-04 |
Pos logit contributions | |
disl | +0.011 |
sure | +0.010 |
free | +0.010 |
Happy | +0.010 |
happy | +0.010 |
Neg logit contributions | |
ditch | -0.021 |
unks | -0.021 |
igs | -0.020 |
loft | -0.019 |
stack | -0.019 |
Token | always |
Token ID | 1464 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
unks | +0.005 |
ditch | +0.005 |
igs | +0.004 |
stack | +0.004 |
alk | +0.004 |
Neg logit contributions | |
Happy | -0.002 |
disl | -0.002 |
free | -0.002 |
Happy | -0.002 |
sure | -0.002 |
Token | acted |
Token ID | 13134 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
free | +0.020 |
Happy | +0.019 |
Happy | +0.018 |
disl | +0.018 |
you | +0.018 |
Neg logit contributions | |
unks | -0.026 |
ses | -0.026 |
ditch | -0.026 |
igs | -0.025 |
stack | -0.025 |
Token | silly |
Token ID | 14397 |
Feature activation | -2.06e-05 |
Pos logit contributions | |
disl | +0.014 |
Happy | +0.013 |
good | +0.013 |
Sorry | +0.012 |
listening | +0.012 |
Neg logit contributions | |
ditch | -0.021 |
igs | -0.020 |
unks | -0.020 |
alk | -0.019 |
trailer | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Happy | +0.000 |
sure | +0.000 |
pleased | +0.000 |
Good | +0.000 |
handsome | +0.000 |
Neg logit contributions | |
unks | -0.000 |
ditch | -0.000 |
igs | -0.000 |
alk | -0.000 |
necks | -0.000 |
Token | mis |
Token ID | 2984 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
Happy | +0.018 |
Happy | +0.017 |
good | +0.016 |
you | +0.016 |
rav | +0.016 |
Neg logit contributions | |
igs | -0.026 |
ses | -0.026 |
ditch | -0.026 |
stack | -0.025 |
sticks | -0.024 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Happy | +0.070 |
sure | +0.069 |
disl | +0.068 |
happy | +0.068 |
caring | +0.063 |
Neg logit contributions | |
ditch | -0.107 |
unks | -0.107 |
igs | -0.102 |
alk | -0.098 |
icer | -0.098 |
Token | vous |
Token ID | 31222 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
handsome | +0.096 |
accidents | +0.096 |
Happy | +0.094 |
caring | +0.089 |
forgiving | +0.089 |
Neg logit contributions | |
ak | -0.074 |
ool | -0.073 |
aver | -0.072 |
alk | -0.070 |
unks | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Happy | +0.026 |
you | +0.024 |
disl | +0.024 |
sure | +0.024 |
listened | +0.024 |
Neg logit contributions | |
ditch | -0.043 |
igs | -0.040 |
unks | -0.039 |
enclosure | -0.039 |
alks | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
sure | +0.018 |
happy | +0.016 |
disl | +0.016 |
Happy | +0.016 |
caring | +0.016 |
Neg logit contributions | |
unks | -0.039 |
ditch | -0.038 |
igs | -0.037 |
icer | -0.036 |
stack | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ditch | +0.024 |
unks | +0.024 |
igs | +0.024 |
ses | +0.024 |
stack | +0.023 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.004 |
Happy | -0.003 |
excited | -0.003 |
caring | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
unks | +0.020 |
ditch | +0.019 |
igs | +0.019 |
ses | +0.018 |
stack | +0.018 |
Neg logit contributions | |
sure | -0.024 |
happy | -0.023 |
caring | -0.022 |
disl | -0.022 |
free | -0.022 |
Token | told |
Token ID | 1297 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
free | +0.025 |
Happy | +0.025 |
disl | +0.024 |
rav | +0.024 |
Happy | +0.023 |
Neg logit contributions | |
ditch | -0.034 |
igs | -0.031 |
stack | -0.031 |
unks | -0.030 |
ses | -0.030 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
sure | +0.006 |
disl | +0.006 |
free | +0.005 |
Happy | +0.005 |
happy | +0.005 |
Neg logit contributions | |
ditch | -0.007 |
igs | -0.007 |
unks | -0.007 |
ifier | -0.007 |
stack | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
Happy | +0.009 |
disl | +0.008 |
Happy | +0.008 |
good | +0.008 |
talented | +0.008 |
Neg logit contributions | |
ditch | -0.009 |
igs | -0.009 |
alk | -0.009 |
stack | -0.009 |
enclosure | -0.009 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ditch | +0.002 |
stack | +0.002 |
igs | +0.002 |
unks | +0.002 |
alk | +0.002 |
Neg logit contributions | |
Happy | -0.001 |
sure | -0.001 |
Happy | -0.001 |
free | -0.001 |
disl | -0.001 |
Token | mis |
Token ID | 2984 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
Happy | +0.026 |
sure | +0.024 |
Happy | +0.024 |
handsome | +0.024 |
good | +0.023 |
Neg logit contributions | |
unks | -0.038 |
ditch | -0.037 |
igs | -0.036 |
alk | -0.035 |
stack | -0.034 |
Token | beh |
Token ID | 20709 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
sure | +0.032 |
happy | +0.030 |
Happy | +0.030 |
disl | +0.030 |
caring | +0.027 |
Neg logit contributions | |
ditch | -0.084 |
unks | -0.083 |
igs | -0.080 |
icer | -0.078 |
alk | -0.078 |
Token | aving |
Token ID | 2703 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
free | +0.085 |
sure | +0.083 |
disl | +0.081 |
forg | +0.079 |
Happy | +0.079 |
Neg logit contributions | |
igs | -0.101 |
ditch | -0.099 |
unks | -0.098 |
loft | -0.096 |
stack | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
Happy | +0.009 |
disl | +0.008 |
handsome | +0.008 |
talented | +0.008 |
sure | +0.008 |
Neg logit contributions | |
ditch | -0.015 |
alk | -0.014 |
unks | -0.014 |
igs | -0.013 |
stack | -0.013 |
Token | But |
Token ID | 887 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
sure | +0.011 |
disl | +0.010 |
free | +0.010 |
happy | +0.010 |
Happy | +0.010 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.013 |
stack | -0.012 |
loft | -0.012 |
igs | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
ditch | +0.014 |
unks | +0.013 |
igs | +0.013 |
stack | +0.013 |
loft | +0.013 |
Neg logit contributions | |
disl | -0.010 |
sure | -0.009 |
free | -0.009 |
Happy | -0.009 |
Happy | -0.009 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
unks | +0.008 |
ditch | +0.008 |
igs | +0.008 |
icer | +0.008 |
stack | +0.008 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
disl | -0.003 |
Happy | -0.003 |
caring | -0.002 |
Token | We |
Token ID | 775 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.001 |
disl | +0.001 |
Happy | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.004 |
icer | -0.004 |
alk | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
unks | +0.025 |
ditch | +0.025 |
igs | +0.024 |
icer | +0.024 |
stack | +0.024 |
Neg logit contributions | |
sure | -0.012 |
happy | -0.011 |
disl | -0.011 |
Happy | -0.010 |
caring | -0.010 |
Token | different |
Token ID | 1180 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
unks | +0.026 |
ditch | +0.026 |
igs | +0.025 |
icer | +0.025 |
stack | +0.025 |
Neg logit contributions | |
sure | -0.009 |
happy | -0.008 |
disl | -0.008 |
Happy | -0.008 |
caring | -0.008 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
sure | +0.005 |
happy | +0.005 |
disl | +0.005 |
free | +0.005 |
caring | +0.005 |
Neg logit contributions | |
unks | -0.007 |
ditch | -0.006 |
igs | -0.006 |
alk | -0.006 |
icer | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -7.86e-03 |
Pos logit contributions | |
unks | +0.024 |
ditch | +0.024 |
igs | +0.023 |
icer | +0.022 |
alk | +0.022 |
Neg logit contributions | |
sure | -0.014 |
disl | -0.012 |
happy | -0.012 |
Happy | -0.012 |
free | -0.012 |
Token | disl |
Token ID | 19621 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
sure | +0.009 |
good | +0.009 |
Happy | +0.009 |
you | +0.009 |
free | +0.009 |
Neg logit contributions | |
igs | -0.015 |
ses | -0.015 |
alk | -0.015 |
ditch | -0.015 |
unks | -0.015 |
Token | ikes |
Token ID | 7938 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
happy | +0.084 |
sure | +0.084 |
caring | +0.080 |
free | +0.080 |
pleased | +0.080 |
Neg logit contributions | |
unks | -0.104 |
ippy | -0.096 |
icer | -0.093 |
igs | -0.092 |
ates | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
disl | +0.022 |
sure | +0.020 |
caring | +0.019 |
observ | +0.018 |
beh | +0.018 |
Neg logit contributions | |
ditch | -0.035 |
unks | -0.035 |
igs | -0.033 |
trailer | -0.033 |
alk | -0.033 |
Token | We |
Token ID | 775 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.001 |
disl | +0.001 |
Happy | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.003 |
icer | -0.003 |
alk | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.018 |
alk | +0.018 |
Neg logit contributions | |
sure | -0.008 |
disl | -0.008 |
happy | -0.008 |
Happy | -0.008 |
caring | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
ditch | +0.009 |
unks | +0.009 |
icer | +0.009 |
loft | +0.009 |
igs | +0.009 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
listen | -0.003 |
don | -0.003 |
caring | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
Happy | +0.001 |
disl | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.006 |
ditch | -0.006 |
igs | -0.006 |
alk | -0.006 |
icer | -0.006 |
Token | ambulance |
Token ID | 22536 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
sure | +0.007 |
happy | +0.006 |
disl | +0.006 |
Happy | +0.006 |
caring | +0.006 |
Neg logit contributions | |
unks | -0.006 |
ditch | -0.006 |
igs | -0.006 |
icer | -0.006 |
stack | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
disl | +0.042 |
sure | +0.040 |
caring | +0.039 |
free | +0.038 |
Happy | +0.038 |
Neg logit contributions | |
stack | -0.060 |
ditch | -0.060 |
unks | -0.059 |
enclosure | -0.058 |
loft | -0.056 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
unks | +0.006 |
ditch | +0.006 |
icer | +0.006 |
igs | +0.006 |
enclosure | +0.006 |
Neg logit contributions | |
disl | -0.005 |
free | -0.005 |
caring | -0.005 |
Happy | -0.004 |
sure | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
disl | +0.017 |
free | +0.016 |
sure | +0.016 |
caring | +0.016 |
Happy | +0.015 |
Neg logit contributions | |
ditch | -0.032 |
unks | -0.032 |
stack | -0.030 |
icer | -0.030 |
enclosure | -0.029 |
Token | paramed |
Token ID | 34581 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
sure | +0.013 |
disl | +0.012 |
Happy | +0.012 |
you | +0.012 |
free | +0.012 |
Neg logit contributions | |
ditch | -0.020 |
unks | -0.019 |
loft | -0.019 |
icer | -0.018 |
stack | -0.018 |
Token | ic |
Token ID | 291 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Happy | +0.103 |
sure | +0.103 |
happy | +0.100 |
disl | +0.100 |
don | +0.097 |
Neg logit contributions | |
icer | -0.082 |
unks | -0.080 |
ippy | -0.079 |
ditch | -0.076 |
stack | -0.069 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
disl | +0.036 |
handsome | +0.033 |
Happy | +0.033 |
caring | +0.033 |
sure | +0.032 |
Neg logit contributions | |
ditch | -0.046 |
unks | -0.045 |
igs | -0.044 |
stack | -0.043 |
ool | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
sure | +0.015 |
disl | +0.015 |
caring | +0.014 |
Happy | +0.014 |
rav | +0.014 |
Neg logit contributions | |
ditch | -0.027 |
unks | -0.025 |
igs | -0.024 |
icer | -0.024 |
trailer | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +8.07e-03 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
happy | +0.002 |
Happy | +0.002 |
free | +0.002 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
igs | -0.003 |
icer | -0.003 |
stack | -0.003 |
Token | coat |
Token ID | 13209 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
unks | +0.016 |
ditch | +0.015 |
igs | +0.015 |
alk | +0.015 |
icer | +0.015 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.011 |
disl | -0.010 |
caring | -0.010 |
nos | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | -1.28e-02 |
Token | play |
Token ID | 711 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
sure | +0.014 |
happy | +0.013 |
disl | +0.012 |
Happy | +0.012 |
caring | +0.012 |
Neg logit contributions | |
unks | -0.029 |
ditch | -0.029 |
igs | -0.028 |
icer | -0.027 |
alk | -0.027 |
Token | make |
Token ID | 787 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
disl | +0.009 |
sure | +0.009 |
free | +0.009 |
beh | +0.009 |
listening | +0.008 |
Neg logit contributions | |
ditch | -0.018 |
unks | -0.017 |
igs | -0.017 |
icer | -0.017 |
ifier | -0.016 |
Token | believe |
Token ID | 1975 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
free | +0.005 |
listened | +0.005 |
rav | +0.004 |
minded | +0.004 |
stru | +0.004 |
Neg logit contributions | |
igs | -0.006 |
ditch | -0.006 |
unks | -0.006 |
ifier | -0.005 |
trailer | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
disl | +0.037 |
forg | +0.035 |
listened | +0.033 |
good | +0.033 |
beh | +0.032 |
Neg logit contributions | |
igs | -0.046 |
unks | -0.045 |
ions | -0.044 |
ifier | -0.043 |
ates | -0.042 |
Token | Pret |
Token ID | 37123 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
sure | +0.014 |
disl | +0.013 |
happy | +0.013 |
free | +0.012 |
caring | +0.012 |
Neg logit contributions | |
ditch | -0.029 |
unks | -0.029 |
stack | -0.028 |
loft | -0.027 |
ifier | -0.027 |
Token | end |
Token ID | 437 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
sure | +0.085 |
happy | +0.084 |
Happy | +0.081 |
nos | +0.080 |
handsome | +0.079 |
Neg logit contributions | |
unks | -0.100 |
igs | -0.094 |
ditch | -0.093 |
alk | -0.090 |
icer | -0.088 |
Token | this |
Token ID | 428 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
sure | +0.030 |
disl | +0.030 |
caring | +0.029 |
happy | +0.029 |
nos | +0.029 |
Neg logit contributions | |
unks | -0.040 |
ditch | -0.039 |
alk | -0.039 |
igs | -0.038 |
icer | -0.037 |
Token | whip |
Token ID | 22972 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
disl | +0.024 |
sure | +0.023 |
free | +0.023 |
Happy | +0.023 |
minded | +0.023 |
Neg logit contributions | |
ditch | -0.027 |
igs | -0.027 |
unks | -0.027 |
trailer | -0.026 |
loft | -0.025 |
Token | is |
Token ID | 318 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
Happy | +0.005 |
caring | +0.005 |
handsome | +0.005 |
Neg logit contributions | |
unks | -0.008 |
igs | -0.007 |
ditch | -0.007 |
stack | -0.007 |
alk | -0.007 |
Token | like |
Token ID | 588 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.029 |
igs | +0.028 |
alk | +0.027 |
icer | +0.027 |
Neg logit contributions | |
sure | -0.012 |
disl | -0.011 |
Happy | -0.011 |
free | -0.011 |
happy | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ditch | +0.022 |
unks | +0.022 |
stack | +0.022 |
igs | +0.021 |
icer | +0.021 |
Neg logit contributions | |
disl | -0.012 |
sure | -0.012 |
Happy | -0.011 |
happy | -0.011 |
caring | -0.011 |
Token | being |
Token ID | 852 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
unks | +0.027 |
ditch | +0.027 |
igs | +0.027 |
icer | +0.025 |
alk | +0.025 |
Neg logit contributions | |
disl | -0.015 |
free | -0.014 |
sure | -0.014 |
nos | -0.013 |
Happy | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
disl | +0.019 |
rav | +0.017 |
good | +0.017 |
free | +0.016 |
discourage | +0.016 |
Neg logit contributions | |
ditch | -0.028 |
unks | -0.027 |
igs | -0.025 |
ates | -0.025 |
ifier | -0.025 |
Token | well |
Token ID | 880 |
Feature activation | +9.03e-04 |
Pos logit contributions | |
disl | +0.003 |
good | +0.003 |
Happy | +0.003 |
sure | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
ditch | -0.008 |
igs | -0.008 |
unks | -0.008 |
ifi | -0.008 |
ippy | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
unks | +0.002 |
ditch | +0.002 |
igs | +0.002 |
alk | +0.002 |
stack | +0.002 |
Neg logit contributions | |
disl | -0.001 |
sure | -0.001 |
Happy | -0.001 |
Happy | -0.001 |
free | -0.001 |
Token | beh |
Token ID | 20709 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
Happy | +0.030 |
happy | +0.027 |
sure | +0.027 |
disl | +0.026 |
amused | +0.025 |
Neg logit contributions | |
unks | -0.040 |
igs | -0.038 |
ifi | -0.038 |
ippy | -0.037 |
ditch | -0.037 |
Token | aved |
Token ID | 9586 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
sure | +0.114 |
happy | +0.108 |
disl | +0.108 |
Happy | +0.107 |
free | +0.106 |
Neg logit contributions | |
unks | -0.070 |
ditch | -0.069 |
igs | -0.066 |
icer | -0.062 |
stack | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ditch | +0.015 |
unks | +0.015 |
stack | +0.014 |
alk | +0.014 |
igs | +0.014 |
Neg logit contributions | |
disl | -0.009 |
sure | -0.009 |
caring | -0.008 |
handsome | -0.008 |
happy | -0.008 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
disl | +0.016 |
Happy | +0.016 |
free | +0.016 |
sure | +0.015 |
Happy | +0.015 |
Neg logit contributions | |
ditch | -0.027 |
unks | -0.027 |
stack | -0.026 |
igs | -0.026 |
footing | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
disl | +0.013 |
free | +0.012 |
Happy | +0.011 |
Happy | +0.011 |
caring | +0.011 |
Neg logit contributions | |
unks | -0.024 |
ditch | -0.023 |
stack | -0.023 |
enclosure | -0.023 |
igs | -0.022 |
Token | delighted |
Token ID | 20707 |
Feature activation | -3.75e-04 |
Pos logit contributions | |
ditch | +0.015 |
unks | +0.014 |
stack | +0.014 |
igs | +0.014 |
loft | +0.013 |
Neg logit contributions | |
disl | -0.008 |
minded | -0.007 |
rav | -0.007 |
Happy | -0.007 |
free | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
ditch | +0.002 |
unks | +0.002 |
igs | +0.002 |
alk | +0.002 |
stack | +0.002 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
Happy | -0.001 |
happy | -0.001 |
caring | -0.001 |
Token | be |
Token ID | 307 |
Feature activation | -2.04e-04 |
Pos logit contributions | |
ditch | +0.020 |
unks | +0.019 |
igs | +0.019 |
alk | +0.019 |
stack | +0.018 |
Neg logit contributions | |
disl | -0.011 |
Happy | -0.011 |
sure | -0.011 |
caring | -0.011 |
handsome | -0.010 |
Token | clean |
Token ID | 3424 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
disl | +0.000 |
Happy | +0.000 |
rav | +0.000 |
good | +0.000 |
Happy | +0.000 |
Neg logit contributions | |
ditch | -0.000 |
unks | -0.000 |
igs | -0.000 |
dam | -0.000 |
alk | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
disl | +0.028 |
sure | +0.026 |
caring | +0.025 |
Happy | +0.025 |
listened | +0.025 |
Neg logit contributions | |
ditch | -0.049 |
unks | -0.048 |
icer | -0.047 |
igs | -0.047 |
stack | -0.045 |
Token | no |
Token ID | 645 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
Happy | +0.026 |
Happy | +0.025 |
good | +0.024 |
minded | +0.023 |
rav | +0.023 |
Neg logit contributions | |
igs | -0.043 |
ditch | -0.041 |
unks | -0.040 |
stack | -0.038 |
footing | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
disl | +0.010 |
sure | +0.009 |
free | +0.009 |
Happy | +0.009 |
you | +0.009 |
Neg logit contributions | |
ditch | -0.014 |
igs | -0.014 |
unks | -0.013 |
ifi | -0.013 |
footing | -0.012 |
Token | one |
Token ID | 505 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Happy | +0.084 |
happy | +0.078 |
disl | +0.077 |
caring | +0.076 |
sure | +0.074 |
Neg logit contributions | |
unks | -0.091 |
igs | -0.089 |
ditch | -0.088 |
ifi | -0.087 |
icer | -0.085 |
Token | will |
Token ID | 481 |
Feature activation | +3.12e-03 |
Pos logit contributions | |
Happy | +0.016 |
caring | +0.016 |
disl | +0.016 |
Happy | +0.015 |
free | +0.015 |
Neg logit contributions | |
unks | -0.027 |
igs | -0.026 |
ditch | -0.026 |
enclosure | -0.025 |
alk | -0.025 |
Token | want |
Token ID | 765 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
ditch | +0.007 |
unks | +0.007 |
igs | +0.006 |
alk | +0.006 |
stack | +0.006 |
Neg logit contributions | |
sure | -0.004 |
disl | -0.003 |
Happy | -0.003 |
happy | -0.003 |
caring | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
unks | +0.050 |
ditch | +0.049 |
igs | +0.048 |
alk | +0.046 |
icer | +0.046 |
Neg logit contributions | |
sure | -0.015 |
disl | -0.015 |
happy | -0.014 |
Happy | -0.013 |
free | -0.013 |
Token | play |
Token ID | 711 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
sure | +0.014 |
Happy | +0.013 |
disl | +0.013 |
happy | +0.013 |
free | +0.013 |
Neg logit contributions | |
ditch | -0.024 |
unks | -0.024 |
igs | -0.023 |
alk | -0.022 |
stack | -0.022 |
Token | caul |
Token ID | 46087 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
unks | +0.012 |
ditch | +0.012 |
igs | +0.012 |
icer | +0.011 |
alk | +0.011 |
Neg logit contributions | |
sure | -0.012 |
disl | -0.012 |
free | -0.011 |
Happy | -0.011 |
happy | -0.011 |
Token | iflower |
Token ID | 42642 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
happy | +0.005 |
Happy | +0.005 |
caring | +0.005 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.004 |
icer | -0.003 |
alk | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
unks | +0.009 |
ditch | +0.009 |
igs | +0.009 |
stack | +0.009 |
alk | +0.009 |
Neg logit contributions | |
disl | -0.005 |
sure | -0.005 |
Happy | -0.005 |
free | -0.005 |
nos | -0.005 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
free | +0.002 |
Happy | +0.002 |
caring | +0.002 |
Neg logit contributions | |
ditch | -0.004 |
unks | -0.004 |
igs | -0.003 |
stack | -0.003 |
ses | -0.003 |
Token | qu |
Token ID | 627 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
sure | +0.016 |
Happy | +0.016 |
Happy | +0.016 |
free | +0.016 |
disl | +0.015 |
Neg logit contributions | |
unks | -0.023 |
igs | -0.022 |
ditch | -0.022 |
alk | -0.021 |
icer | -0.021 |
Token | arre |
Token ID | 9624 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
sure | +0.054 |
disl | +0.052 |
Happy | +0.051 |
happy | +0.051 |
caring | +0.051 |
Neg logit contributions | |
unks | -0.048 |
ditch | -0.047 |
igs | -0.045 |
icer | -0.044 |
alk | -0.043 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
disl | +0.111 |
Of | +0.098 |
Thank | +0.097 |
Happy | +0.096 |
caring | +0.095 |
Neg logit contributions | |
ditch | -0.074 |
igs | -0.074 |
icer | -0.071 |
unks | -0.068 |
alk | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-05 |
Pos logit contributions | |
disl | +0.016 |
talented | +0.015 |
sure | +0.014 |
observ | +0.014 |
rav | +0.014 |
Neg logit contributions | |
ditch | -0.020 |
alk | -0.020 |
enclosure | -0.020 |
loft | -0.019 |
cage | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
sure | +0.000 |
disl | +0.000 |
happy | +0.000 |
free | +0.000 |
listening | +0.000 |
Neg logit contributions | |
unks | -0.000 |
ditch | -0.000 |
igs | -0.000 |
alk | -0.000 |
stack | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
unks | +0.011 |
ditch | +0.011 |
igs | +0.011 |
icer | +0.011 |
alk | +0.011 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
disl | -0.004 |
Happy | -0.004 |
caring | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
igs | +0.006 |
alk | +0.005 |
ses | +0.005 |
unks | +0.005 |
alks | +0.005 |
Neg logit contributions | |
disl | -0.005 |
beh | -0.005 |
sure | -0.005 |
you | -0.005 |
don | -0.005 |
Token | � |
Token ID | 95 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
sure | +0.016 |
disl | +0.015 |
happy | +0.015 |
Happy | +0.015 |
caring | +0.015 |
Neg logit contributions | |
unks | -0.013 |
ditch | -0.013 |
igs | -0.013 |
icer | -0.012 |
alk | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
sure | +0.013 |
happy | +0.013 |
caring | +0.013 |
handsome | +0.012 |
free | +0.012 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.014 |
stack | -0.013 |
alk | -0.013 |
icer | -0.013 |
Token | ˜ |
Token ID | 41185 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
unks | +0.010 |
ditch | +0.009 |
enclosure | +0.009 |
icer | +0.009 |
igs | +0.009 |
Neg logit contributions | |
caring | -0.007 |
free | -0.007 |
forgiving | -0.006 |
sure | -0.006 |
handsome | -0.006 |
Token | Come |
Token ID | 16773 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
disl | +0.017 |
sure | +0.016 |
handsome | +0.016 |
caring | +0.016 |
happy | +0.016 |
Neg logit contributions | |
unks | -0.026 |
stack | -0.026 |
enclosure | -0.024 |
ditch | -0.024 |
ippy | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
sure | +0.010 |
happy | +0.009 |
disl | +0.009 |
Happy | +0.009 |
caring | +0.009 |
Neg logit contributions | |
unks | -0.020 |
ditch | -0.020 |
igs | -0.020 |
icer | -0.019 |
stack | -0.019 |
Token | Ex |
Token ID | 1475 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
free | +0.006 |
disl | +0.006 |
caring | +0.006 |
good | +0.006 |
sure | +0.006 |
Neg logit contributions | |
stack | -0.009 |
ditch | -0.009 |
enclosure | -0.008 |
unks | -0.008 |
loft | -0.008 |
Token | amine |
Token ID | 9862 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
happy | +0.086 |
disl | +0.082 |
sure | +0.081 |
Happy | +0.080 |
handsome | +0.080 |
Neg logit contributions | |
unks | -0.091 |
igs | -0.089 |
ditch | -0.088 |
ool | -0.085 |
icer | -0.084 |
Token | ! |
Token ID | 0 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
disl | +0.017 |
forg | +0.015 |
free | +0.015 |
caring | +0.015 |
good | +0.015 |
Neg logit contributions | |
unks | -0.028 |
ditch | -0.028 |
igs | -0.027 |
loft | -0.026 |
enclosure | -0.026 |
Token | â |
Token ID | 22940 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
sure | +0.007 |
disl | +0.006 |
happy | +0.006 |
caring | +0.006 |
free | +0.006 |
Neg logit contributions | |
ditch | -0.014 |
unks | -0.014 |
stack | -0.013 |
icer | -0.013 |
igs | -0.013 |
Token | € |
Token ID | 26391 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
sure | +0.027 |
happy | +0.026 |
caring | +0.026 |
nos | +0.026 |
handsome | +0.025 |
Neg logit contributions | |
stack | -0.031 |
unks | -0.031 |
alk | -0.030 |
ditch | -0.030 |
enclosure | -0.030 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
caring | +0.003 |
free | +0.003 |
sure | +0.003 |
handsome | +0.003 |
forgiving | +0.003 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
icer | -0.005 |
igs | -0.005 |
enclosure | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
sure | +0.010 |
happy | +0.009 |
Happy | +0.008 |
disl | +0.008 |
excited | +0.008 |
Neg logit contributions | |
unks | -0.031 |
ditch | -0.031 |
igs | -0.030 |
icer | -0.029 |
alk | -0.029 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.33e-04 |
Pos logit contributions | |
unks | +0.025 |
ditch | +0.025 |
igs | +0.023 |
icer | +0.023 |
stack | +0.023 |
Neg logit contributions | |
happy | -0.031 |
sure | -0.030 |
nos | -0.029 |
handsome | -0.029 |
caring | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
ditch | +0.000 |
unks | +0.000 |
igs | +0.000 |
stack | +0.000 |
alk | +0.000 |
Neg logit contributions | |
disl | -0.000 |
sure | -0.000 |
caring | -0.000 |
Happy | -0.000 |
happy | -0.000 |
Token | smiled |
Token ID | 13541 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
disl | +0.013 |
free | +0.013 |
caring | +0.012 |
sure | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
ditch | -0.017 |
unks | -0.017 |
stack | -0.017 |
igs | -0.017 |
loft | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
disl | +0.013 |
have | +0.011 |
beh | +0.011 |
listened | +0.011 |
forg | +0.011 |
Neg logit contributions | |
ditch | -0.014 |
hood | -0.014 |
tentacles | -0.014 |
stack | -0.013 |
pouch | -0.013 |
Token | Pret |
Token ID | 37123 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
happy | +0.005 |
caring | +0.005 |
free | +0.005 |
Neg logit contributions | |
unks | -0.008 |
ditch | -0.008 |
igs | -0.007 |
stack | -0.007 |
alk | -0.007 |
Token | ending |
Token ID | 1571 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
sure | +0.067 |
happy | +0.066 |
Happy | +0.064 |
nos | +0.062 |
disl | +0.061 |
Neg logit contributions | |
unks | -0.115 |
igs | -0.109 |
ditch | -0.109 |
alk | -0.106 |
icer | -0.105 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
disl | +0.036 |
Happy | +0.034 |
sure | +0.034 |
Happy | +0.033 |
free | +0.033 |
Neg logit contributions | |
ditch | -0.069 |
igs | -0.067 |
unks | -0.067 |
stack | -0.066 |
alk | -0.064 |
Token | so |
Token ID | 523 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
ditch | +0.027 |
unks | +0.026 |
igs | +0.025 |
stack | +0.025 |
alk | +0.024 |
Neg logit contributions | |
disl | -0.014 |
Happy | -0.014 |
free | -0.013 |
Happy | -0.013 |
you | -0.013 |
Token | much |
Token ID | 881 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
you | +0.003 |
rav | +0.003 |
Happy | +0.003 |
good | +0.003 |
minded | +0.003 |
Neg logit contributions | |
igs | -0.004 |
ditch | -0.004 |
unks | -0.004 |
alks | -0.004 |
alk | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
disl | +0.020 |
you | +0.020 |
rav | +0.020 |
Happy | +0.019 |
free | +0.019 |
Neg logit contributions | |
ditch | -0.034 |
igs | -0.032 |
dam | -0.031 |
gap | -0.030 |
unks | -0.030 |
Token | each |
Token ID | 1123 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ditch | +0.028 |
unks | +0.028 |
igs | +0.027 |
icer | +0.027 |
stack | +0.027 |
Neg logit contributions | |
sure | -0.016 |
disl | -0.015 |
happy | -0.015 |
Happy | -0.014 |
caring | -0.014 |
Token | choose |
Token ID | 3853 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ditch | +0.027 |
unks | +0.027 |
igs | +0.026 |
icer | +0.026 |
loft | +0.025 |
Neg logit contributions | |
sure | -0.016 |
disl | -0.016 |
Happy | -0.015 |
caring | -0.015 |
free | -0.014 |
Token | an |
Token ID | 281 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
disl | +0.013 |
sure | +0.013 |
free | +0.012 |
Happy | +0.012 |
caring | +0.011 |
Neg logit contributions | |
unks | -0.020 |
ditch | -0.020 |
igs | -0.019 |
loft | -0.019 |
icer | -0.019 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
unks | +0.040 |
igs | +0.038 |
ditch | +0.038 |
alk | +0.037 |
stack | +0.037 |
Neg logit contributions | |
sure | -0.027 |
happy | -0.026 |
kind | -0.024 |
excited | -0.024 |
caring | -0.024 |
Token | cream |
Token ID | 8566 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
unks | +0.044 |
ditch | +0.044 |
igs | +0.042 |
icer | +0.041 |
alk | +0.041 |
Neg logit contributions | |
sure | -0.026 |
happy | -0.024 |
disl | -0.024 |
Happy | -0.023 |
caring | -0.023 |
Token | cone |
Token ID | 27763 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
unks | +0.022 |
ditch | +0.022 |
igs | +0.021 |
alk | +0.020 |
icer | +0.020 |
Neg logit contributions | |
sure | -0.026 |
happy | -0.025 |
disl | -0.024 |
Happy | -0.024 |
caring | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
unks | +0.080 |
ditch | +0.080 |
igs | +0.078 |
icer | +0.076 |
alk | +0.076 |
Neg logit contributions | |
sure | -0.021 |
happy | -0.019 |
disl | -0.018 |
Happy | -0.018 |
caring | -0.017 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
unks | +0.007 |
ditch | +0.007 |
igs | +0.006 |
icer | +0.006 |
stack | +0.006 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
Happy | -0.004 |
disl | -0.004 |
caring | -0.004 |
Token | picks |
Token ID | 11103 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
unks | +0.041 |
ditch | +0.041 |
igs | +0.040 |
icer | +0.039 |
alk | +0.039 |
Neg logit contributions | |
sure | -0.022 |
happy | -0.021 |
disl | -0.020 |
Happy | -0.020 |
caring | -0.020 |
Token | chocolate |
Token ID | 11311 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
disl | +0.029 |
free | +0.026 |
caring | +0.026 |
sure | +0.026 |
listening | +0.025 |
Neg logit contributions | |
ditch | -0.047 |
icer | -0.046 |
unks | -0.046 |
igs | -0.044 |
ippy | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
unks | +0.018 |
ditch | +0.018 |
igs | +0.017 |
icer | +0.017 |
stack | +0.017 |
Neg logit contributions | |
sure | -0.009 |
disl | -0.008 |
happy | -0.008 |
Happy | -0.008 |
caring | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
sure | +0.014 |
disl | +0.013 |
happy | +0.012 |
Happy | +0.012 |
caring | +0.012 |
Neg logit contributions | |
ditch | -0.040 |
unks | -0.040 |
igs | -0.039 |
stack | -0.038 |
icer | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +7.39e-03 |
Pos logit contributions | |
sure | +0.008 |
disl | +0.008 |
happy | +0.008 |
caring | +0.008 |
handsome | +0.008 |
Neg logit contributions | |
unks | -0.019 |
ditch | -0.019 |
stack | -0.018 |
igs | -0.018 |
alk | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ditch | +0.020 |
unks | +0.020 |
igs | +0.020 |
icer | +0.020 |
loft | +0.019 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.004 |
Happy | -0.004 |
disl | -0.004 |
caring | -0.003 |
Token | As |
Token ID | 1722 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.029 |
igs | +0.028 |
stack | +0.027 |
icer | +0.027 |
Neg logit contributions | |
sure | -0.021 |
disl | -0.020 |
happy | -0.020 |
Happy | -0.020 |
caring | -0.019 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ditch | +0.047 |
unks | +0.047 |
igs | +0.046 |
stack | +0.044 |
loft | +0.044 |
Neg logit contributions | |
sure | -0.015 |
disl | -0.014 |
happy | -0.013 |
Happy | -0.013 |
free | -0.013 |
Token | slowly |
Token ID | 6364 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
unks | +0.031 |
ditch | +0.031 |
igs | +0.031 |
alk | +0.030 |
icer | +0.029 |
Neg logit contributions | |
sure | -0.014 |
listened | -0.012 |
happy | -0.012 |
Happy | -0.011 |
excited | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
unks | +0.067 |
icer | +0.065 |
ditch | +0.065 |
igs | +0.062 |
stack | +0.061 |
Neg logit contributions | |
sure | -0.038 |
happy | -0.035 |
listened | -0.034 |
excited | -0.033 |
Happy | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
happy | +0.002 |
Happy | +0.002 |
caring | +0.002 |
Neg logit contributions | |
ditch | -0.006 |
unks | -0.006 |
igs | -0.006 |
alk | -0.006 |
icer | -0.006 |
Token | way |
Token ID | 835 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
disl | +0.021 |
Happy | +0.020 |
Happy | +0.020 |
free | +0.020 |
sure | +0.020 |
Neg logit contributions | |
ditch | -0.025 |
unks | -0.024 |
igs | -0.023 |
loft | -0.023 |
stack | -0.023 |
Token | through |
Token ID | 832 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
unks | +0.032 |
ditch | +0.031 |
icer | +0.031 |
igs | +0.030 |
alk | +0.030 |
Neg logit contributions | |
sure | -0.013 |
happy | -0.012 |
free | -0.011 |
excited | -0.011 |
listening | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
unks | +0.005 |
ditch | +0.005 |
igs | +0.005 |
icer | +0.005 |
stack | +0.005 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.001 |
Happy | -0.001 |
disl | -0.001 |
caring | -0.001 |
Token | looking |
Token ID | 2045 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
unks | +0.057 |
igs | +0.056 |
alk | +0.055 |
ditch | +0.055 |
icer | +0.054 |
Neg logit contributions | |
happy | -0.021 |
sure | -0.020 |
nos | -0.017 |
listening | -0.017 |
excited | -0.017 |
Token | at |
Token ID | 379 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
disl | +0.007 |
sure | +0.007 |
Happy | +0.007 |
Happy | +0.007 |
you | +0.007 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.012 |
igs | -0.012 |
icer | -0.012 |
ses | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
ditch | +0.012 |
igs | +0.012 |
unks | +0.012 |
loft | +0.011 |
alk | +0.011 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
Happy | -0.003 |
listening | -0.003 |
forg | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
disl | +0.006 |
sure | +0.006 |
Happy | +0.006 |
Happy | +0.005 |
free | +0.005 |
Neg logit contributions | |
ditch | -0.014 |
unks | -0.014 |
igs | -0.013 |
stack | -0.013 |
icer | -0.013 |
Token | its |
Token ID | 663 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
unks | +0.031 |
ditch | +0.030 |
igs | +0.030 |
loft | +0.029 |
icer | +0.029 |
Neg logit contributions | |
sure | -0.014 |
happy | -0.013 |
disl | -0.012 |
nos | -0.012 |
caring | -0.011 |
Token | tiny |
Token ID | 7009 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ditch | +0.021 |
unks | +0.021 |
loft | +0.020 |
igs | +0.019 |
stack | +0.019 |
Neg logit contributions | |
happy | -0.022 |
sure | -0.022 |
nos | -0.021 |
disl | -0.021 |
kind | -0.020 |
Token | eyes |
Token ID | 2951 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
stack | +0.050 |
unks | +0.050 |
ditch | +0.049 |
loft | +0.048 |
icer | +0.047 |
Neg logit contributions | |
sure | -0.058 |
happy | -0.057 |
nos | -0.056 |
gr | -0.054 |
disl | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
disl | +0.003 |
sure | +0.003 |
caring | +0.003 |
Happy | +0.003 |
talented | +0.003 |
Neg logit contributions | |
ditch | -0.007 |
unks | -0.007 |
igs | -0.007 |
enclosure | -0.007 |
loft | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
unks | +0.006 |
ditch | +0.006 |
igs | +0.006 |
icer | +0.005 |
alk | +0.005 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
disl | -0.003 |
Happy | -0.003 |
caring | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
unks | +0.013 |
ditch | +0.013 |
igs | +0.013 |
icer | +0.013 |
stack | +0.013 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.002 |
disl | -0.002 |
excited | -0.002 |
Happy | -0.002 |
Token | Tom |
Token ID | 13787 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
unks | +0.021 |
ditch | +0.021 |
igs | +0.020 |
icer | +0.020 |
alk | +0.020 |
Neg logit contributions | |
sure | -0.015 |
happy | -0.014 |
disl | -0.014 |
Happy | -0.014 |
caring | -0.013 |
Token | understand |
Token ID | 1833 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
Happy | +0.004 |
disl | +0.004 |
Happy | +0.004 |
minded | +0.004 |
you | +0.004 |
Neg logit contributions | |
ditch | -0.006 |
alk | -0.006 |
ifi | -0.006 |
igs | -0.006 |
grip | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
Happy | +0.010 |
rav | +0.009 |
good | +0.008 |
free | +0.008 |
disl | +0.008 |
Neg logit contributions | |
ditch | -0.014 |
icer | -0.014 |
igs | -0.014 |
unks | -0.014 |
pel | -0.013 |
Token | thing |
Token ID | 1517 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
disl | +0.012 |
Happy | +0.011 |
Happy | +0.010 |
free | +0.010 |
beh | +0.010 |
Neg logit contributions | |
ditch | -0.014 |
ool | -0.012 |
loft | -0.012 |
enclosure | -0.012 |
trailer | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
disl | +0.011 |
Happy | +0.011 |
talented | +0.010 |
handsome | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
stack | -0.015 |
unks | -0.015 |
ditch | -0.015 |
ippy | -0.014 |
enclosure | -0.014 |
Token | As |
Token ID | 1081 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
sure | +0.012 |
disl | +0.011 |
caring | +0.011 |
happy | +0.011 |
free | +0.011 |
Neg logit contributions | |
ditch | -0.014 |
unks | -0.013 |
icer | -0.013 |
stack | -0.012 |
loft | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ditch | +0.031 |
unks | +0.030 |
igs | +0.029 |
loft | +0.028 |
icer | +0.028 |
Neg logit contributions | |
disl | -0.013 |
free | -0.011 |
sure | -0.011 |
you | -0.010 |
beh | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
unks | +0.079 |
ditch | +0.079 |
igs | +0.076 |
icer | +0.074 |
alk | +0.074 |
Neg logit contributions | |
sure | -0.036 |
happy | -0.033 |
disl | -0.033 |
Happy | -0.032 |
caring | -0.032 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ditch | +0.047 |
unks | +0.047 |
igs | +0.045 |
alk | +0.044 |
loft | +0.043 |
Neg logit contributions | |
sure | -0.028 |
disl | -0.027 |
Happy | -0.027 |
free | -0.027 |
happy | -0.026 |
Token | around |
Token ID | 1088 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sure | +0.012 |
happy | +0.011 |
disl | +0.011 |
Happy | +0.010 |
caring | +0.010 |
Neg logit contributions | |
unks | -0.027 |
ditch | -0.027 |
igs | -0.026 |
icer | -0.025 |
alk | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +4.47e-04 |
Pos logit contributions | |
disl | +0.017 |
sure | +0.017 |
caring | +0.016 |
beh | +0.016 |
Happy | +0.016 |
Neg logit contributions | |
ditch | -0.031 |
unks | -0.030 |
stack | -0.029 |
icer | -0.029 |
alk | -0.029 |
Token | stadium |
Token ID | 10308 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
ditch | +0.001 |
unks | +0.001 |
igs | +0.001 |
icer | +0.001 |
alk | +0.001 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
happy | -0.001 |
Happy | -0.001 |
caring | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | +8.15e-03 |
Pos logit contributions | |
unks | +0.026 |
ditch | +0.026 |
igs | +0.025 |
poles | +0.024 |
loft | +0.024 |
Neg logit contributions | |
disl | -0.020 |
free | -0.019 |
sure | -0.018 |
forg | -0.017 |
caring | -0.017 |
Token | went |
Token ID | 1816 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
ditch | +0.019 |
unks | +0.019 |
icer | +0.018 |
igs | +0.018 |
alk | +0.018 |
Neg logit contributions | |
sure | -0.008 |
disl | -0.008 |
caring | -0.007 |
free | -0.007 |
Happy | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -8.44e-04 |
Pos logit contributions | |
unks | +0.017 |
ditch | +0.017 |
icer | +0.017 |
igs | +0.017 |
alk | +0.016 |
Neg logit contributions | |
sure | -0.003 |
happy | -0.003 |
Happy | -0.003 |
listening | -0.003 |
caring | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
Happy | +0.001 |
disl | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.002 |
ditch | -0.002 |
igs | -0.002 |
icer | -0.002 |
stack | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | +8.74e-03 |
Pos logit contributions | |
happy | +0.003 |
kind | +0.003 |
sure | +0.003 |
Happy | +0.003 |
nos | +0.003 |
Neg logit contributions | |
unks | -0.003 |
igs | -0.003 |
alk | -0.003 |
ditch | -0.003 |
ifi | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
enclosure | +0.019 |
ditch | +0.019 |
unks | +0.019 |
stack | +0.018 |
loft | +0.018 |
Neg logit contributions | |
disl | -0.010 |
sure | -0.010 |
handsome | -0.009 |
free | -0.009 |
caring | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
ditch | +0.074 |
unks | +0.073 |
igs | +0.071 |
stack | +0.070 |
icer | +0.070 |
Neg logit contributions | |
sure | -0.033 |
happy | -0.031 |
Happy | -0.029 |
caring | -0.028 |
disl | -0.028 |
Token | moms |
Token ID | 34015 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
caring | +0.002 |
disl | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
igs | -0.003 |
alk | -0.003 |
icer | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
disl | +0.005 |
sure | +0.005 |
caring | +0.005 |
handsome | +0.005 |
free | +0.004 |
Neg logit contributions | |
unks | -0.012 |
ditch | -0.011 |
enclosure | -0.011 |
stack | -0.011 |
loft | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
unks | +0.033 |
ditch | +0.032 |
igs | +0.032 |
icer | +0.031 |
stack | +0.030 |
Neg logit contributions | |
sure | -0.020 |
Happy | -0.019 |
happy | -0.019 |
disl | -0.019 |
nos | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.37e-04 |
Pos logit contributions | |
unks | +0.030 |
ditch | +0.029 |
igs | +0.028 |
icer | +0.028 |
stack | +0.028 |
Neg logit contributions | |
sure | -0.015 |
disl | -0.014 |
happy | -0.014 |
Happy | -0.014 |
caring | -0.014 |
Token | our |
Token ID | 674 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
unks | +0.031 |
ditch | +0.031 |
igs | +0.031 |
alk | +0.029 |
icer | +0.029 |
Neg logit contributions | |
sure | -0.014 |
disl | -0.014 |
Happy | -0.013 |
free | -0.013 |
happy | -0.013 |
Token | health |
Token ID | 1535 |
Feature activation | -6.56e-03 |
Pos logit contributions | |
sure | +0.010 |
Happy | +0.010 |
Happy | +0.010 |
disl | +0.009 |
you | +0.009 |
Neg logit contributions | |
ditch | -0.011 |
unks | -0.011 |
ses | -0.011 |
igs | -0.011 |
loft | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.02e-04 |
Pos logit contributions | |
disl | +0.007 |
sure | +0.006 |
Happy | +0.006 |
handsome | +0.006 |
caring | +0.006 |
Neg logit contributions | |
unks | -0.015 |
ditch | -0.014 |
alk | -0.014 |
igs | -0.014 |
ool | -0.014 |
Token | |
Token ID | 220 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
sure | +0.001 |
listening | +0.001 |
caring | +0.001 |
free | +0.001 |
disl | +0.001 |
Neg logit contributions | |
unks | -0.001 |
ditch | -0.001 |
igs | -0.001 |
icer | -0.001 |
alk | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
sure | +0.018 |
disl | +0.017 |
caring | +0.016 |
Happy | +0.016 |
happy | +0.016 |
Neg logit contributions | |
unks | -0.050 |
ditch | -0.049 |
igs | -0.047 |
icer | -0.047 |
alk | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
unks | +0.026 |
ditch | +0.026 |
igs | +0.025 |
icer | +0.024 |
stack | +0.024 |
Neg logit contributions | |
sure | -0.008 |
happy | -0.007 |
disl | -0.007 |
Happy | -0.007 |
caring | -0.006 |
Token | L |
Token ID | 43 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
unks | +0.040 |
ditch | +0.040 |
igs | +0.039 |
icer | +0.038 |
stack | +0.037 |
Neg logit contributions | |
sure | -0.021 |
happy | -0.019 |
disl | -0.019 |
Happy | -0.018 |
caring | -0.018 |
Token | ily |
Token ID | 813 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
ditch | +0.029 |
unks | +0.028 |
stack | +0.027 |
igs | +0.026 |
loft | +0.026 |
Neg logit contributions | |
sure | -0.029 |
happy | -0.027 |
disl | -0.026 |
free | -0.025 |
forg | -0.025 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.011 |
igs | +0.010 |
icer | +0.010 |
enclosure | +0.010 |
Neg logit contributions | |
free | -0.004 |
sure | -0.003 |
disl | -0.003 |
Happy | -0.003 |
caring | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
sure | +0.010 |
disl | +0.010 |
Happy | +0.009 |
free | +0.009 |
happy | +0.009 |
Neg logit contributions | |
unks | -0.023 |
ditch | -0.023 |
igs | -0.023 |
stack | -0.022 |
icer | -0.022 |
Token | man |
Token ID | 582 |
Feature activation | -6.55e-03 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.003 |
Happy | +0.003 |
you | +0.003 |
beh | +0.003 |
Neg logit contributions | |
ditch | -0.007 |
loft | -0.007 |
unks | -0.006 |
igs | -0.006 |
icer | -0.006 |
Token | what |
Token ID | 644 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
disl | +0.005 |
Happy | +0.004 |
good | +0.004 |
rav | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
ditch | -0.007 |
igs | -0.007 |
unks | -0.006 |
dam | -0.006 |
sticks | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
free | +0.024 |
sure | +0.023 |
disl | +0.022 |
pleased | +0.021 |
you | +0.021 |
Neg logit contributions | |
igs | -0.038 |
ditch | -0.037 |
poles | -0.037 |
unks | -0.037 |
sticks | -0.036 |
Token | high |
Token ID | 1029 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ditch | +0.019 |
unks | +0.019 |
igs | +0.018 |
loft | +0.018 |
stack | +0.017 |
Neg logit contributions | |
disl | -0.011 |
sure | -0.011 |
Happy | -0.011 |
caring | -0.011 |
happy | -0.011 |
Token | up |
Token ID | 510 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
ditch | +0.041 |
unks | +0.039 |
igs | +0.039 |
icer | +0.038 |
loft | +0.038 |
Neg logit contributions | |
sure | -0.024 |
disl | -0.024 |
caring | -0.023 |
Happy | -0.023 |
Happy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ditch | +0.064 |
unks | +0.064 |
igs | +0.062 |
alk | +0.060 |
icer | +0.060 |
Neg logit contributions | |
sure | -0.026 |
disl | -0.025 |
Happy | -0.024 |
happy | -0.023 |
caring | -0.023 |
Token | One |
Token ID | 1881 |
Feature activation | +5.03e-04 |
Pos logit contributions | |
sure | +0.017 |
happy | +0.016 |
disl | +0.016 |
Happy | +0.016 |
caring | +0.016 |
Neg logit contributions | |
unks | -0.017 |
ditch | -0.017 |
igs | -0.016 |
icer | -0.015 |
alk | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +1.20e-04 |
Pos logit contributions | |
ditch | +0.001 |
unks | +0.001 |
igs | +0.001 |
icer | +0.001 |
alk | +0.001 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
Happy | -0.000 |
caring | -0.000 |
handsome | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ditch | +0.000 |
unks | +0.000 |
igs | +0.000 |
loft | +0.000 |
icer | +0.000 |
Neg logit contributions | |
disl | -0.000 |
sure | -0.000 |
caring | -0.000 |
responsible | -0.000 |
you | -0.000 |
Token | found |
Token ID | 1043 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
ditch | +0.040 |
unks | +0.040 |
igs | +0.039 |
icer | +0.038 |
loft | +0.037 |
Neg logit contributions | |
sure | -0.022 |
disl | -0.021 |
Happy | -0.020 |
happy | -0.020 |
caring | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
sure | +0.006 |
happy | +0.005 |
kind | +0.004 |
nos | +0.004 |
excited | +0.004 |
Neg logit contributions | |
unks | -0.026 |
ditch | -0.025 |
alk | -0.025 |
igs | -0.025 |
icer | -0.024 |
Token | wallet |
Token ID | 13008 |
Feature activation | +7.57e-04 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
caring | +0.002 |
disl | +0.002 |
nos | +0.002 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
igs | -0.003 |
icer | -0.003 |
alk | -0.003 |
Token | |
Token ID | 220 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
sure | +0.004 |
happy | +0.004 |
disl | +0.004 |
caring | +0.004 |
free | +0.004 |
Neg logit contributions | |
unks | -0.008 |
ditch | -0.008 |
igs | -0.007 |
stack | -0.007 |
icer | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
sure | +0.016 |
disl | +0.015 |
caring | +0.015 |
happy | +0.014 |
Happy | +0.014 |
Neg logit contributions | |
unks | -0.041 |
ditch | -0.040 |
igs | -0.039 |
alk | -0.038 |
icer | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
unks | +0.019 |
ditch | +0.019 |
igs | +0.018 |
icer | +0.018 |
alk | +0.017 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.005 |
disl | -0.005 |
Happy | -0.005 |
caring | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -6.04e-03 |
Pos logit contributions | |
unks | +0.024 |
ditch | +0.024 |
igs | +0.023 |
icer | +0.022 |
alk | +0.022 |
Neg logit contributions | |
sure | -0.016 |
happy | -0.015 |
disl | -0.014 |
Happy | -0.014 |
caring | -0.014 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sure | +0.011 |
disl | +0.010 |
happy | +0.010 |
Happy | +0.010 |
free | +0.010 |
Neg logit contributions | |
ditch | -0.009 |
unks | -0.009 |
igs | -0.009 |
icer | -0.009 |
stack | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
sure | +0.015 |
caring | +0.014 |
happy | +0.014 |
kind | +0.014 |
Happy | +0.013 |
Neg logit contributions | |
unks | -0.035 |
ditch | -0.034 |
icer | -0.033 |
stack | -0.033 |
igs | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -8.88e-05 |
Pos logit contributions | |
ditch | +0.065 |
unks | +0.065 |
igs | +0.063 |
loft | +0.061 |
icer | +0.061 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.014 |
Happy | -0.013 |
caring | -0.013 |
disl | -0.013 |
Token | story |
Token ID | 1621 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
disl | +0.000 |
sure | +0.000 |
free | +0.000 |
Happy | +0.000 |
happy | +0.000 |
Neg logit contributions | |
ditch | -0.000 |
igs | -0.000 |
unks | -0.000 |
alk | -0.000 |
icer | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
sure | +0.033 |
disl | +0.031 |
free | +0.030 |
handsome | +0.030 |
happy | +0.030 |
Neg logit contributions | |
unks | -0.043 |
ditch | -0.043 |
alk | -0.042 |
igs | -0.042 |
stack | -0.041 |
Token | that |
Token ID | 326 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
sure | +0.014 |
happy | +0.013 |
disl | +0.012 |
caring | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
ditch | -0.030 |
unks | -0.030 |
igs | -0.029 |
icer | -0.029 |
stack | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Happy | +0.032 |
disl | +0.032 |
handsome | +0.030 |
free | +0.030 |
Happy | +0.028 |
Neg logit contributions | |
ditch | -0.057 |
igs | -0.056 |
unks | -0.054 |
stack | -0.054 |
alk | -0.053 |
Token | play |
Token ID | 711 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
sure | +0.010 |
you | +0.010 |
Happy | +0.010 |
Happy | +0.009 |
free | +0.009 |
Neg logit contributions | |
ditch | -0.013 |
igs | -0.012 |
unks | -0.012 |
loft | -0.011 |
alk | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
disl | +0.014 |
sure | +0.014 |
caring | +0.013 |
Happy | +0.013 |
free | +0.012 |
Neg logit contributions | |
ditch | -0.035 |
unks | -0.034 |
igs | -0.034 |
icer | -0.033 |
loft | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
unks | +0.039 |
ditch | +0.039 |
alk | +0.038 |
stack | +0.038 |
igs | +0.037 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.011 |
Happy | -0.009 |
excited | -0.009 |
disl | -0.008 |
Token | toys |
Token ID | 14958 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
happy | +0.011 |
sure | +0.011 |
Happy | +0.010 |
free | +0.010 |
nos | +0.010 |
Neg logit contributions | |
unks | -0.010 |
ditch | -0.010 |
igs | -0.010 |
alk | -0.010 |
stack | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
sure | +0.005 |
happy | +0.005 |
Happy | +0.005 |
free | +0.004 |
caring | +0.004 |
Neg logit contributions | |
unks | -0.015 |
ditch | -0.015 |
igs | -0.014 |
icer | -0.014 |
alk | -0.014 |
Token | pretending |
Token ID | 23662 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
unks | +0.021 |
ditch | +0.021 |
igs | +0.020 |
icer | +0.020 |
alk | +0.020 |
Neg logit contributions | |
sure | -0.010 |
happy | -0.009 |
Happy | -0.009 |
disl | -0.009 |
caring | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
sure | +0.003 |
disl | +0.003 |
free | +0.003 |
caring | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
ditch | -0.008 |
unks | -0.008 |
igs | -0.008 |
stack | -0.008 |
loft | -0.008 |
Token | be |
Token ID | 307 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
unks | +0.021 |
ditch | +0.020 |
igs | +0.020 |
icer | +0.020 |
ifier | +0.019 |
Neg logit contributions | |
happy | -0.009 |
sure | -0.008 |
disl | -0.008 |
kind | -0.008 |
listen | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -3.45e-03 |
Pos logit contributions | |
ditch | +0.005 |
unks | +0.005 |
igs | +0.005 |
loft | +0.005 |
trailer | +0.005 |
Neg logit contributions | |
sure | -0.003 |
disl | -0.003 |
you | -0.003 |
good | -0.003 |
Happy | -0.003 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.76e-04 |
Pos logit contributions | |
sure | +0.005 |
disl | +0.005 |
you | +0.005 |
free | +0.005 |
Happy | +0.004 |
Neg logit contributions | |
ditch | -0.006 |
unks | -0.006 |
igs | -0.006 |
loft | -0.006 |
stack | -0.006 |
Token | knight |
Token ID | 22062 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
sure | +0.000 |
happy | +0.000 |
disl | +0.000 |
Happy | +0.000 |
caring | +0.000 |
Neg logit contributions | |
unks | -0.000 |
ditch | -0.000 |
igs | -0.000 |
icer | -0.000 |
stack | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.008 |
caring | +0.008 |
free | +0.008 |
happy | +0.008 |
Neg logit contributions | |
unks | -0.019 |
ditch | -0.018 |
igs | -0.018 |
stack | -0.017 |
alk | -0.017 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
disl | +0.007 |
sure | +0.007 |
free | +0.006 |
caring | +0.006 |
Happy | +0.006 |
Neg logit contributions | |
unks | -0.013 |
ditch | -0.013 |
igs | -0.012 |
icer | -0.012 |
loft | -0.012 |
Token | tag |
Token ID | 7621 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
sure | +0.014 |
disl | +0.014 |
caring | +0.013 |
Happy | +0.013 |
happy | +0.013 |
Neg logit contributions | |
ditch | -0.028 |
unks | -0.028 |
igs | -0.027 |
icer | -0.026 |
stack | -0.026 |
Token | outside |
Token ID | 2354 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
unks | +0.060 |
ditch | +0.060 |
igs | +0.058 |
icer | +0.057 |
alk | +0.057 |
Neg logit contributions | |
sure | -0.022 |
happy | -0.020 |
disl | -0.019 |
Happy | -0.019 |
caring | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
ditch | +0.018 |
unks | +0.018 |
stack | +0.017 |
loft | +0.017 |
igs | +0.017 |
Neg logit contributions | |
disl | -0.009 |
sure | -0.008 |
handsome | -0.008 |
caring | -0.008 |
forg | -0.008 |
Token | Sus |
Token ID | 8932 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
sure | +0.010 |
disl | +0.009 |
caring | +0.009 |
happy | +0.009 |
free | +0.009 |
Neg logit contributions | |
unks | -0.015 |
ditch | -0.015 |
igs | -0.014 |
icer | -0.014 |
stack | -0.014 |
Token | ie |
Token ID | 494 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
happy | +0.002 |
Happy | +0.002 |
caring | +0.002 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
igs | -0.002 |
icer | -0.002 |
alk | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
unks | +0.015 |
ditch | +0.015 |
igs | +0.014 |
icer | +0.014 |
alk | +0.014 |
Neg logit contributions | |
sure | -0.006 |
happy | -0.005 |
disl | -0.005 |
Happy | -0.005 |
caring | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
unks | +0.055 |
ditch | +0.055 |
igs | +0.053 |
icer | +0.052 |
alk | +0.052 |
Neg logit contributions | |
sure | -0.023 |
happy | -0.021 |
disl | -0.020 |
Happy | -0.020 |
caring | -0.020 |
Token | furry |
Token ID | 40857 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
unks | +0.034 |
ditch | +0.032 |
igs | +0.032 |
alk | +0.031 |
icer | +0.031 |
Neg logit contributions | |
happy | -0.021 |
sure | -0.020 |
nos | -0.019 |
kind | -0.019 |
handsome | -0.019 |
Token | er |
Token ID | 1931 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
unks | +0.099 |
igs | +0.092 |
ditch | +0.091 |
icer | +0.090 |
alk | +0.088 |
Neg logit contributions | |
happy | -0.070 |
kind | -0.065 |
nos | -0.064 |
excited | -0.061 |
gr | -0.060 |
Token | into |
Token ID | 656 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
unks | +0.018 |
ditch | +0.018 |
stack | +0.017 |
igs | +0.017 |
alk | +0.017 |
Neg logit contributions | |
disl | -0.011 |
sure | -0.011 |
caring | -0.010 |
handsome | -0.010 |
happy | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-05 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
Happy | +0.002 |
caring | +0.001 |
disl | +0.001 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
igs | -0.005 |
stack | -0.005 |
alk | -0.005 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
ditch | +0.000 |
unks | +0.000 |
icer | +0.000 |
igs | +0.000 |
loft | +0.000 |
Neg logit contributions | |
sure | -0.000 |
disl | -0.000 |
caring | -0.000 |
listening | -0.000 |
happy | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
disl | +0.002 |
forg | +0.002 |
handsome | +0.002 |
sure | +0.002 |
caring | +0.002 |
Neg logit contributions | |
ditch | -0.004 |
unks | -0.004 |
alk | -0.004 |
stack | -0.004 |
enclosure | -0.004 |
Token | P |
Token ID | 350 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
disl | +0.002 |
caring | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
unks | -0.003 |
ditch | -0.003 |
igs | -0.003 |
icer | -0.003 |
alk | -0.003 |
Token | up |
Token ID | 929 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
sure | +0.007 |
happy | +0.006 |
disl | +0.006 |
Happy | +0.006 |
caring | +0.006 |
Neg logit contributions | |
unks | -0.005 |
ditch | -0.005 |
igs | -0.005 |
icer | -0.005 |
alk | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
disl | +0.024 |
sure | +0.023 |
Happy | +0.022 |
free | +0.022 |
caring | +0.022 |
Neg logit contributions | |
unks | -0.063 |
ditch | -0.062 |
igs | -0.061 |
icer | -0.059 |
alk | -0.059 |
Token | so |
Token ID | 523 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.011 |
igs | +0.010 |
stack | +0.010 |
loft | +0.010 |
Neg logit contributions | |
disl | -0.005 |
Happy | -0.004 |
free | -0.004 |
minded | -0.004 |
rav | -0.004 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
minded | +0.004 |
you | +0.003 |
disl | +0.003 |
Happy | +0.003 |
good | +0.003 |
Neg logit contributions | |
igs | -0.009 |
unks | -0.009 |
alks | -0.008 |
ditch | -0.008 |
alk | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
free | +0.010 |
disl | +0.010 |
Happy | +0.010 |
handsome | +0.010 |
happy | +0.010 |
Neg logit contributions | |
unks | -0.014 |
igs | -0.014 |
alk | -0.013 |
ditch | -0.013 |
ippy | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.009 |
happy | +0.009 |
caring | +0.009 |
listening | +0.008 |
Neg logit contributions | |
unks | -0.013 |
ditch | -0.013 |
igs | -0.012 |
alk | -0.012 |
icer | -0.012 |
Token | do |
Token ID | 466 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
sure | +0.002 |
happy | +0.002 |
disl | +0.002 |
caring | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.004 |
icer | -0.004 |
stack | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Happy | +0.012 |
disl | +0.012 |
Happy | +0.011 |
free | +0.011 |
rav | +0.011 |
Neg logit contributions | |
igs | -0.017 |
unks | -0.016 |
ditch | -0.015 |
alk | -0.015 |
pel | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
free | +0.026 |
disl | +0.024 |
minded | +0.024 |
sure | +0.023 |
rav | +0.023 |
Neg logit contributions | |
igs | -0.043 |
loft | -0.041 |
unks | -0.041 |
ool | -0.040 |
ditch | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.92e-04 |
Pos logit contributions | |
unks | +0.010 |
ditch | +0.010 |
igs | +0.010 |
icer | +0.010 |
loft | +0.010 |
Neg logit contributions | |
sure | -0.006 |
disl | -0.006 |
free | -0.006 |
Happy | -0.006 |
happy | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -3.35e-04 |
Pos logit contributions | |
disl | +0.000 |
free | +0.000 |
Happy | +0.000 |
Happy | +0.000 |
rav | +0.000 |
Neg logit contributions | |
unks | -0.001 |
ool | -0.001 |
igs | -0.001 |
stack | -0.001 |
ditch | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
disl | +0.000 |
Happy | +0.000 |
Sorry | +0.000 |
beh | +0.000 |
handsome | +0.000 |
Neg logit contributions | |
stack | -0.001 |
alk | -0.001 |
ditch | -0.001 |
loft | -0.001 |
unks | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.009 |
handsome | +0.009 |
free | +0.009 |
caring | +0.009 |
Neg logit contributions | |
stack | -0.009 |
ditch | -0.009 |
loft | -0.009 |
unks | -0.008 |
alk | -0.008 |
Token | put |
Token ID | 1234 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
caring | +0.001 |
listened | +0.001 |
Happy | +0.001 |
Neg logit contributions | |
unks | -0.004 |
ditch | -0.004 |
igs | -0.004 |
icer | -0.004 |
alk | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
sure | +0.002 |
disl | +0.002 |
happy | +0.002 |
Happy | +0.002 |
caring | +0.002 |
Neg logit contributions | |
unks | -0.007 |
ditch | -0.007 |
igs | -0.007 |
icer | -0.007 |
stack | -0.006 |
Token | pill |
Token ID | 9582 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
unks | +0.020 |
stack | +0.019 |
alk | +0.019 |
ditch | +0.018 |
igs | +0.018 |
Neg logit contributions | |
happy | -0.019 |
sure | -0.019 |
gr | -0.018 |
kind | -0.018 |
free | -0.018 |
Token | away |
Token ID | 1497 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
unks | +0.010 |
ditch | +0.010 |
igs | +0.009 |
stack | +0.009 |
loft | +0.009 |
Neg logit contributions | |
disl | -0.006 |
sure | -0.006 |
Happy | -0.006 |
caring | -0.006 |
happy | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
unks | +0.028 |
ditch | +0.028 |
igs | +0.027 |
stack | +0.027 |
alk | +0.027 |
Neg logit contributions | |
disl | -0.013 |
sure | -0.013 |
Happy | -0.012 |
caring | -0.012 |
handsome | -0.011 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
sure | +0.015 |
disl | +0.014 |
happy | +0.014 |
caring | +0.013 |
listening | +0.013 |
Neg logit contributions | |
ditch | -0.029 |
unks | -0.029 |
stack | -0.028 |
igs | -0.027 |
enclosure | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
disl | +0.003 |
free | +0.003 |
caring | +0.003 |
pleased | +0.003 |
listening | +0.003 |
Neg logit contributions | |
ditch | -0.006 |
unks | -0.006 |
igs | -0.006 |
icer | -0.006 |
ippy | -0.006 |
Token | look |
Token ID | 804 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
sure | +0.021 |
happy | +0.018 |
disl | +0.017 |
caring | +0.017 |
Happy | +0.017 |
Neg logit contributions | |
unks | -0.044 |
ditch | -0.043 |
igs | -0.042 |
icer | -0.041 |
alk | -0.040 |
Token | together |
Token ID | 1978 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
disl | +0.017 |
sure | +0.016 |
caring | +0.015 |
free | +0.015 |
Happy | +0.015 |
Neg logit contributions | |
ditch | -0.027 |
unks | -0.026 |
igs | -0.026 |
icer | -0.025 |
loft | -0.025 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.96e-03 |
Pos logit contributions | |
unks | +0.004 |
ditch | +0.004 |
igs | +0.003 |
loft | +0.003 |
alk | +0.003 |
Neg logit contributions | |
disl | -0.002 |
sure | -0.002 |
caring | -0.002 |
forg | -0.002 |
free | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
disl | +0.010 |
handsome | +0.010 |
nos | +0.009 |
sure | +0.009 |
caring | +0.009 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.013 |
stack | -0.013 |
enclosure | -0.012 |
alk | -0.012 |
Token | searched |
Token ID | 16499 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
sure | +0.007 |
happy | +0.007 |
listened | +0.006 |
excited | +0.006 |
forg | +0.006 |
Neg logit contributions | |
unks | -0.011 |
icer | -0.010 |
ditch | -0.010 |
igs | -0.010 |
alk | -0.010 |
Token | high |
Token ID | 1029 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
unks | +0.017 |
ifier | +0.017 |
ditch | +0.017 |
pel | +0.016 |
icer | +0.016 |
Neg logit contributions | |
happy | -0.007 |
sure | -0.006 |
excited | -0.006 |
if | -0.005 |
Happy | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
unks | +0.040 |
ditch | +0.040 |
igs | +0.038 |
alk | +0.038 |
icer | +0.038 |
Neg logit contributions | |
sure | -0.015 |
happy | -0.013 |
Happy | -0.012 |
excited | -0.012 |
listening | -0.012 |
Token | low |
Token ID | 1877 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
sure | +0.034 |
disl | +0.033 |
Happy | +0.032 |
caring | +0.031 |
happy | +0.031 |
Neg logit contributions | |
ditch | -0.034 |
unks | -0.034 |
igs | -0.033 |
stack | -0.031 |
icer | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ditch | +0.004 |
unks | +0.004 |
igs | +0.003 |
stack | +0.003 |
icer | +0.003 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
happy | -0.001 |
Happy | -0.001 |
caring | -0.001 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.08e-04 |
Pos logit contributions | |
sure | +0.037 |
disl | +0.036 |
Happy | +0.034 |
caring | +0.033 |
happy | +0.033 |
Neg logit contributions | |
ditch | -0.068 |
unks | -0.067 |
loft | -0.064 |
icer | -0.064 |
igs | -0.063 |
Token | 's |
Token ID | 338 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ditch | +0.000 |
unks | +0.000 |
igs | +0.000 |
icer | +0.000 |
ippy | +0.000 |
Neg logit contributions | |
free | -0.000 |
disl | -0.000 |
listening | -0.000 |
Happy | -0.000 |
caring | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
sure | +0.024 |
happy | +0.022 |
disl | +0.021 |
Happy | +0.021 |
caring | +0.021 |
Neg logit contributions | |
unks | -0.049 |
ditch | -0.048 |
igs | -0.047 |
icer | -0.045 |
alk | -0.045 |
Token | back |
Token ID | 736 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ditch | +0.009 |
unks | +0.009 |
igs | +0.009 |
icer | +0.008 |
alk | +0.008 |
Neg logit contributions | |
sure | -0.004 |
happy | -0.004 |
Happy | -0.003 |
free | -0.003 |
disl | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
unks | +0.045 |
ditch | +0.045 |
igs | +0.044 |
icer | +0.043 |
stack | +0.042 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.015 |
disl | -0.015 |
Happy | -0.015 |
caring | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -6.60e-04 |
Pos logit contributions | |
sure | +0.009 |
happy | +0.008 |
disl | +0.008 |
Happy | +0.008 |
caring | +0.008 |
Neg logit contributions | |
unks | -0.028 |
ditch | -0.027 |
igs | -0.027 |
icer | -0.026 |
alk | -0.026 |
Token | park |
Token ID | 3952 |
Feature activation | -3.61e-04 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
Happy | +0.001 |
disl | +0.001 |
caring | +0.001 |
Neg logit contributions | |
unks | -0.001 |
ditch | -0.001 |
igs | -0.001 |
alk | -0.001 |
icer | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
disl | +0.000 |
sure | +0.000 |
caring | +0.000 |
free | +0.000 |
handsome | +0.000 |
Neg logit contributions | |
enclosure | -0.001 |
ditch | -0.001 |
loft | -0.001 |
stack | -0.001 |
unks | -0.001 |
Token | look |
Token ID | 804 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
sure | +0.009 |
disl | +0.008 |
free | +0.008 |
caring | +0.008 |
Happy | +0.008 |
Neg logit contributions | |
ditch | -0.013 |
unks | -0.012 |
stack | -0.012 |
enclosure | -0.012 |
igs | -0.012 |
Token | ." |
Token ID | 526 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
disl | +0.034 |
good | +0.030 |
you | +0.030 |
beh | +0.030 |
caring | +0.029 |
Neg logit contributions | |
ditch | -0.039 |
igs | -0.039 |
unks | -0.037 |
trailer | -0.036 |
icer | -0.036 |
Token | go |
Token ID | 467 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
disl | +0.000 |
sure | +0.000 |
Happy | +0.000 |
caring | +0.000 |
happy | +0.000 |
Neg logit contributions | |
ditch | -0.000 |
unks | -0.000 |
alk | -0.000 |
igs | -0.000 |
stack | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
unks | +0.012 |
ditch | +0.012 |
igs | +0.012 |
icer | +0.011 |
alk | +0.011 |
Neg logit contributions | |
sure | -0.005 |
happy | -0.004 |
Happy | -0.004 |
free | -0.004 |
caring | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
unks | +0.044 |
icer | +0.043 |
stack | +0.042 |
ditch | +0.041 |
ool | +0.041 |
Neg logit contributions | |
sure | -0.011 |
happy | -0.009 |
Happy | -0.009 |
caring | -0.009 |
listening | -0.008 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
ditch | +0.011 |
unks | +0.011 |
igs | +0.011 |
alk | +0.011 |
loft | +0.010 |
Neg logit contributions | |
sure | -0.009 |
disl | -0.008 |
Happy | -0.008 |
happy | -0.008 |
free | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
unks | +0.003 |
ditch | +0.003 |
igs | +0.003 |
icer | +0.003 |
alk | +0.003 |
Neg logit contributions | |
sure | -0.001 |
happy | -0.001 |
disl | -0.001 |
Happy | -0.001 |
free | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
sure | +0.001 |
happy | +0.001 |
Happy | +0.001 |
excited | +0.000 |
if | +0.000 |
Neg logit contributions | |
unks | -0.005 |
igs | -0.005 |
ditch | -0.005 |
ses | -0.005 |
icer | -0.005 |
Token | woods |
Token ID | 16479 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
happy | +0.012 |
sure | +0.012 |
Happy | +0.011 |
kind | +0.011 |
nos | +0.011 |
Neg logit contributions | |
unks | -0.009 |
igs | -0.009 |
alk | -0.008 |
ditch | -0.008 |
ses | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
sure | +0.001 |
disl | +0.001 |
Happy | +0.001 |
caring | +0.001 |
happy | +0.001 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
igs | -0.003 |
stack | -0.003 |
alk | -0.003 |
Token | but |
Token ID | 475 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ditch | +0.010 |
unks | +0.010 |
stack | +0.009 |
enclosure | +0.009 |
loft | +0.009 |
Neg logit contributions | |
disl | -0.006 |
Happy | -0.006 |
free | -0.006 |
Happy | -0.006 |
sure | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -7.46e-03 |
Pos logit contributions | |
ditch | +0.027 |
stack | +0.026 |
unks | +0.026 |
igs | +0.025 |
loft | +0.025 |
Neg logit contributions | |
disl | -0.014 |
sure | -0.013 |
free | -0.013 |
Happy | -0.013 |
good | -0.012 |
Token | bear |
Token ID | 6842 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
sure | +0.011 |
happy | +0.010 |
disl | +0.010 |
Happy | +0.010 |
caring | +0.010 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.014 |
igs | -0.014 |
icer | -0.013 |
alk | -0.013 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
disl | +0.005 |
free | +0.005 |
sure | +0.005 |
handsome | +0.004 |
beh | +0.004 |
Neg logit contributions | |
ditch | -0.009 |
loft | -0.009 |
igs | -0.009 |
stack | -0.009 |
unks | -0.009 |
Token | arrived |
Token ID | 5284 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
unks | +0.016 |
ditch | +0.016 |
igs | +0.015 |
icer | +0.015 |
stack | +0.015 |
Neg logit contributions | |
sure | -0.007 |
disl | -0.006 |
happy | -0.006 |
Happy | -0.006 |
caring | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
disl | +0.016 |
sure | +0.016 |
free | +0.014 |
caring | +0.014 |
Happy | +0.014 |
Neg logit contributions | |
unks | -0.041 |
ditch | -0.041 |
igs | -0.040 |
loft | -0.039 |
stack | -0.038 |
Token | she |
Token ID | 673 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
disl | +0.029 |
beh | +0.024 |
minded | +0.024 |
free | +0.024 |
caring | +0.023 |
Neg logit contributions | |
loft | -0.039 |
ditch | -0.038 |
stack | -0.037 |
igs | -0.036 |
footing | -0.035 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
free | +0.005 |
disl | +0.005 |
sure | +0.005 |
caring | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
ditch | -0.008 |
unks | -0.008 |
igs | -0.008 |
icer | -0.008 |
enclosure | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
sure | +0.024 |
disl | +0.023 |
free | +0.023 |
Happy | +0.022 |
happy | +0.022 |
Neg logit contributions | |
unks | -0.044 |
ditch | -0.044 |
igs | -0.043 |
stack | -0.042 |
loft | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
disl | +0.058 |
free | +0.057 |
rav | +0.055 |
beh | +0.054 |
you | +0.052 |
Neg logit contributions | |
loft | -0.073 |
ditch | -0.070 |
stack | -0.067 |
igs | -0.065 |
cage | -0.063 |
Token | theater |
Token ID | 13766 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
disl | +0.025 |
beh | +0.024 |
caring | +0.023 |
sure | +0.023 |
forg | +0.023 |
Neg logit contributions | |
ditch | -0.016 |
unks | -0.015 |
icer | -0.015 |
enclosure | -0.015 |
loft | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
disl | +0.042 |
sure | +0.041 |
free | +0.040 |
caring | +0.039 |
beh | +0.037 |
Neg logit contributions | |
unks | -0.058 |
ditch | -0.058 |
stack | -0.057 |
loft | -0.057 |
enclosure | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ditch | +0.040 |
unks | +0.039 |
igs | +0.037 |
stack | +0.037 |
loft | +0.037 |
Neg logit contributions | |
sure | -0.022 |
disl | -0.022 |
Happy | -0.021 |
free | -0.020 |
happy | -0.020 |
Token | bit |
Token ID | 1643 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
sure | +0.022 |
disl | +0.021 |
you | +0.021 |
good | +0.020 |
beh | +0.020 |
Neg logit contributions | |
ditch | -0.033 |
loft | -0.030 |
unks | -0.029 |
icer | -0.029 |
funnel | -0.029 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
sure | +0.015 |
disl | +0.015 |
Happy | +0.014 |
free | +0.014 |
listening | +0.013 |
Neg logit contributions | |
ditch | -0.027 |
unks | -0.026 |
igs | -0.026 |
stack | -0.025 |
loft | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
sure | +0.015 |
happy | +0.013 |
caring | +0.013 |
Happy | +0.013 |
disl | +0.013 |
Neg logit contributions | |
unks | -0.027 |
ditch | -0.027 |
igs | -0.026 |
icer | -0.026 |
stack | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
unks | +0.064 |
ditch | +0.064 |
igs | +0.062 |
icer | +0.061 |
loft | +0.061 |
Neg logit contributions | |
sure | -0.019 |
happy | -0.017 |
disl | -0.016 |
Happy | -0.016 |
caring | -0.016 |
Token | story |
Token ID | 1621 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
disl | +0.004 |
free | +0.004 |
sure | +0.004 |
good | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
igs | -0.005 |
ditch | -0.005 |
alk | -0.005 |
unks | -0.005 |
loft | -0.005 |
Token | ? |
Token ID | 30 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
sure | +0.032 |
disl | +0.031 |
free | +0.030 |
handsome | +0.030 |
Happy | +0.030 |
Neg logit contributions | |
unks | -0.040 |
alk | -0.040 |
ditch | -0.039 |
igs | -0.039 |
stack | -0.038 |
Token | Comp |
Token ID | 3082 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
sure | +0.006 |
happy | +0.006 |
disl | +0.006 |
handsome | +0.006 |
caring | +0.005 |
Neg logit contributions | |
unks | -0.011 |
ditch | -0.011 |
igs | -0.010 |
alk | -0.010 |
stack | -0.010 |
Token | rom |
Token ID | 398 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
sure | +0.056 |
Happy | +0.054 |
happy | +0.053 |
listening | +0.051 |
nos | +0.050 |
Neg logit contributions | |
unks | -0.091 |
ditch | -0.089 |
alk | -0.088 |
igs | -0.088 |
icer | -0.084 |
Token | ise |
Token ID | 786 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
sure | +0.040 |
handsome | +0.039 |
Happy | +0.038 |
happy | +0.038 |
caring | +0.038 |
Neg logit contributions | |
unks | -0.040 |
alk | -0.038 |
ditch | -0.038 |
igs | -0.037 |
icer | -0.036 |
Token | is |
Token ID | 318 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
sure | +0.009 |
Happy | +0.009 |
handsome | +0.009 |
happy | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
unks | -0.015 |
alk | -0.015 |
igs | -0.015 |
ditch | -0.014 |
stack | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.45e-04 |
Pos logit contributions | |
disl | +0.005 |
Happy | +0.005 |
Happy | +0.005 |
free | +0.005 |
good | +0.005 |
Neg logit contributions | |
igs | -0.010 |
unks | -0.010 |
ditch | -0.009 |
stack | -0.009 |
alk | -0.009 |
Token | best |
Token ID | 1266 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ditch | +0.001 |
unks | +0.001 |
loft | +0.001 |
stack | +0.001 |
icer | +0.001 |
Neg logit contributions | |
disl | -0.001 |
sure | -0.001 |
Happy | -0.001 |
free | -0.001 |
Happy | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
disl | +0.016 |
Happy | +0.015 |
yes | +0.015 |
caring | +0.015 |
good | +0.014 |
Neg logit contributions | |
unks | -0.021 |
enclosure | -0.021 |
igs | -0.021 |
web | -0.020 |
cage | -0.020 |
Token | time |
Token ID | 640 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
disl | +0.002 |
Happy | +0.001 |
free | +0.001 |
sure | +0.001 |
Happy | +0.001 |
Neg logit contributions | |
ditch | -0.003 |
unks | -0.003 |
igs | -0.003 |
alk | -0.003 |
icer | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
unks | +0.011 |
alk | +0.011 |
ditch | +0.011 |
igs | +0.011 |
stack | +0.010 |
Neg logit contributions | |
disl | -0.007 |
forg | -0.006 |
caring | -0.006 |
good | -0.006 |
sure | -0.006 |
Token | dance |
Token ID | 9280 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
sure | +0.007 |
disl | +0.007 |
happy | +0.007 |
Happy | +0.007 |
free | +0.007 |
Neg logit contributions | |
unks | -0.014 |
ditch | -0.014 |
igs | -0.013 |
alk | -0.013 |
icer | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
disl | +0.012 |
sure | +0.012 |
caring | +0.011 |
listening | +0.011 |
forg | +0.011 |
Neg logit contributions | |
unks | -0.022 |
ditch | -0.022 |
igs | -0.021 |
alk | -0.021 |
stack | -0.020 |
Token | That |
Token ID | 1320 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
ditch | +0.003 |
unks | +0.003 |
alk | +0.003 |
stack | +0.003 |
igs | +0.003 |
Neg logit contributions | |
sure | -0.002 |
caring | -0.002 |
happy | -0.002 |
handsome | -0.002 |
disl | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
disl | +0.054 |
free | +0.053 |
you | +0.047 |
caring | +0.046 |
beh | +0.046 |
Neg logit contributions | |
ditch | -0.086 |
icer | -0.081 |
loft | -0.080 |
alk | -0.080 |
unks | -0.080 |
Token | her |
Token ID | 607 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
igs | +0.022 |
unks | +0.021 |
ditch | +0.021 |
icer | +0.020 |
alk | +0.020 |
Neg logit contributions | |
disl | -0.012 |
free | -0.011 |
handsome | -0.010 |
nos | -0.010 |
good | -0.010 |
Token | feel |
Token ID | 1254 |
Feature activation | -6.21e-04 |
Pos logit contributions | |
disl | +0.034 |
Happy | +0.032 |
free | +0.032 |
you | +0.030 |
Happy | +0.030 |
Neg logit contributions | |
ditch | -0.048 |
unks | -0.046 |
ses | -0.046 |
alk | -0.045 |
igs | -0.045 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
disl | +0.001 |
rav | +0.001 |
Happy | +0.001 |
good | +0.001 |
you | +0.001 |
Neg logit contributions | |
ditch | -0.001 |
igs | -0.001 |
alk | -0.001 |
unks | -0.001 |
dam | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
disl | +0.014 |
beh | +0.013 |
Happy | +0.013 |
free | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
ditch | -0.019 |
alk | -0.019 |
igs | -0.018 |
web | -0.018 |
unks | -0.018 |
Token | proudly |
Token ID | 23017 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
disl | +0.008 |
free | +0.008 |
sure | +0.007 |
Happy | +0.007 |
you | +0.007 |
Neg logit contributions | |
ditch | -0.017 |
unks | -0.016 |
enclosure | -0.016 |
igs | -0.016 |
stack | -0.016 |
Token | strut |
Token ID | 30577 |
Feature activation | +7.00e-04 |
Pos logit contributions | |
unks | +0.047 |
ditch | +0.046 |
enclosure | +0.046 |
alk | +0.044 |
igs | +0.043 |
Neg logit contributions | |
free | -0.032 |
you | -0.030 |
sure | -0.029 |
disl | -0.029 |
caring | -0.029 |
Token | ted |
Token ID | 1513 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
ditch | +0.001 |
unks | +0.001 |
icer | +0.001 |
igs | +0.001 |
enclosure | +0.001 |
Neg logit contributions | |
sure | -0.001 |
disl | -0.001 |
caring | -0.001 |
happy | -0.001 |
listening | -0.001 |
Token | around |
Token ID | 1088 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ditch | +0.005 |
unks | +0.005 |
stack | +0.005 |
alk | +0.005 |
loft | +0.005 |
Neg logit contributions | |
disl | -0.003 |
sure | -0.003 |
caring | -0.003 |
handsome | -0.003 |
talented | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
disl | +0.020 |
beh | +0.018 |
sure | +0.018 |
caring | +0.018 |
handsome | +0.018 |
Neg logit contributions | |
ditch | -0.033 |
stack | -0.032 |
unks | -0.032 |
enclosure | -0.031 |
alk | -0.031 |
Token | festival |
Token ID | 10876 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
sure | +0.015 |
disl | +0.015 |
caring | +0.014 |
free | +0.014 |
forg | +0.013 |
Neg logit contributions | |
ditch | -0.012 |
unks | -0.011 |
loft | -0.011 |
icer | -0.011 |
enclosure | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
disl | +0.059 |
sure | +0.052 |
caring | +0.052 |
beh | +0.050 |
handsome | +0.049 |
Neg logit contributions | |
stack | -0.085 |
enclosure | -0.085 |
ditch | -0.084 |
unks | -0.080 |
loft | -0.080 |
Token | making |
Token ID | 1642 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
Happy | +0.007 |
disl | +0.007 |
beh | +0.007 |
sure | +0.007 |
free | +0.007 |
Neg logit contributions | |
ditch | -0.011 |
stack | -0.011 |
unks | -0.010 |
enclosure | -0.010 |
loft | -0.010 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
disl | +0.010 |
Acc | +0.010 |
free | +0.010 |
rav | +0.009 |
Of | +0.009 |
Neg logit contributions | |
ditch | -0.017 |
igs | -0.017 |
poles | -0.016 |
unks | -0.016 |
sticks | -0.015 |
Token | gasp |
Token ID | 47440 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
minded | +0.037 |
Good | +0.035 |
disl | +0.034 |
Happy | +0.033 |
Sorry | +0.033 |
Neg logit contributions | |
enclosure | -0.043 |
cage | -0.041 |
ditch | -0.041 |
web | -0.037 |
alk | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
disl | +0.012 |
Of | +0.011 |
beh | +0.010 |
Sorry | +0.010 |
caring | +0.010 |
Neg logit contributions | |
ditch | -0.012 |
unks | -0.012 |
ifier | -0.011 |
igs | -0.011 |
icer | -0.011 |
Token | got |
Token ID | 1392 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
unks | +0.066 |
ditch | +0.065 |
igs | +0.063 |
icer | +0.062 |
alk | +0.061 |
Neg logit contributions | |
sure | -0.029 |
happy | -0.026 |
disl | -0.025 |
Happy | -0.025 |
caring | -0.025 |
Token | closer |
Token ID | 5699 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
sure | +0.004 |
happy | +0.004 |
nos | +0.003 |
Happy | +0.003 |
excited | +0.003 |
Neg logit contributions | |
unks | -0.010 |
ditch | -0.010 |
igs | -0.010 |
icer | -0.010 |
alk | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
disl | +0.019 |
sure | +0.018 |
caring | +0.017 |
free | +0.017 |
Happy | +0.017 |
Neg logit contributions | |
unks | -0.035 |
ditch | -0.034 |
igs | -0.034 |
stack | -0.033 |
alk | -0.033 |
Token | he |
Token ID | 339 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
disl | +0.035 |
beh | +0.031 |
good | +0.030 |
caring | +0.029 |
free | +0.029 |
Neg logit contributions | |
ditch | -0.047 |
unks | -0.045 |
loft | -0.044 |
igs | -0.043 |
icer | -0.043 |
Token | realised |
Token ID | 19169 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
unks | +0.013 |
ditch | +0.013 |
igs | +0.013 |
icer | +0.012 |
stack | +0.012 |
Neg logit contributions | |
sure | -0.007 |
disl | -0.007 |
happy | -0.007 |
Happy | -0.007 |
free | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
free | +0.017 |
disl | +0.016 |
Happy | +0.016 |
Happy | +0.016 |
good | +0.016 |
Neg logit contributions | |
ditch | -0.031 |
unks | -0.031 |
igs | -0.031 |
stack | -0.029 |
loft | -0.029 |
Token | what |
Token ID | 644 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
free | +0.050 |
disl | +0.047 |
Happy | +0.046 |
good | +0.046 |
rav | +0.045 |
Neg logit contributions | |
ditch | -0.077 |
unks | -0.074 |
igs | -0.072 |
stack | -0.072 |
loft | -0.071 |
Token | he |
Token ID | 339 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
free | +0.036 |
disl | +0.031 |
good | +0.031 |
you | +0.031 |
sure | +0.031 |
Neg logit contributions | |
ditch | -0.054 |
unks | -0.053 |
alk | -0.053 |
igs | -0.052 |
hook | -0.049 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.23e-04 |
Pos logit contributions | |
ditch | +0.046 |
unks | +0.046 |
igs | +0.045 |
stack | +0.044 |
alk | +0.043 |
Neg logit contributions | |
sure | -0.017 |
happy | -0.015 |
disl | -0.014 |
Happy | -0.014 |
nos | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
sure | +0.000 |
disl | +0.000 |
happy | +0.000 |
caring | +0.000 |
Happy | +0.000 |
Neg logit contributions | |
unks | -0.001 |
ditch | -0.001 |
igs | -0.001 |
icer | -0.001 |
stack | -0.001 |
Token | an |
Token ID | 281 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
unks | +0.029 |
ditch | +0.029 |
stack | +0.028 |
alk | +0.027 |
igs | +0.027 |
Neg logit contributions | |
sure | -0.016 |
disl | -0.015 |
Happy | -0.015 |
Happy | -0.015 |
free | -0.015 |