Token | and |
Token ID | 290 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
Woo | +0.036 |
wagon | +0.034 |
leash | +0.034 |
lamb | +0.033 |
sled | +0.031 |
Neg logit contributions | |
ways | -0.066 |
vals | -0.062 |
ad | -0.062 |
ven | -0.060 |
od | -0.059 |
Token | cried |
Token ID | 16896 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
wagon | +0.044 |
Woo | +0.044 |
leash | +0.043 |
yacht | +0.043 |
lamb | +0.042 |
Neg logit contributions | |
ways | -0.057 |
ad | -0.054 |
arom | -0.049 |
od | -0.049 |
mastered | -0.048 |
Token | sadly |
Token ID | 21098 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Woo | +0.046 |
wagon | +0.044 |
leash | +0.043 |
lamb | +0.043 |
puppy | +0.041 |
Neg logit contributions | |
ways | -0.058 |
vals | -0.058 |
ad | -0.055 |
ven | -0.055 |
mastered | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
leash | +0.030 |
wagon | +0.030 |
Woo | +0.030 |
lamb | +0.029 |
yacht | +0.029 |
Neg logit contributions | |
ways | -0.026 |
ad | -0.024 |
vals | -0.023 |
ven | -0.023 |
od | -0.023 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Woo | +0.027 |
wagon | +0.026 |
lamb | +0.025 |
mole | +0.025 |
leash | +0.025 |
Neg logit contributions | |
ways | -0.034 |
ad | -0.033 |
vals | -0.032 |
br | -0.031 |
ven | -0.031 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
Woo | +0.016 |
Drop | +0.014 |
yacht | +0.014 |
drown | +0.014 |
Spot | +0.014 |
Neg logit contributions | |
ad | -0.023 |
ways | -0.022 |
agg | -0.021 |
arom | -0.021 |
mastered | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
Woo | +0.079 |
wagon | +0.078 |
leash | +0.077 |
lamb | +0.076 |
yacht | +0.075 |
Neg logit contributions | |
ways | -0.150 |
ad | -0.141 |
vals | -0.133 |
od | -0.132 |
ven | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
wagon | +0.025 |
Woo | +0.025 |
yacht | +0.024 |
leash | +0.024 |
lamb | +0.024 |
Neg logit contributions | |
ways | -0.031 |
ad | -0.030 |
mastered | -0.027 |
od | -0.026 |
arom | -0.026 |
Token | reminder |
Token ID | 15438 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Woo | +0.058 |
wagon | +0.055 |
yacht | +0.054 |
lamb | +0.053 |
sled | +0.053 |
Neg logit contributions | |
ways | -0.066 |
br | -0.062 |
ad | -0.062 |
arom | -0.060 |
mastered | -0.060 |
Token | of |
Token ID | 286 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
ways | +0.033 |
vals | +0.030 |
ad | +0.029 |
arom | +0.029 |
ven | +0.029 |
Neg logit contributions | |
Woo | -0.018 |
leash | -0.018 |
wagon | -0.018 |
lamb | -0.018 |
mole | -0.017 |
Token | how |
Token ID | 703 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Woo | +0.008 |
wagon | +0.008 |
mole | +0.008 |
lamb | +0.008 |
leash | +0.008 |
Neg logit contributions | |
ways | -0.011 |
ad | -0.010 |
vals | -0.010 |
br | -0.009 |
ven | -0.009 |
Token | crying |
Token ID | 13774 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
ways | +0.042 |
ad | +0.040 |
vals | +0.038 |
arom | +0.037 |
od | +0.037 |
Neg logit contributions | |
Woo | -0.024 |
wagon | -0.024 |
leash | -0.023 |
yacht | -0.023 |
sled | -0.022 |
Token | because |
Token ID | 780 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
wagon | +0.100 |
sled | +0.097 |
lamb | +0.097 |
paddle | +0.097 |
leash | +0.097 |
Neg logit contributions | |
ways | -0.076 |
ad | -0.074 |
od | -0.064 |
arom | -0.063 |
mastered | -0.062 |
Token | she |
Token ID | 673 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
leash | +0.036 |
wagon | +0.035 |
Woo | +0.035 |
paddle | +0.034 |
lamb | +0.034 |
Neg logit contributions | |
ways | -0.039 |
ad | -0.038 |
od | -0.033 |
arom | -0.033 |
mastered | -0.033 |
Token | lost |
Token ID | 2626 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
Woo | +0.010 |
wagon | +0.009 |
leash | +0.009 |
lamb | +0.009 |
yacht | +0.009 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.012 |
vals | -0.011 |
od | -0.011 |
ven | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Woo | +0.090 |
wagon | +0.089 |
leash | +0.088 |
yacht | +0.088 |
lamb | +0.088 |
Neg logit contributions | |
ways | -0.071 |
ad | -0.068 |
arom | -0.059 |
shades | -0.059 |
od | -0.058 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Woo | +0.024 |
Drop | +0.022 |
paddle | +0.022 |
Spot | +0.021 |
lamb | +0.020 |
Neg logit contributions | |
ways | -0.031 |
ad | -0.031 |
shades | -0.029 |
powers | -0.029 |
arom | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
Woo | +0.133 |
paddle | +0.130 |
drown | +0.129 |
Spot | +0.127 |
lamb | +0.127 |
Neg logit contributions | |
ways | -0.084 |
ad | -0.077 |
br | -0.068 |
od | -0.066 |
shades | -0.063 |
Token | The |
Token ID | 383 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Woo | +0.022 |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
ways | -0.029 |
ad | -0.027 |
vals | -0.025 |
od | -0.025 |
ven | -0.025 |
Token | cat |
Token ID | 3797 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
Woo | +0.013 |
paddle | +0.011 |
drown | +0.011 |
sled | +0.011 |
Drop | +0.011 |
Neg logit contributions | |
ad | -0.019 |
ways | -0.017 |
arom | -0.017 |
equations | -0.016 |
symbols | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
Woo | +0.058 |
leash | +0.056 |
wagon | +0.056 |
yacht | +0.056 |
lamb | +0.055 |
Neg logit contributions | |
ways | -0.052 |
ad | -0.049 |
mastered | -0.043 |
od | -0.043 |
ven | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
Woo | +0.048 |
leash | +0.044 |
wagon | +0.044 |
lamb | +0.043 |
dog | +0.043 |
Neg logit contributions | |
ways | -0.087 |
vals | -0.080 |
ad | -0.078 |
od | -0.078 |
ven | -0.078 |
Token | He |
Token ID | 679 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Woo | +0.010 |
wagon | +0.010 |
leash | +0.010 |
mole | +0.009 |
yacht | +0.009 |
Neg logit contributions | |
ways | -0.018 |
ad | -0.017 |
vals | -0.017 |
arom | -0.016 |
od | -0.016 |
Token | cried |
Token ID | 16896 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
Woo | +0.028 |
leash | +0.027 |
wagon | +0.027 |
lamb | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.033 |
ad | -0.031 |
mastered | -0.028 |
ven | -0.028 |
od | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Woo | +0.044 |
wagon | +0.044 |
leash | +0.043 |
lamb | +0.041 |
sled | +0.041 |
Neg logit contributions | |
ways | -0.070 |
ad | -0.066 |
vals | -0.064 |
ven | -0.062 |
od | -0.062 |
Token | hugged |
Token ID | 41130 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
wagon | +0.040 |
lamb | +0.039 |
leash | +0.039 |
Woo | +0.038 |
yacht | +0.038 |
Neg logit contributions | |
ways | -0.047 |
ad | -0.045 |
arom | -0.041 |
mastered | -0.040 |
ven | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
Woo | +0.056 |
wagon | +0.055 |
leash | +0.054 |
lamb | +0.054 |
yacht | +0.053 |
Neg logit contributions | |
ways | -0.099 |
ad | -0.094 |
od | -0.087 |
arom | -0.086 |
vals | -0.086 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Woo | +0.047 |
Drop | +0.040 |
Spot | +0.039 |
drown | +0.038 |
Leave | +0.038 |
Neg logit contributions | |
ad | -0.065 |
arom | -0.062 |
ways | -0.062 |
shades | -0.061 |
br | -0.061 |
Token | plane |
Token ID | 6614 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Woo | +0.070 |
Spot | +0.062 |
drown | +0.060 |
lamb | +0.059 |
mole | +0.058 |
Neg logit contributions | |
ways | -0.152 |
ad | -0.144 |
br | -0.135 |
od | -0.134 |
arom | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
Woo | +0.054 |
wagon | +0.053 |
lamb | +0.053 |
leash | +0.053 |
yacht | +0.052 |
Neg logit contributions | |
ways | -0.035 |
ad | -0.032 |
od | -0.028 |
vals | -0.028 |
ven | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Woo | +0.023 |
wagon | +0.022 |
lamb | +0.022 |
leash | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
ways | -0.034 |
ad | -0.032 |
od | -0.030 |
vals | -0.030 |
ven | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
lamb | +0.032 |
yacht | +0.032 |
wagon | +0.032 |
Woo | +0.030 |
leash | +0.030 |
Neg logit contributions | |
ad | -0.028 |
ways | -0.028 |
agg | -0.024 |
od | -0.024 |
ven | -0.023 |
Token | His |
Token ID | 6653 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
lamb | +0.011 |
Woo | +0.011 |
yacht | +0.011 |
wagon | +0.011 |
bicycle | +0.010 |
Neg logit contributions | |
ways | -0.013 |
ad | -0.013 |
vals | -0.011 |
ven | -0.011 |
br | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
ways | +0.016 |
vals | +0.014 |
ad | +0.014 |
equations | +0.014 |
ven | +0.014 |
Neg logit contributions | |
paddle | -0.010 |
yacht | -0.010 |
leash | -0.009 |
Woo | -0.009 |
wagon | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.012 |
vals | +0.012 |
ven | +0.012 |
equations | +0.012 |
Neg logit contributions | |
leash | -0.014 |
wagon | -0.014 |
Woo | -0.014 |
yacht | -0.014 |
paddle | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.016 |
od | +0.016 |
br | +0.015 |
ven | +0.015 |
Neg logit contributions | |
wagon | -0.017 |
leash | -0.017 |
lamb | -0.016 |
Woo | -0.016 |
yacht | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -6.78e-03 |
Pos logit contributions | |
ways | +0.009 |
ad | +0.009 |
od | +0.008 |
br | +0.008 |
ven | +0.008 |
Neg logit contributions | |
wagon | -0.008 |
lamb | -0.008 |
leash | -0.007 |
Woo | -0.007 |
yacht | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +4.04e-04 |
Pos logit contributions | |
ways | +0.011 |
ad | +0.010 |
vals | +0.010 |
ven | +0.010 |
od | +0.009 |
Neg logit contributions | |
wagon | -0.011 |
Woo | -0.011 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
Token | rh |
Token ID | 9529 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
Woo | +0.000 |
wagon | +0.000 |
leash | +0.000 |
lamb | +0.000 |
raft | +0.000 |
Neg logit contributions | |
ad | -0.001 |
ways | -0.001 |
arom | -0.001 |
br | -0.001 |
vals | -0.001 |
Token | in |
Token ID | 259 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
Woo | +0.104 |
wagon | +0.098 |
leash | +0.096 |
lamb | +0.093 |
raft | +0.091 |
Neg logit contributions | |
ad | -0.127 |
ways | -0.124 |
od | -0.116 |
br | -0.115 |
vals | -0.113 |
Token | oc |
Token ID | 420 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
Woo | +0.037 |
wagon | +0.034 |
leash | +0.034 |
lamb | +0.033 |
yacht | +0.032 |
Neg logit contributions | |
ways | -0.093 |
ad | -0.091 |
vals | -0.085 |
od | -0.084 |
ven | -0.084 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
Woo | +0.001 |
wagon | +0.001 |
leash | +0.001 |
lamb | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.002 |
vals | -0.002 |
od | -0.002 |
ven | -0.002 |
Token | nodded |
Token ID | 14464 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
yacht | +0.036 |
duck | +0.036 |
wagon | +0.036 |
dog | +0.036 |
mole | +0.036 |
Neg logit contributions | |
ways | -0.048 |
ad | -0.043 |
vals | -0.043 |
od | -0.041 |
agg | -0.040 |
Token | its |
Token ID | 663 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
wagon | +0.019 |
Woo | +0.019 |
leash | +0.019 |
lamb | +0.018 |
yacht | +0.018 |
Neg logit contributions | |
ways | -0.020 |
ad | -0.018 |
vals | -0.018 |
ven | -0.017 |
od | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
wagon | +0.047 |
lamb | +0.046 |
yacht | +0.046 |
raft | +0.045 |
leash | +0.044 |
Neg logit contributions | |
ways | -0.050 |
ad | -0.045 |
od | -0.043 |
agg | -0.041 |
books | -0.041 |
Token | L |
Token ID | 43 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
sled | +0.021 |
wagon | +0.021 |
paddle | +0.021 |
lamb | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
ways | -0.023 |
ad | -0.020 |
br | -0.019 |
ven | -0.019 |
od | -0.019 |
Token | ily |
Token ID | 813 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.012 |
vals | +0.011 |
ven | +0.010 |
arom | +0.010 |
Neg logit contributions | |
Woo | -0.017 |
wagon | -0.017 |
leash | -0.017 |
lamb | -0.017 |
yacht | -0.017 |
Token | drove |
Token ID | 10357 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
Woo | +0.016 |
wagon | +0.016 |
leash | +0.016 |
lamb | +0.016 |
yacht | +0.016 |
Neg logit contributions | |
ways | -0.018 |
ad | -0.017 |
od | -0.015 |
mastered | -0.015 |
ven | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
wagon | +0.082 |
Woo | +0.082 |
lamb | +0.081 |
yacht | +0.080 |
mole | +0.079 |
Neg logit contributions | |
ways | -0.107 |
ad | -0.099 |
od | -0.090 |
mastered | -0.090 |
ven | -0.089 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Drop | +0.035 |
Woo | +0.035 |
Drop | +0.032 |
lamb | +0.031 |
mole | +0.031 |
Neg logit contributions | |
ways | -0.034 |
powers | -0.032 |
ad | -0.032 |
br | -0.032 |
shades | -0.030 |
Token | car |
Token ID | 1097 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
drown | +0.069 |
lamb | +0.068 |
Woo | +0.067 |
paddle | +0.065 |
mole | +0.065 |
Neg logit contributions | |
ways | -0.150 |
ad | -0.139 |
br | -0.130 |
equations | -0.124 |
mastered | -0.124 |
Token | around |
Token ID | 1088 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
lamb | +0.044 |
Woo | +0.044 |
wagon | +0.042 |
mole | +0.042 |
yacht | +0.041 |
Neg logit contributions | |
ways | -0.061 |
ad | -0.055 |
ven | -0.051 |
mastered | -0.051 |
od | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
Woo | +0.032 |
wagon | +0.031 |
leash | +0.030 |
dog | +0.030 |
lamb | +0.030 |
Neg logit contributions | |
ways | -0.048 |
vals | -0.045 |
ad | -0.044 |
ven | -0.043 |
br | -0.042 |
Token | park |
Token ID | 3952 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
ways | +0.004 |
ad | +0.003 |
shades | +0.003 |
mastered | +0.003 |
br | +0.003 |
Neg logit contributions | |
lamb | -0.004 |
Woo | -0.004 |
mole | -0.004 |
drown | -0.004 |
reins | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
leash | +0.011 |
wagon | +0.011 |
Woo | +0.011 |
dog | +0.011 |
yacht | +0.011 |
Neg logit contributions | |
ad | -0.013 |
vals | -0.013 |
ways | -0.013 |
agg | -0.013 |
br | -0.012 |
Token | me |
Token ID | 502 |
Feature activation | +9.00e-04 |
Pos logit contributions | |
Woo | +0.025 |
wagon | +0.025 |
leash | +0.024 |
lamb | +0.024 |
yacht | +0.024 |
Neg logit contributions | |
ways | -0.031 |
ad | -0.029 |
vals | -0.027 |
od | -0.027 |
ven | -0.026 |
Token | ." |
Token ID | 526 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.001 |
sled | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
vals | -0.001 |
arom | -0.001 |
od | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.016 |
vals | +0.016 |
od | +0.015 |
arom | +0.015 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.009 |
leash | -0.009 |
lamb | -0.009 |
yacht | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
wagon | +0.003 |
yacht | +0.003 |
Woo | +0.003 |
lamb | +0.003 |
leash | +0.003 |
Neg logit contributions | |
ways | -0.005 |
ad | -0.005 |
od | -0.004 |
agg | -0.004 |
ven | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
ways | +0.006 |
ad | +0.006 |
od | +0.006 |
ven | +0.006 |
vals | +0.006 |
Neg logit contributions | |
wagon | -0.004 |
Woo | -0.004 |
yacht | -0.004 |
lamb | -0.004 |
leash | -0.004 |
Token | rh |
Token ID | 9529 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.017 |
od | +0.016 |
vals | +0.016 |
arom | +0.016 |
Neg logit contributions | |
Woo | -0.009 |
wagon | -0.009 |
leash | -0.009 |
lamb | -0.008 |
yacht | -0.008 |
Token | in |
Token ID | 259 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Woo | +0.092 |
wagon | +0.089 |
leash | +0.087 |
lamb | +0.085 |
raft | +0.082 |
Neg logit contributions | |
ways | -0.135 |
ad | -0.132 |
od | -0.124 |
vals | -0.120 |
ven | -0.120 |
Token | oc |
Token ID | 420 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
wagon | +0.021 |
leash | +0.020 |
Woo | +0.019 |
yacht | +0.019 |
lamb | +0.019 |
Neg logit contributions | |
ways | -0.092 |
ad | -0.087 |
vals | -0.083 |
od | -0.083 |
arom | -0.082 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Woo | +0.006 |
wagon | +0.006 |
leash | +0.006 |
yacht | +0.006 |
lamb | +0.006 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
vals | -0.013 |
od | -0.013 |
ven | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
dog | +0.025 |
wagon | +0.025 |
duck | +0.025 |
mole | +0.025 |
yacht | +0.024 |
Neg logit contributions | |
ways | -0.041 |
vals | -0.038 |
ad | -0.037 |
arom | -0.036 |
br | -0.035 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Woo | +0.014 |
leash | +0.014 |
wagon | +0.014 |
lamb | +0.013 |
sled | +0.013 |
Neg logit contributions | |
ways | -0.022 |
ad | -0.020 |
vals | -0.019 |
od | -0.019 |
arom | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
Woo | +0.032 |
wagon | +0.032 |
leash | +0.031 |
yacht | +0.031 |
lamb | +0.031 |
Neg logit contributions | |
ways | -0.050 |
ad | -0.047 |
od | -0.043 |
mastered | -0.043 |
ven | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
Woo | +0.008 |
wagon | +0.007 |
lamb | +0.007 |
leash | +0.007 |
mole | +0.007 |
Neg logit contributions | |
ways | -0.011 |
ad | -0.010 |
vals | -0.010 |
arom | -0.010 |
ven | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
mastered | +0.003 |
od | +0.003 |
ven | +0.003 |
Neg logit contributions | |
Woo | -0.003 |
wagon | -0.003 |
leash | -0.003 |
yacht | -0.003 |
lamb | -0.003 |
Token | hurt |
Token ID | 5938 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Woo | +0.023 |
leash | +0.022 |
dog | +0.020 |
wagon | +0.020 |
Spot | +0.020 |
Neg logit contributions | |
ways | -0.033 |
vals | -0.031 |
arom | -0.030 |
od | -0.030 |
ami | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Woo | +0.051 |
leash | +0.049 |
wagon | +0.049 |
lamb | +0.049 |
mole | +0.048 |
Neg logit contributions | |
ways | -0.057 |
vals | -0.052 |
ad | -0.052 |
ven | -0.050 |
od | -0.050 |
Token | loyal |
Token ID | 9112 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
Woo | +0.078 |
yacht | +0.072 |
wagon | +0.071 |
Spot | +0.070 |
Drop | +0.070 |
Neg logit contributions | |
ways | -0.073 |
br | -0.073 |
ad | -0.072 |
mastered | -0.069 |
arom | -0.068 |
Token | animal |
Token ID | 5044 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
Woo | +0.070 |
yacht | +0.067 |
wagon | +0.065 |
Spot | +0.064 |
drown | +0.063 |
Neg logit contributions | |
ad | -0.137 |
ways | -0.135 |
mastered | -0.124 |
arom | -0.123 |
br | -0.121 |
Token | who |
Token ID | 508 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Woo | +0.046 |
wagon | +0.044 |
yacht | +0.043 |
lamb | +0.043 |
paddle | +0.042 |
Neg logit contributions | |
ways | -0.056 |
ad | -0.053 |
od | -0.048 |
mastered | -0.048 |
br | -0.048 |
Token | didn |
Token ID | 1422 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
Woo | +0.067 |
wagon | +0.066 |
lamb | +0.065 |
leash | +0.065 |
yacht | +0.064 |
Neg logit contributions | |
ways | -0.097 |
ad | -0.091 |
vals | -0.086 |
arom | -0.085 |
od | -0.085 |
Token | 't |
Token ID | 470 |
Feature activation | -6.28e-04 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.015 |
arom | +0.015 |
vals | +0.015 |
agg | +0.015 |
Neg logit contributions | |
Woo | -0.013 |
wagon | -0.012 |
leash | -0.012 |
sled | -0.012 |
yacht | -0.012 |
Token | deserve |
Token ID | 10925 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
ways | +0.001 |
ad | +0.001 |
vals | +0.001 |
od | +0.001 |
ven | +0.001 |
Neg logit contributions | |
Woo | -0.001 |
leash | -0.001 |
wagon | -0.001 |
lamb | -0.001 |
yacht | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
ways | +0.007 |
ad | +0.007 |
od | +0.007 |
mastered | +0.006 |
arom | +0.006 |
Neg logit contributions | |
wagon | -0.003 |
Woo | -0.003 |
leash | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -6.10e-03 |
Pos logit contributions | |
Woo | +0.012 |
dog | +0.012 |
wagon | +0.012 |
leash | +0.012 |
mole | +0.011 |
Neg logit contributions | |
ways | -0.014 |
vals | -0.013 |
ad | -0.013 |
ven | -0.013 |
agg | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
ways | +0.012 |
ad | +0.011 |
vals | +0.011 |
arom | +0.011 |
ven | +0.011 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.007 |
mole | -0.007 |
dog | -0.007 |
leash | -0.007 |
Token | hugged |
Token ID | 41130 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ways | +0.016 |
ad | +0.015 |
vals | +0.014 |
od | +0.014 |
ven | +0.014 |
Neg logit contributions | |
Woo | -0.011 |
wagon | -0.011 |
leash | -0.011 |
lamb | -0.011 |
yacht | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Woo | +0.065 |
wagon | +0.064 |
leash | +0.064 |
lamb | +0.063 |
yacht | +0.062 |
Neg logit contributions | |
ways | -0.068 |
ad | -0.063 |
vals | -0.059 |
od | -0.058 |
ven | -0.058 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
Woo | +0.027 |
yacht | +0.025 |
lamb | +0.025 |
drown | +0.025 |
paddle | +0.024 |
Neg logit contributions | |
ways | -0.049 |
ad | -0.048 |
shades | -0.045 |
arom | -0.045 |
mastered | -0.045 |
Token | cat |
Token ID | 3797 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Woo | +0.067 |
wagon | +0.065 |
leash | +0.064 |
lamb | +0.063 |
yacht | +0.062 |
Neg logit contributions | |
ways | -0.157 |
ad | -0.150 |
od | -0.140 |
vals | -0.140 |
ven | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
wagon | +0.021 |
leash | +0.021 |
dog | +0.021 |
puppy | +0.021 |
Woo | +0.021 |
Neg logit contributions | |
ways | -0.053 |
vals | -0.050 |
ad | -0.049 |
agg | -0.048 |
ven | -0.048 |
Token | said |
Token ID | 531 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Woo | +0.036 |
wagon | +0.036 |
leash | +0.035 |
lamb | +0.035 |
yacht | +0.035 |
Neg logit contributions | |
ways | -0.040 |
ad | -0.038 |
od | -0.034 |
vals | -0.034 |
mastered | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
ways | +0.028 |
ad | +0.026 |
vals | +0.025 |
ami | +0.025 |
shades | +0.024 |
Neg logit contributions | |
Woo | -0.024 |
yacht | -0.023 |
wagon | -0.023 |
mole | -0.022 |
dog | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
wagon | +0.003 |
Woo | +0.003 |
leash | +0.003 |
lamb | +0.003 |
yacht | +0.003 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
od | -0.003 |
ven | -0.003 |
arom | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
wagon | +0.017 |
Woo | +0.017 |
sled | +0.017 |
leash | +0.017 |
yacht | +0.016 |
Neg logit contributions | |
ways | -0.028 |
vals | -0.026 |
ad | -0.026 |
arom | -0.026 |
od | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
sled | +0.010 |
wagon | +0.010 |
Woo | +0.010 |
leash | +0.010 |
yacht | +0.010 |
Neg logit contributions | |
ways | -0.019 |
vals | -0.018 |
ven | -0.017 |
br | -0.017 |
bows | -0.017 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Woo | +0.015 |
wagon | +0.015 |
leash | +0.015 |
lamb | +0.015 |
yacht | +0.015 |
Neg logit contributions | |
ways | -0.026 |
ad | -0.025 |
od | -0.023 |
vals | -0.023 |
ven | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
Woo | +0.014 |
wagon | +0.014 |
leash | +0.014 |
lamb | +0.014 |
yacht | +0.013 |
Neg logit contributions | |
ways | -0.021 |
ad | -0.020 |
vals | -0.019 |
od | -0.018 |
arom | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
Woo | +0.032 |
wagon | +0.032 |
lamb | +0.031 |
yacht | +0.031 |
leash | +0.031 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.042 |
mastered | -0.038 |
od | -0.038 |
arom | -0.038 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
Woo | +0.044 |
lamb | +0.040 |
drown | +0.036 |
Drop | +0.036 |
Spot | +0.036 |
Neg logit contributions | |
ad | -0.070 |
ways | -0.069 |
symbols | -0.063 |
shades | -0.063 |
od | -0.062 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
Woo | +0.074 |
leash | +0.067 |
lamb | +0.067 |
wagon | +0.061 |
Spot | +0.061 |
Neg logit contributions | |
ways | -0.152 |
ad | -0.146 |
od | -0.133 |
vals | -0.132 |
arom | -0.132 |
Token | went |
Token ID | 1816 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Woo | +0.066 |
wagon | +0.064 |
leash | +0.064 |
lamb | +0.063 |
yacht | +0.063 |
Neg logit contributions | |
ways | -0.071 |
ad | -0.065 |
od | -0.060 |
mastered | -0.060 |
vals | -0.059 |
Token | home |
Token ID | 1363 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
lamb | +0.052 |
Woo | +0.050 |
wagon | +0.050 |
mole | +0.049 |
yacht | +0.048 |
Neg logit contributions | |
ways | -0.083 |
ad | -0.074 |
mastered | -0.066 |
br | -0.065 |
ers | -0.065 |
Token | with |
Token ID | 351 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Woo | +0.027 |
wagon | +0.027 |
lamb | +0.027 |
leash | +0.027 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.020 |
ad | -0.018 |
od | -0.017 |
mastered | -0.016 |
arom | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
Woo | +0.037 |
wagon | +0.036 |
leash | +0.036 |
yacht | +0.035 |
lamb | +0.035 |
Neg logit contributions | |
ways | -0.051 |
ad | -0.047 |
vals | -0.045 |
od | -0.044 |
ven | -0.044 |
Token | with |
Token ID | 351 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
wagon | +0.029 |
Woo | +0.028 |
lamb | +0.028 |
yacht | +0.027 |
leash | +0.027 |
Neg logit contributions | |
ways | -0.039 |
ad | -0.036 |
od | -0.033 |
mastered | -0.033 |
arom | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
Woo | +0.047 |
wagon | +0.046 |
leash | +0.045 |
yacht | +0.044 |
lamb | +0.044 |
Neg logit contributions | |
ways | -0.066 |
ad | -0.060 |
vals | -0.058 |
od | -0.058 |
ven | -0.057 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Woo | +0.034 |
lamb | +0.031 |
wagon | +0.030 |
yacht | +0.030 |
paddle | +0.028 |
Neg logit contributions | |
ways | -0.074 |
ad | -0.072 |
arom | -0.066 |
mastered | -0.066 |
vals | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
Woo | +0.016 |
wagon | +0.015 |
leash | +0.015 |
yacht | +0.015 |
lamb | +0.015 |
Neg logit contributions | |
ways | -0.019 |
ad | -0.018 |
od | -0.017 |
vals | -0.017 |
ven | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
wagon | +0.070 |
lamb | +0.068 |
leash | +0.068 |
raft | +0.067 |
Woo | +0.066 |
Neg logit contributions | |
ways | -0.075 |
ad | -0.073 |
mastered | -0.068 |
arom | -0.066 |
lit | -0.065 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Woo | +0.036 |
lamb | +0.031 |
yacht | +0.030 |
wagon | +0.030 |
Spot | +0.028 |
Neg logit contributions | |
ways | -0.082 |
ad | -0.080 |
arom | -0.075 |
mastered | -0.073 |
vals | -0.073 |
Token | car |
Token ID | 1097 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Woo | +0.049 |
lamb | +0.045 |
paddle | +0.043 |
wagon | +0.042 |
drown | +0.042 |
Neg logit contributions | |
ways | -0.167 |
ad | -0.160 |
br | -0.147 |
vals | -0.146 |
arom | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
wagon | +0.060 |
leash | +0.060 |
Woo | +0.059 |
yacht | +0.058 |
sled | +0.058 |
Neg logit contributions | |
ways | -0.053 |
ad | -0.049 |
vals | -0.047 |
od | -0.047 |
arom | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
yacht | +0.023 |
lamb | +0.023 |
wagon | +0.023 |
leash | +0.023 |
raft | +0.023 |
Neg logit contributions | |
ways | -0.031 |
ad | -0.029 |
mastered | -0.027 |
od | -0.026 |
shades | -0.026 |
Token | hugged |
Token ID | 41130 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
wagon | +0.027 |
leash | +0.026 |
Woo | +0.026 |
lamb | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.030 |
ad | -0.029 |
mastered | -0.026 |
ven | -0.026 |
od | -0.026 |
Token | his |
Token ID | 465 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
wagon | +0.067 |
yacht | +0.066 |
lamb | +0.066 |
leash | +0.066 |
Woo | +0.065 |
Neg logit contributions | |
ways | -0.076 |
ad | -0.076 |
arom | -0.065 |
od | -0.064 |
agg | -0.063 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
wagon | +0.018 |
Woo | +0.018 |
sled | +0.017 |
lamb | +0.017 |
yacht | +0.017 |
Neg logit contributions | |
ways | -0.030 |
ad | -0.030 |
mastered | -0.028 |
od | -0.028 |
arom | -0.027 |
Token | because |
Token ID | 780 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
wagon | +0.048 |
lamb | +0.048 |
leash | +0.047 |
Woo | +0.047 |
yacht | +0.047 |
Neg logit contributions | |
ways | -0.054 |
ad | -0.050 |
od | -0.045 |
mastered | -0.045 |
arom | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
wagon | +0.055 |
leash | +0.055 |
Woo | +0.055 |
lamb | +0.054 |
paddle | +0.052 |
Neg logit contributions | |
ways | -0.070 |
ad | -0.067 |
od | -0.060 |
mastered | -0.058 |
arom | -0.058 |
Token | lost |
Token ID | 2626 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
wagon | +0.042 |
leash | +0.041 |
Woo | +0.041 |
lamb | +0.041 |
yacht | +0.040 |
Neg logit contributions | |
ways | -0.041 |
ad | -0.038 |
mastered | -0.036 |
od | -0.034 |
ven | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Woo | +0.060 |
wagon | +0.059 |
leash | +0.058 |
lamb | +0.057 |
yacht | +0.056 |
Neg logit contributions | |
ways | -0.100 |
ad | -0.095 |
od | -0.087 |
arom | -0.087 |
vals | -0.086 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
Woo | +0.042 |
lamb | +0.041 |
Drop | +0.037 |
Spot | +0.036 |
sled | +0.034 |
Neg logit contributions | |
ways | -0.064 |
ad | -0.063 |
powers | -0.061 |
symbols | -0.061 |
mastered | -0.059 |
Token | gun |
Token ID | 2485 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
Woo | +0.083 |
lamb | +0.079 |
drown | +0.076 |
paddle | +0.075 |
Spot | +0.075 |
Neg logit contributions | |
ways | -0.129 |
ad | -0.119 |
br | -0.110 |
ier | -0.110 |
od | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Woo | +0.062 |
wagon | +0.062 |
leash | +0.061 |
yacht | +0.060 |
lamb | +0.059 |
Neg logit contributions | |
ways | -0.059 |
ad | -0.055 |
vals | -0.051 |
arom | -0.050 |
od | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Woo | +0.027 |
wagon | +0.027 |
leash | +0.027 |
lamb | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.041 |
ad | -0.039 |
od | -0.036 |
vals | -0.036 |
ven | -0.035 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
wagon | +0.042 |
leash | +0.041 |
arl | +0.041 |
lamb | +0.041 |
Woo | +0.041 |
Neg logit contributions | |
ways | -0.038 |
ad | -0.037 |
mastered | -0.034 |
lit | -0.032 |
arom | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
ways | +0.009 |
ad | +0.009 |
od | +0.008 |
mastered | +0.008 |
br | +0.008 |
Neg logit contributions | |
lamb | -0.007 |
wagon | -0.007 |
paddle | -0.007 |
leash | -0.007 |
yacht | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -8.83e-03 |
Pos logit contributions | |
ways | +0.034 |
ad | +0.032 |
arom | +0.031 |
ven | +0.030 |
od | +0.030 |
Neg logit contributions | |
Woo | -0.019 |
wagon | -0.019 |
leash | -0.018 |
yacht | -0.018 |
sled | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ways | +0.019 |
ad | +0.018 |
ement | +0.017 |
od | +0.017 |
mastered | +0.016 |
Neg logit contributions | |
Woo | -0.011 |
wagon | -0.010 |
sled | -0.010 |
duck | -0.010 |
dog | -0.009 |
Token | pitcher |
Token ID | 18086 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Woo | +0.013 |
wagon | +0.013 |
leash | +0.013 |
lamb | +0.013 |
yacht | +0.013 |
Neg logit contributions | |
ways | -0.023 |
ad | -0.021 |
vals | -0.020 |
od | -0.020 |
ven | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ways | +0.032 |
ad | +0.030 |
ven | +0.029 |
arom | +0.028 |
od | +0.028 |
Neg logit contributions | |
wagon | -0.023 |
Woo | -0.023 |
leash | -0.023 |
yacht | -0.022 |
raft | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Woo | +0.030 |
wagon | +0.030 |
leash | +0.030 |
lamb | +0.029 |
yacht | +0.029 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.033 |
vals | -0.031 |
od | -0.031 |
ven | -0.031 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
Woo | +0.024 |
lamb | +0.023 |
leash | +0.022 |
wagon | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
ways | -0.053 |
ad | -0.050 |
vals | -0.047 |
arom | -0.047 |
mastered | -0.047 |
Token | box |
Token ID | 3091 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
Woo | +0.072 |
wagon | +0.070 |
leash | +0.070 |
lamb | +0.069 |
yacht | +0.067 |
Neg logit contributions | |
ways | -0.148 |
ad | -0.139 |
vals | -0.131 |
od | -0.130 |
ven | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
wagon | +0.027 |
leash | +0.027 |
dog | +0.025 |
sled | +0.025 |
yacht | +0.025 |
Neg logit contributions | |
ways | -0.026 |
arom | -0.026 |
ad | -0.026 |
vals | -0.025 |
ven | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
arom | +0.002 |
vals | +0.002 |
od | +0.002 |
Neg logit contributions | |
Woo | -0.002 |
wagon | -0.001 |
leash | -0.001 |
lamb | -0.001 |
mole | -0.001 |
Token | fills |
Token ID | 23816 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
ways | +0.029 |
ad | +0.028 |
vals | +0.026 |
od | +0.026 |
ven | +0.025 |
Neg logit contributions | |
Woo | -0.019 |
wagon | -0.019 |
leash | -0.018 |
lamb | -0.018 |
yacht | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ways | +0.049 |
ad | +0.046 |
vals | +0.044 |
mastered | +0.044 |
ven | +0.043 |
Neg logit contributions | |
Woo | -0.032 |
wagon | -0.031 |
yacht | -0.030 |
leash | -0.030 |
lamb | -0.029 |
Token | again |
Token ID | 757 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
ways | +0.000 |
vals | +0.000 |
ad | +0.000 |
ven | +0.000 |
agg | +0.000 |
Neg logit contributions | |
Woo | -0.000 |
dog | -0.000 |
wagon | -0.000 |
who | -0.000 |
puppy | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
ways | +0.011 |
ad | +0.010 |
vals | +0.010 |
agg | +0.010 |
arom | +0.010 |
Neg logit contributions | |
Woo | -0.010 |
leash | -0.010 |
who | -0.010 |
lamb | -0.010 |
dog | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
Woo | +0.005 |
wagon | +0.005 |
leash | +0.005 |
lamb | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
ways | -0.007 |
ad | -0.006 |
od | -0.006 |
vals | -0.006 |
ven | -0.006 |
Token | hugged |
Token ID | 41130 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ways | +0.012 |
ad | +0.011 |
vals | +0.011 |
od | +0.010 |
ven | +0.010 |
Neg logit contributions | |
Woo | -0.009 |
wagon | -0.009 |
leash | -0.009 |
lamb | -0.009 |
yacht | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
wagon | +0.062 |
leash | +0.061 |
lamb | +0.060 |
sled | +0.060 |
Woo | +0.059 |
Neg logit contributions | |
ways | -0.058 |
ad | -0.057 |
od | -0.050 |
arom | -0.049 |
mastered | -0.048 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
Woo | +0.031 |
drown | +0.030 |
Spot | +0.028 |
lamb | +0.027 |
Drop | +0.026 |
Neg logit contributions | |
ad | -0.051 |
ways | -0.051 |
arom | -0.049 |
mastered | -0.047 |
ement | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Woo | +0.067 |
drown | +0.061 |
leash | +0.059 |
lamb | +0.058 |
Spot | +0.057 |
Neg logit contributions | |
ways | -0.151 |
ad | -0.144 |
arom | -0.134 |
od | -0.134 |
ven | -0.132 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
wagon | +0.032 |
Woo | +0.032 |
leash | +0.032 |
lamb | +0.032 |
yacht | +0.031 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.034 |
od | -0.031 |
mastered | -0.031 |
vals | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
Woo | +0.021 |
yacht | +0.019 |
wagon | +0.019 |
lamb | +0.019 |
leash | +0.018 |
Neg logit contributions | |
ways | -0.030 |
vals | -0.027 |
br | -0.026 |
ven | -0.026 |
mastered | -0.026 |
Token | man |
Token ID | 582 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
wagon | +0.008 |
Woo | +0.008 |
leash | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
Neg logit contributions | |
ways | -0.014 |
ad | -0.014 |
vals | -0.013 |
od | -0.013 |
ven | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
Woo | +0.020 |
wagon | +0.020 |
leash | +0.020 |
lamb | +0.019 |
yacht | +0.019 |
Neg logit contributions | |
ways | -0.023 |
ad | -0.021 |
vals | -0.020 |
ven | -0.019 |
arom | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
Woo | +0.008 |
wagon | +0.008 |
leash | +0.008 |
lamb | +0.008 |
yacht | +0.008 |
Neg logit contributions | |
ways | -0.013 |
ad | -0.013 |
od | -0.012 |
vals | -0.012 |
mastered | -0.012 |
Token | Baby |
Token ID | 36534 |
Feature activation | +7.54e-03 |
Pos logit contributions | |
Woo | +0.008 |
wagon | +0.008 |
Spot | +0.008 |
sled | +0.008 |
dog | +0.007 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
vals | -0.014 |
arom | -0.014 |
ven | -0.013 |
Token | Bear |
Token ID | 14732 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Woo | +0.010 |
wagon | +0.010 |
lamb | +0.009 |
leash | +0.009 |
yacht | +0.009 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
vals | -0.013 |
od | -0.013 |
ven | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +6.43e-03 |
Pos logit contributions | |
Woo | +0.029 |
wagon | +0.029 |
leash | +0.029 |
lamb | +0.028 |
yacht | +0.028 |
Neg logit contributions | |
ways | -0.038 |
ad | -0.036 |
vals | -0.033 |
od | -0.033 |
ven | -0.033 |
Token | always |
Token ID | 1464 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
wagon | +0.009 |
Woo | +0.009 |
leash | +0.008 |
yacht | +0.008 |
lamb | +0.008 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.011 |
od | -0.010 |
mastered | -0.010 |
ven | -0.010 |
Token | depend |
Token ID | 4745 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
Woo | +0.019 |
wagon | +0.018 |
leash | +0.018 |
lamb | +0.018 |
yacht | +0.018 |
Neg logit contributions | |
ways | -0.033 |
ad | -0.031 |
vals | -0.029 |
od | -0.029 |
ven | -0.029 |
Token | able |
Token ID | 540 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
raft | +0.117 |
yacht | +0.114 |
wagon | +0.112 |
drown | +0.111 |
paddle | +0.108 |
Neg logit contributions | |
ad | -0.107 |
ways | -0.102 |
ers | -0.092 |
ce | -0.091 |
mastered | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
wagon | +0.033 |
Woo | +0.032 |
lamb | +0.032 |
leash | +0.032 |
yacht | +0.031 |
Neg logit contributions | |
ways | -0.035 |
ad | -0.032 |
vals | -0.031 |
ven | -0.030 |
br | -0.030 |
Token | He |
Token ID | 679 |
Feature activation | +2.89e-03 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.002 |
yacht | +0.002 |
lamb | +0.002 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
od | -0.002 |
arom | -0.002 |
vals | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Woo | +0.003 |
wagon | +0.003 |
lamb | +0.003 |
leash | +0.003 |
yacht | +0.003 |
Neg logit contributions | |
ways | -0.006 |
vals | -0.005 |
ad | -0.005 |
od | -0.005 |
arom | -0.005 |
Token | always |
Token ID | 1464 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Woo | +0.019 |
wagon | +0.019 |
leash | +0.018 |
lamb | +0.018 |
yacht | +0.018 |
Neg logit contributions | |
ways | -0.025 |
ad | -0.023 |
vals | -0.022 |
od | -0.021 |
arom | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
Woo | +0.005 |
wagon | +0.004 |
leash | +0.004 |
yacht | +0.004 |
lamb | +0.004 |
Neg logit contributions | |
ways | -0.004 |
ad | -0.004 |
vals | -0.004 |
od | -0.004 |
arom | -0.004 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
lamb | +0.003 |
leash | +0.003 |
yacht | +0.003 |
Woo | +0.003 |
wagon | +0.003 |
Neg logit contributions | |
ways | -0.004 |
ad | -0.004 |
od | -0.003 |
mastered | -0.003 |
ven | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
Woo | +0.013 |
yacht | +0.013 |
leash | +0.013 |
wagon | +0.013 |
mole | +0.012 |
Neg logit contributions | |
ad | -0.014 |
ways | -0.014 |
od | -0.013 |
mastered | -0.012 |
ven | -0.012 |
Token | flew |
Token ID | 13112 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.005 |
od | +0.005 |
mastered | +0.005 |
ven | +0.005 |
Neg logit contributions | |
Woo | -0.005 |
wagon | -0.005 |
leash | -0.005 |
lamb | -0.005 |
yacht | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
lamb | +0.038 |
wagon | +0.037 |
Woo | +0.037 |
yacht | +0.036 |
leash | +0.036 |
Neg logit contributions | |
ways | -0.060 |
ad | -0.057 |
mastered | -0.052 |
od | -0.051 |
ven | -0.051 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
Woo | +0.052 |
Drop | +0.049 |
mole | +0.045 |
arl | +0.044 |
Otto | +0.044 |
Neg logit contributions | |
ways | -0.050 |
br | -0.047 |
shades | -0.045 |
powers | -0.045 |
ad | -0.044 |
Token | plane |
Token ID | 6614 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
Woo | +0.090 |
drown | +0.079 |
lamb | +0.079 |
mole | +0.079 |
Spot | +0.079 |
Neg logit contributions | |
ways | -0.128 |
br | -0.119 |
ad | -0.116 |
od | -0.109 |
vals | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
Woo | +0.019 |
lamb | +0.019 |
wagon | +0.019 |
leash | +0.018 |
yacht | +0.018 |
Neg logit contributions | |
ways | -0.034 |
ad | -0.031 |
od | -0.029 |
mastered | -0.029 |
vals | -0.029 |
Token | pretended |
Token ID | 36766 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
leash | +0.014 |
wagon | +0.014 |
lamb | +0.014 |
Woo | +0.014 |
mole | +0.013 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
mastered | -0.013 |
od | -0.013 |
ven | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Woo | +0.007 |
yacht | +0.007 |
dog | +0.007 |
leash | +0.007 |
sled | +0.007 |
Neg logit contributions | |
ways | -0.018 |
vals | -0.018 |
agg | -0.018 |
ad | -0.017 |
ami | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
ways | +0.033 |
agg | +0.031 |
vals | +0.030 |
ad | +0.030 |
arom | +0.030 |
Neg logit contributions | |
dog | -0.017 |
Woo | -0.017 |
wagon | -0.017 |
bicycle | -0.017 |
sled | -0.017 |
Token | takes |
Token ID | 2753 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
Woo | +0.024 |
wagon | +0.024 |
leash | +0.024 |
lamb | +0.023 |
yacht | +0.023 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.034 |
vals | -0.032 |
od | -0.032 |
ven | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Woo | +0.009 |
wagon | +0.008 |
leash | +0.008 |
sled | +0.008 |
Spot | +0.008 |
Neg logit contributions | |
ways | -0.016 |
ad | -0.015 |
vals | -0.015 |
od | -0.015 |
agg | -0.014 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
Woo | +0.012 |
lamb | +0.009 |
yacht | +0.009 |
bases | +0.009 |
Spot | +0.009 |
Neg logit contributions | |
ad | -0.020 |
br | -0.018 |
powers | -0.018 |
arom | -0.018 |
shades | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
lamb | +0.050 |
Woo | +0.047 |
yacht | +0.046 |
mole | +0.045 |
drown | +0.045 |
Neg logit contributions | |
ways | -0.049 |
ad | -0.049 |
br | -0.040 |
mastered | -0.040 |
od | -0.040 |
Token | his |
Token ID | 465 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
Woo | +0.023 |
lamb | +0.023 |
yacht | +0.022 |
leash | +0.022 |
wagon | +0.022 |
Neg logit contributions | |
ways | -0.032 |
ad | -0.031 |
arom | -0.029 |
vals | -0.029 |
mastered | -0.028 |
Token | k |
Token ID | 479 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
Woo | +0.027 |
lamb | +0.024 |
yacht | +0.021 |
Spot | +0.021 |
lves | +0.021 |
Neg logit contributions | |
ad | -0.042 |
shades | -0.040 |
powers | -0.039 |
ways | -0.039 |
symbols | -0.039 |
Token | ite |
Token ID | 578 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
yacht | +0.094 |
Woo | +0.090 |
raft | +0.086 |
wagon | +0.086 |
lamb | +0.085 |
Neg logit contributions | |
ad | -0.123 |
ways | -0.115 |
vals | -0.102 |
ven | -0.100 |
od | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
wagon | +0.046 |
Woo | +0.045 |
leash | +0.045 |
yacht | +0.044 |
lamb | +0.044 |
Neg logit contributions | |
ways | -0.038 |
ad | -0.035 |
vals | -0.032 |
od | -0.032 |
ven | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
lamb | +0.036 |
Woo | +0.036 |
yacht | +0.035 |
leash | +0.035 |
mole | +0.034 |
Neg logit contributions | |
ways | -0.045 |
ad | -0.043 |
mastered | -0.040 |
vals | -0.040 |
br | -0.040 |
Token | bike |
Token ID | 7161 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
Woo | +0.024 |
lamb | +0.021 |
yacht | +0.018 |
Spot | +0.018 |
Drop | +0.018 |
Neg logit contributions | |
ad | -0.046 |
ways | -0.046 |
shades | -0.043 |
br | -0.043 |
vals | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
wagon | +0.066 |
leash | +0.066 |
Woo | +0.065 |
sled | +0.064 |
yacht | +0.063 |
Neg logit contributions | |
ways | -0.052 |
ad | -0.047 |
agg | -0.046 |
arom | -0.045 |
od | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
mastered | +0.002 |
ven | +0.002 |
od | +0.002 |
Neg logit contributions | |
wagon | -0.002 |
leash | -0.002 |
Woo | -0.002 |
yacht | -0.002 |
lamb | -0.002 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
wagon | +0.046 |
yacht | +0.043 |
raft | +0.043 |
sled | +0.042 |
paddle | +0.042 |
Neg logit contributions | |
ways | -0.060 |
ad | -0.058 |
mastered | -0.053 |
od | -0.052 |
shades | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
wagon | +0.059 |
yacht | +0.059 |
paddle | +0.058 |
leash | +0.058 |
lamb | +0.058 |
Neg logit contributions | |
ways | -0.043 |
ad | -0.037 |
mastered | -0.034 |
od | -0.034 |
br | -0.033 |
Token | missed |
Token ID | 6825 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
wagon | +0.057 |
sled | +0.057 |
leash | +0.056 |
paddle | +0.055 |
lamb | +0.055 |
Neg logit contributions | |
ways | -0.051 |
ad | -0.046 |
arom | -0.039 |
lit | -0.039 |
mastered | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
wagon | +0.076 |
Woo | +0.075 |
leash | +0.075 |
yacht | +0.074 |
lamb | +0.074 |
Neg logit contributions | |
ways | -0.100 |
ad | -0.094 |
od | -0.086 |
arom | -0.085 |
mastered | -0.085 |
Token | furry |
Token ID | 40857 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
Woo | +0.026 |
Drop | +0.026 |
yacht | +0.025 |
paddle | +0.025 |
lamb | +0.025 |
Neg logit contributions | |
ways | -0.038 |
ad | -0.038 |
shades | -0.036 |
bows | -0.035 |
arom | -0.034 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Woo | +0.073 |
yacht | +0.070 |
wagon | +0.068 |
paddle | +0.067 |
drown | +0.066 |
Neg logit contributions | |
ad | -0.131 |
ways | -0.129 |
shades | -0.122 |
arom | -0.120 |
agg | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Woo | +0.045 |
wagon | +0.044 |
leash | +0.044 |
lamb | +0.043 |
yacht | +0.042 |
Neg logit contributions | |
ways | -0.031 |
ad | -0.028 |
vals | -0.026 |
arom | -0.026 |
agg | -0.025 |
Token | |
Token ID | 220 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
lamb | +0.041 |
yacht | +0.040 |
paddle | +0.040 |
leash | +0.040 |
raft | +0.040 |
Neg logit contributions | |
ways | -0.047 |
ad | -0.041 |
shades | -0.037 |
mastered | -0.037 |
od | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
lamb | +0.010 |
yacht | +0.010 |
wagon | +0.010 |
Woo | +0.009 |
leash | +0.009 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.012 |
od | -0.011 |
agg | -0.010 |
ven | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
yacht | +0.056 |
wagon | +0.055 |
lamb | +0.055 |
mole | +0.054 |
raft | +0.054 |
Neg logit contributions | |
ways | -0.047 |
ad | -0.044 |
od | -0.040 |
books | -0.039 |
agg | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
Woo | +0.031 |
wagon | +0.031 |
leash | +0.030 |
lamb | +0.029 |
yacht | +0.029 |
Neg logit contributions | |
ways | -0.063 |
ad | -0.059 |
vals | -0.057 |
ven | -0.056 |
arom | -0.056 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
Woo | +0.031 |
wagon | +0.031 |
leash | +0.031 |
lamb | +0.030 |
yacht | +0.030 |
Neg logit contributions | |
ways | -0.039 |
ad | -0.037 |
od | -0.034 |
vals | -0.034 |
ven | -0.034 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Woo | +0.052 |
wagon | +0.052 |
leash | +0.051 |
lamb | +0.051 |
yacht | +0.050 |
Neg logit contributions | |
ways | -0.069 |
ad | -0.066 |
od | -0.060 |
vals | -0.060 |
ven | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
Woo | +0.031 |
wagon | +0.031 |
leash | +0.030 |
lamb | +0.029 |
yacht | +0.029 |
Neg logit contributions | |
ways | -0.054 |
ad | -0.051 |
vals | -0.048 |
od | -0.048 |
ven | -0.048 |
Token | his |
Token ID | 465 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
Woo | +0.034 |
wagon | +0.034 |
leash | +0.034 |
lamb | +0.033 |
yacht | +0.033 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.033 |
vals | -0.031 |
od | -0.031 |
ven | -0.031 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
Woo | +0.033 |
Spot | +0.032 |
lamb | +0.030 |
leash | +0.030 |
sled | +0.029 |
Neg logit contributions | |
ad | -0.049 |
ways | -0.049 |
arom | -0.048 |
shades | -0.047 |
powers | -0.047 |
Token | back |
Token ID | 736 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
Woo | +0.089 |
lamb | +0.085 |
leash | +0.085 |
Spot | +0.082 |
mole | +0.081 |
Neg logit contributions | |
ways | -0.124 |
ad | -0.119 |
arom | -0.107 |
od | -0.107 |
br | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
wagon | +0.029 |
Woo | +0.029 |
leash | +0.029 |
yacht | +0.028 |
lamb | +0.028 |
Neg logit contributions | |
ways | -0.025 |
ad | -0.023 |
vals | -0.021 |
ven | -0.021 |
arom | -0.021 |
Token | |
Token ID | 220 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
leash | +0.007 |
lamb | +0.007 |
Woo | +0.007 |
wagon | +0.007 |
yacht | +0.007 |
Neg logit contributions | |
ways | -0.009 |
ad | -0.008 |
od | -0.007 |
vals | -0.007 |
ven | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
vals | +0.013 |
od | +0.013 |
ven | +0.013 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.008 |
leash | -0.008 |
lamb | -0.007 |
yacht | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
lamb | +0.016 |
yacht | +0.015 |
wagon | +0.015 |
mole | +0.015 |
paddle | +0.015 |
Neg logit contributions | |
ways | -0.014 |
ad | -0.013 |
od | -0.012 |
books | -0.012 |
mastered | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
Woo | +0.021 |
leash | +0.019 |
yacht | +0.018 |
drown | +0.018 |
wagon | +0.017 |
Neg logit contributions | |
ways | -0.049 |
ad | -0.047 |
arom | -0.044 |
shades | -0.043 |
ven | -0.043 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ways | +0.002 |
vals | +0.002 |
ad | +0.002 |
od | +0.002 |
arom | +0.002 |
Neg logit contributions | |
Woo | -0.002 |
wagon | -0.002 |
dog | -0.002 |
duck | -0.002 |
sled | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Woo | +0.021 |
wagon | +0.021 |
leash | +0.021 |
lamb | +0.020 |
yacht | +0.020 |
Neg logit contributions | |
ways | -0.029 |
ad | -0.028 |
od | -0.025 |
vals | -0.025 |
arom | -0.025 |
Token | hugged |
Token ID | 41130 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
Woo | +0.020 |
wagon | +0.020 |
leash | +0.020 |
lamb | +0.019 |
yacht | +0.019 |
Neg logit contributions | |
ways | -0.026 |
ad | -0.024 |
vals | -0.022 |
od | -0.022 |
ven | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Woo | +0.061 |
wagon | +0.058 |
leash | +0.057 |
lamb | +0.056 |
sled | +0.055 |
Neg logit contributions | |
ways | -0.080 |
vals | -0.076 |
ad | -0.071 |
ven | -0.071 |
br | -0.071 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
Woo | +0.020 |
drown | +0.018 |
lamb | +0.018 |
yacht | +0.017 |
mole | +0.017 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.043 |
arom | -0.040 |
mastered | -0.039 |
ven | -0.039 |
Token | phone |
Token ID | 3072 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Woo | +0.066 |
lamb | +0.060 |
yacht | +0.058 |
mole | +0.058 |
leash | +0.058 |
Neg logit contributions | |
ways | -0.151 |
ad | -0.144 |
od | -0.132 |
ven | -0.131 |
arom | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
wagon | +0.036 |
leash | +0.036 |
sled | +0.034 |
bicycle | +0.034 |
Woo | +0.034 |
Neg logit contributions | |
ways | -0.033 |
vals | -0.032 |
ad | -0.032 |
agg | -0.031 |
arom | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
lamb | +0.002 |
leash | +0.002 |
sled | +0.002 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.002 |
vals | -0.002 |
ven | -0.002 |
od | -0.002 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
mastered | +0.003 |
od | +0.003 |
ven | +0.003 |
Neg logit contributions | |
Woo | -0.003 |
wagon | -0.003 |
leash | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ways | +0.038 |
ad | +0.035 |
vals | +0.033 |
od | +0.032 |
ven | +0.032 |
Neg logit contributions | |
Woo | -0.032 |
wagon | -0.031 |
leash | -0.031 |
lamb | -0.030 |
yacht | -0.030 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ways | +0.000 |
ad | +0.000 |
vals | +0.000 |
od | +0.000 |
ven | +0.000 |
Neg logit contributions | |
Woo | -0.000 |
wagon | -0.000 |
leash | -0.000 |
lamb | -0.000 |
yacht | -0.000 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
Woo | +0.023 |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
ways | -0.030 |
ad | -0.028 |
vals | -0.026 |
od | -0.026 |
ven | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.021 |
vals | +0.020 |
od | +0.020 |
ven | +0.020 |
Neg logit contributions | |
Woo | -0.015 |
wagon | -0.015 |
leash | -0.014 |
lamb | -0.014 |
yacht | -0.014 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
ways | +0.042 |
vals | +0.039 |
ad | +0.038 |
br | +0.037 |
bows | +0.037 |
Neg logit contributions | |
lamb | -0.012 |
dog | -0.012 |
Woo | -0.012 |
wound | -0.011 |
wagon | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Woo | +0.002 |
Spot | +0.002 |
who | +0.002 |
wagon | +0.002 |
puppy | +0.002 |
Neg logit contributions | |
vals | -0.003 |
ways | -0.003 |
br | -0.002 |
mastered | -0.002 |
ad | -0.002 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
wagon | +0.014 |
leash | +0.013 |
Woo | +0.013 |
lamb | +0.013 |
yacht | +0.013 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.042 |
vals | -0.041 |
ven | -0.040 |
mastered | -0.040 |
Token | dragon |
Token ID | 10441 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
wagon | +0.053 |
Woo | +0.051 |
leash | +0.049 |
lamb | +0.049 |
yacht | +0.049 |
Neg logit contributions | |
ways | -0.168 |
ad | -0.158 |
vals | -0.152 |
mastered | -0.150 |
od | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +4.40e-03 |
Pos logit contributions | |
leash | +0.043 |
wagon | +0.042 |
lamb | +0.042 |
sled | +0.042 |
mole | +0.041 |
Neg logit contributions | |
ways | -0.044 |
vals | -0.040 |
ad | -0.038 |
arom | -0.038 |
mastered | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Woo | +0.004 |
wagon | +0.004 |
leash | +0.004 |
Spot | +0.004 |
dog | +0.004 |
Neg logit contributions | |
ways | -0.010 |
ad | -0.010 |
vals | -0.009 |
arom | -0.009 |
agg | -0.009 |
Token | We |
Token ID | 1135 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
wagon | +0.034 |
yacht | +0.033 |
raft | +0.033 |
leash | +0.031 |
lamb | +0.030 |
Neg logit contributions | |
ad | -0.043 |
ways | -0.041 |
od | -0.039 |
br | -0.039 |
vals | -0.038 |
Token | are |
Token ID | 389 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
vals | +0.003 |
od | +0.003 |
ven | +0.002 |
Neg logit contributions | |
Woo | -0.002 |
wagon | -0.002 |
leash | -0.002 |
lamb | -0.002 |
yacht | -0.002 |
Token | cakes |
Token ID | 30849 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
ways | +0.066 |
ad | +0.061 |
vals | +0.058 |
ven | +0.058 |
od | +0.057 |
Neg logit contributions | |
Woo | -0.045 |
wagon | -0.045 |
leash | -0.043 |
yacht | -0.043 |
sled | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ways | +0.075 |
ad | +0.073 |
mastered | +0.068 |
agg | +0.068 |
vals | +0.068 |
Neg logit contributions | |
wagon | -0.052 |
leash | -0.051 |
yacht | -0.050 |
Woo | -0.050 |
sled | -0.048 |
Token | cookies |
Token ID | 14746 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ways | +0.049 |
ad | +0.045 |
ven | +0.045 |
mastered | +0.044 |
od | +0.044 |
Neg logit contributions | |
Woo | -0.036 |
wagon | -0.036 |
sled | -0.035 |
yacht | -0.035 |
lamb | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ways | +0.040 |
ad | +0.039 |
agg | +0.037 |
arom | +0.037 |
vals | +0.036 |
Neg logit contributions | |
wagon | -0.022 |
leash | -0.022 |
Woo | -0.021 |
yacht | -0.021 |
raft | -0.020 |
Token | ch |
Token ID | 442 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
ways | +0.021 |
ad | +0.020 |
ven | +0.019 |
od | +0.019 |
vals | +0.018 |
Neg logit contributions | |
wagon | -0.016 |
Woo | -0.016 |
yacht | -0.015 |
lamb | -0.015 |
leash | -0.015 |
Token | ocol |
Token ID | 4668 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
ways | +0.006 |
ven | +0.006 |
equations | +0.005 |
books | +0.005 |
ad | +0.005 |
Neg logit contributions | |
arl | -0.007 |
mole | -0.007 |
leash | -0.007 |
lamb | -0.007 |
drown | -0.007 |
Token | ates |
Token ID | 689 |
Feature activation | +6.39e-04 |
Pos logit contributions | |
ways | +0.157 |
equations | +0.136 |
mastered | +0.134 |
arom | +0.126 |
ad | +0.126 |
Neg logit contributions | |
mole | -0.122 |
sled | -0.122 |
Spot | -0.120 |
arl | -0.119 |
leash | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
yacht | +0.001 |
wagon | +0.001 |
leash | +0.001 |
Woo | +0.001 |
sled | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
vals | -0.001 |
equations | -0.001 |
arom | -0.001 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.014 |
ven | +0.013 |
od | +0.013 |
vals | +0.013 |
Neg logit contributions | |
wagon | -0.011 |
Woo | -0.011 |
yacht | -0.011 |
leash | -0.011 |
mole | -0.011 |
Token | cream |
Token ID | 8566 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
ways | +0.026 |
ad | +0.026 |
mastered | +0.026 |
ven | +0.024 |
subtract | +0.024 |
Neg logit contributions | |
wagon | -0.014 |
leash | -0.013 |
sled | -0.013 |
yacht | -0.013 |
duck | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
wagon | +0.012 |
yacht | +0.012 |
leash | +0.012 |
dog | +0.011 |
Woo | +0.011 |
Neg logit contributions | |
ways | -0.013 |
ad | -0.012 |
agg | -0.012 |
vals | -0.012 |
ven | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ways | +0.056 |
vals | +0.054 |
arom | +0.054 |
ad | +0.054 |
von | +0.052 |
Neg logit contributions | |
sled | -0.025 |
wagon | -0.025 |
who | -0.024 |
leash | -0.024 |
dog | -0.023 |
Token | found |
Token ID | 1043 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
ad | +0.038 |
ways | +0.038 |
br | +0.038 |
vals | +0.037 |
von | +0.037 |
Neg logit contributions | |
who | -0.022 |
paddle | -0.021 |
boy | -0.021 |
wagon | -0.021 |
mole | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ways | +0.040 |
vals | +0.036 |
arom | +0.035 |
ides | +0.035 |
oph | +0.035 |
Neg logit contributions | |
wagon | -0.024 |
mole | -0.022 |
sled | -0.022 |
dog | -0.021 |
who | -0.021 |
Token | there |
Token ID | 612 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
wagon | +0.016 |
Woo | +0.016 |
yacht | +0.016 |
sled | +0.015 |
mole | +0.015 |
Neg logit contributions | |
ways | -0.027 |
ad | -0.025 |
vals | -0.024 |
mastered | -0.023 |
arom | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ways | +0.004 |
vals | +0.004 |
ami | +0.004 |
von | +0.004 |
arom | +0.004 |
Neg logit contributions | |
wagon | -0.002 |
dog | -0.002 |
yacht | -0.002 |
boat | -0.002 |
raft | -0.001 |
Token | 6 |
Token ID | 718 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
ways | +0.059 |
vals | +0.054 |
ides | +0.054 |
ven | +0.053 |
ce | +0.053 |
Neg logit contributions | |
sled | -0.033 |
wagon | -0.032 |
mole | -0.031 |
raft | -0.031 |
duck | -0.030 |
Token | rocks |
Token ID | 12586 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
oph | +0.155 |
ways | +0.153 |
vals | +0.152 |
books | +0.151 |
issy | +0.149 |
Neg logit contributions | |
sled | -0.115 |
paddle | -0.105 |
wagon | -0.101 |
kay | -0.101 |
boat | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ways | +0.010 |
agg | +0.010 |
arom | +0.010 |
ad | +0.010 |
vals | +0.010 |
Neg logit contributions | |
wagon | -0.008 |
yacht | -0.008 |
leash | -0.008 |
sled | -0.008 |
raft | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ways | +0.037 |
ad | +0.035 |
vals | +0.035 |
arom | +0.035 |
agg | +0.034 |
Neg logit contributions | |
wagon | -0.016 |
Woo | -0.015 |
Spot | -0.014 |
dog | -0.014 |
sled | -0.014 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ways | +0.032 |
vals | +0.030 |
arom | +0.029 |
ad | +0.029 |
bows | +0.029 |
Neg logit contributions | |
wagon | -0.019 |
sled | -0.018 |
paddle | -0.018 |
who | -0.018 |
dog | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ways | +0.045 |
arom | +0.043 |
vals | +0.041 |
agg | +0.040 |
shades | +0.040 |
Neg logit contributions | |
Woo | -0.020 |
sled | -0.020 |
wagon | -0.020 |
drown | -0.019 |
Spot | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ways | +0.039 |
ad | +0.037 |
vals | +0.035 |
arom | +0.035 |
od | +0.035 |
Neg logit contributions | |
wagon | -0.026 |
Woo | -0.025 |
lamb | -0.025 |
yacht | -0.025 |
leash | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ement | +0.035 |
arom | +0.035 |
vals | +0.034 |
ways | +0.033 |
ami | +0.033 |
Neg logit contributions | |
Woo | -0.015 |
dog | -0.015 |
leash | -0.015 |
who | -0.014 |
wagon | -0.014 |
Token | know |
Token ID | 760 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ways | +0.035 |
vals | +0.031 |
arom | +0.031 |
br | +0.031 |
od | +0.031 |
Neg logit contributions | |
leash | -0.017 |
wagon | -0.016 |
paddle | -0.016 |
Woo | -0.016 |
yacht | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
ways | +0.030 |
vals | +0.030 |
ad | +0.029 |
arom | +0.029 |
agg | +0.028 |
Neg logit contributions | |
wagon | -0.014 |
who | -0.013 |
leash | -0.013 |
Woo | -0.013 |
sled | -0.013 |
Token | about |
Token ID | 546 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ways | +0.009 |
vals | +0.009 |
arom | +0.008 |
ven | +0.008 |
agg | +0.008 |
Neg logit contributions | |
wagon | -0.006 |
leash | -0.005 |
dog | -0.005 |
lamb | -0.005 |
who | -0.005 |
Token | microsc |
Token ID | 21145 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
ways | +0.020 |
vals | +0.020 |
ven | +0.019 |
ad | +0.019 |
agg | +0.019 |
Neg logit contributions | |
wagon | -0.012 |
Woo | -0.012 |
who | -0.012 |
leash | -0.012 |
dog | -0.012 |
Token | opes |
Token ID | 13920 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
oblig | +0.173 |
br | +0.168 |
ad | +0.164 |
omed | +0.161 |
arom | +0.161 |
Neg logit contributions | |
wagon | -0.064 |
pistols | -0.058 |
bases | -0.057 |
fence | -0.057 |
spears | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-04 |
Pos logit contributions | |
agg | +0.011 |
arom | +0.011 |
von | +0.011 |
ways | +0.011 |
vals | +0.011 |
Neg logit contributions | |
wagon | -0.007 |
who | -0.006 |
yacht | -0.006 |
sled | -0.006 |
leash | -0.006 |
Token | |
Token ID | 220 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ways | +0.001 |
ad | +0.001 |
vals | +0.001 |
od | +0.001 |
ven | +0.001 |
Neg logit contributions | |
Woo | -0.001 |
wagon | -0.001 |
lamb | -0.001 |
leash | -0.001 |
yacht | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
ways | +0.047 |
ad | +0.046 |
arom | +0.044 |
vals | +0.044 |
mastered | +0.043 |
Neg logit contributions | |
Woo | -0.016 |
wagon | -0.015 |
leash | -0.014 |
Spot | -0.014 |
lamb | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ways | +0.006 |
ad | +0.006 |
od | +0.006 |
vals | +0.006 |
ven | +0.006 |
Neg logit contributions | |
Woo | -0.004 |
wagon | -0.004 |
leash | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ways | +0.119 |
ad | +0.111 |
issy | +0.107 |
von | +0.107 |
inda | +0.107 |
Neg logit contributions | |
sled | -0.073 |
dog | -0.066 |
duck | -0.066 |
leash | -0.065 |
ball | -0.064 |
Token | fourteen |
Token ID | 29167 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
ways | +0.050 |
ad | +0.046 |
agg | +0.043 |
mastered | +0.043 |
arom | +0.043 |
Neg logit contributions | |
Woo | -0.054 |
sled | -0.054 |
wagon | -0.052 |
yacht | -0.050 |
paddle | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
ways | +0.089 |
lic | +0.080 |
ad | +0.079 |
von | +0.078 |
books | +0.078 |
Neg logit contributions | |
sled | -0.059 |
wagon | -0.058 |
dog | -0.058 |
yacht | -0.056 |
boat | -0.056 |
Token | fifteen |
Token ID | 17280 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ways | +0.048 |
ad | +0.042 |
agg | +0.040 |
mastered | +0.039 |
arom | +0.039 |
Neg logit contributions | |
sled | -0.067 |
wagon | -0.066 |
Woo | -0.065 |
yacht | -0.065 |
paddle | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
ways | +0.145 |
ad | +0.140 |
issy | +0.138 |
von | +0.137 |
inda | +0.132 |
Neg logit contributions | |
sled | -0.080 |
dog | -0.077 |
slide | -0.075 |
ball | -0.075 |
boat | -0.072 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
ways | +0.056 |
ad | +0.050 |
agg | +0.047 |
mastered | +0.046 |
od | +0.044 |
Neg logit contributions | |
sled | -0.082 |
wagon | -0.081 |
paddle | -0.080 |
yacht | -0.079 |
Woo | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
ways | +0.179 |
issy | +0.175 |
lic | +0.172 |
inda | +0.170 |
von | +0.169 |
Neg logit contributions | |
slide | -0.079 |
ball | -0.076 |
dog | -0.075 |
sled | -0.069 |
fence | -0.069 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
ways | +0.057 |
ad | +0.051 |
agg | +0.048 |
mastered | +0.048 |
od | +0.046 |
Neg logit contributions | |
wagon | -0.086 |
sled | -0.085 |
paddle | -0.084 |
yacht | -0.084 |
leash | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ways | +0.147 |
inda | +0.144 |
issy | +0.140 |
aries | +0.138 |
ary | +0.135 |
Neg logit contributions | |
sled | -0.071 |
dog | -0.069 |
boy | -0.065 |
slide | -0.064 |
ball | -0.063 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ways | +0.053 |
ad | +0.047 |
agg | +0.044 |
mastered | +0.044 |
od | +0.042 |
Neg logit contributions | |
wagon | -0.078 |
sled | -0.078 |
yacht | -0.077 |
paddle | -0.077 |
Woo | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
ways | +0.129 |
ad | +0.120 |
von | +0.117 |
inda | +0.115 |
ol | +0.115 |
Neg logit contributions | |
sled | -0.069 |
dog | -0.065 |
ball | -0.061 |
slide | -0.061 |
who | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ways | +0.011 |
vals | +0.011 |
ad | +0.010 |
br | +0.010 |
mastered | +0.010 |
Neg logit contributions | |
wagon | -0.006 |
Woo | -0.006 |
sled | -0.006 |
yacht | -0.005 |
leash | -0.005 |
Token | tree |
Token ID | 5509 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
ways | +0.022 |
ad | +0.021 |
od | +0.019 |
vals | +0.019 |
ven | +0.019 |
Neg logit contributions | |
wagon | -0.011 |
Woo | -0.011 |
leash | -0.011 |
lamb | -0.010 |
yacht | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.018 |
vals | +0.017 |
agg | +0.017 |
arom | +0.017 |
Neg logit contributions | |
wagon | -0.012 |
leash | -0.012 |
yacht | -0.011 |
raft | -0.011 |
sled | -0.011 |
Token | its |
Token ID | 663 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
ways | +0.020 |
ad | +0.018 |
vals | +0.017 |
od | +0.017 |
ven | +0.017 |
Neg logit contributions | |
Woo | -0.013 |
wagon | -0.013 |
leash | -0.012 |
yacht | -0.012 |
lamb | -0.012 |
Token | once |
Token ID | 1752 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
wagon | +0.002 |
leash | +0.002 |
lamb | +0.002 |
Woo | +0.002 |
mole | +0.002 |
Neg logit contributions | |
ways | -0.004 |
ad | -0.004 |
od | -0.004 |
vals | -0.004 |
ven | -0.004 |
Token | former |
Token ID | 1966 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
vals | +0.002 |
ven | +0.002 |
od | +0.002 |
Neg logit contributions | |
wagon | -0.001 |
lamb | -0.001 |
leash | -0.001 |
sled | -0.001 |
raft | -0.001 |
Token | beauty |
Token ID | 8737 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
od | +0.107 |
ven | +0.103 |
ways | +0.103 |
ad | +0.098 |
lic | +0.098 |
Neg logit contributions | |
wagon | -0.150 |
leash | -0.146 |
bur | -0.140 |
yacht | -0.138 |
raft | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
vals | +0.019 |
ways | +0.019 |
ad | +0.018 |
ven | +0.018 |
arom | +0.018 |
Neg logit contributions | |
wagon | -0.014 |
who | -0.014 |
yacht | -0.014 |
leash | -0.013 |
dog | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
vals | +0.014 |
arom | +0.014 |
ven | +0.014 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.009 |
sled | -0.009 |
yacht | -0.009 |
leash | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
ways | +0.006 |
ad | +0.005 |
vals | +0.005 |
od | +0.005 |
ven | +0.005 |
Neg logit contributions | |
wagon | -0.004 |
lamb | -0.004 |
Woo | -0.004 |
leash | -0.004 |
yacht | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
Woo | +0.006 |
lamb | +0.006 |
leash | +0.005 |
wagon | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
ways | -0.010 |
vals | -0.009 |
ad | -0.009 |
ven | -0.009 |
arom | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ways | +0.123 |
inda | +0.121 |
issy | +0.121 |
ad | +0.120 |
von | +0.119 |
Neg logit contributions | |
sled | -0.076 |
slide | -0.065 |
dog | -0.065 |
boat | -0.064 |
ball | -0.064 |
Token | fourteen |
Token ID | 29167 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
ways | +0.056 |
ad | +0.053 |
agg | +0.053 |
mastered | +0.051 |
arom | +0.050 |
Neg logit contributions | |
sled | -0.055 |
Woo | -0.052 |
wagon | -0.051 |
paddle | -0.049 |
yacht | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
ways | +0.102 |
lic | +0.099 |
von | +0.096 |
inda | +0.095 |
ad | +0.095 |
Neg logit contributions | |
sled | -0.060 |
dog | -0.059 |
boat | -0.058 |
wagon | -0.057 |
boy | -0.056 |
Token | fifteen |
Token ID | 17280 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
ways | +0.056 |
agg | +0.053 |
ad | +0.051 |
oph | +0.049 |
mastered | +0.049 |
Neg logit contributions | |
sled | -0.077 |
wagon | -0.073 |
yacht | -0.071 |
paddle | -0.071 |
dog | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
ad | +0.134 |
ways | +0.133 |
von | +0.132 |
inda | +0.131 |
agg | +0.129 |
Neg logit contributions | |
sled | -0.089 |
boy | -0.085 |
ball | -0.081 |
dog | -0.081 |
slide | -0.080 |
Token | sixteen |
Token ID | 27913 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
ways | +0.064 |
ad | +0.060 |
agg | +0.060 |
mastered | +0.058 |
oph | +0.056 |
Neg logit contributions | |
sled | -0.090 |
wagon | -0.087 |
yacht | -0.085 |
paddle | -0.085 |
boat | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
inda | +0.171 |
agg | +0.167 |
ways | +0.166 |
ema | +0.165 |
lic | +0.165 |
Neg logit contributions | |
boy | -0.084 |
slide | -0.083 |
sled | -0.083 |
ball | -0.082 |
dog | -0.078 |
Token | seventeen |
Token ID | 38741 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
ways | +0.064 |
ad | +0.060 |
agg | +0.058 |
mastered | +0.057 |
od | +0.054 |
Neg logit contributions | |
sled | -0.094 |
wagon | -0.092 |
yacht | -0.090 |
paddle | -0.090 |
boat | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
inda | +0.150 |
ways | +0.146 |
issy | +0.143 |
aries | +0.141 |
ary | +0.141 |
Neg logit contributions | |
sled | -0.075 |
boy | -0.075 |
dog | -0.073 |
slide | -0.068 |
ball | -0.066 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
ways | +0.062 |
ad | +0.057 |
agg | +0.056 |
mastered | +0.055 |
inda | +0.051 |
Neg logit contributions | |
sled | -0.086 |
wagon | -0.084 |
yacht | -0.083 |
paddle | -0.082 |
duck | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ways | +0.129 |
ad | +0.126 |
von | +0.124 |
inda | +0.123 |
ol | +0.122 |
Neg logit contributions | |
sled | -0.072 |
boy | -0.070 |
dog | -0.069 |
who | -0.068 |
ball | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ways | +0.050 |
vals | +0.047 |
agg | +0.045 |
von | +0.044 |
ad | +0.044 |
Neg logit contributions | |
who | -0.040 |
wagon | -0.040 |
leash | -0.039 |
yacht | -0.038 |
Woo | -0.038 |
Token | filled |
Token ID | 5901 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ways | +0.036 |
vals | +0.033 |
ad | +0.032 |
ven | +0.032 |
equations | +0.031 |
Neg logit contributions | |
Woo | -0.021 |
yacht | -0.021 |
leash | -0.021 |
wagon | -0.021 |
lamb | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ways | +0.064 |
ad | +0.059 |
vals | +0.058 |
ven | +0.057 |
mastered | +0.057 |
Neg logit contributions | |
Woo | -0.028 |
wagon | -0.027 |
leash | -0.027 |
yacht | -0.027 |
mole | -0.025 |
Token | delicious |
Token ID | 12625 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
ways | +0.024 |
ven | +0.021 |
vals | +0.021 |
ad | +0.021 |
od | +0.020 |
Neg logit contributions | |
wagon | -0.020 |
Woo | -0.019 |
leash | -0.019 |
yacht | -0.019 |
lamb | -0.019 |
Token | ch |
Token ID | 442 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ways | +0.098 |
ven | +0.090 |
vals | +0.086 |
inda | +0.084 |
ais | +0.082 |
Neg logit contributions | |
wagon | -0.054 |
dog | -0.054 |
lamb | -0.053 |
puppy | -0.053 |
mole | -0.052 |
Token | ocol |
Token ID | 4668 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
ways | +0.031 |
ven | +0.029 |
books | +0.029 |
oph | +0.028 |
equations | +0.027 |
Neg logit contributions | |
lamb | -0.028 |
arl | -0.028 |
mole | -0.026 |
leash | -0.025 |
duck | -0.025 |
Token | ates |
Token ID | 689 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ways | +0.152 |
equations | +0.134 |
mastered | +0.133 |
arom | +0.129 |
oph | +0.122 |
Neg logit contributions | |
sled | -0.105 |
Spot | -0.099 |
amb | -0.099 |
mole | -0.098 |
ich | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
ways | +0.019 |
ad | +0.017 |
vals | +0.016 |
arom | +0.016 |
ven | +0.016 |
Neg logit contributions | |
yacht | -0.021 |
leash | -0.021 |
wagon | -0.021 |
Woo | -0.021 |
sled | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
ways | +0.012 |
ad | +0.011 |
vals | +0.010 |
od | +0.010 |
ven | +0.010 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.008 |
leash | -0.008 |
lamb | -0.008 |
yacht | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +5.53e-04 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
vals | +0.013 |
od | +0.013 |
ven | +0.013 |
Neg logit contributions | |
wagon | -0.010 |
Woo | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
leash | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
Woo | +0.001 |
leash | +0.001 |
lamb | +0.001 |
wagon | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
vals | -0.001 |
ven | -0.001 |
arom | -0.001 |
Token | something |
Token ID | 1223 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
ways | +0.012 |
vals | +0.012 |
ven | +0.011 |
arom | +0.011 |
mastered | +0.011 |
Neg logit contributions | |
Woo | -0.006 |
who | -0.006 |
mole | -0.006 |
duck | -0.006 |
dog | -0.006 |
Token | new |
Token ID | 649 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ways | +0.009 |
ad | +0.009 |
vals | +0.009 |
ven | +0.008 |
ami | +0.008 |
Neg logit contributions | |
wagon | -0.006 |
leash | -0.006 |
yacht | -0.006 |
raft | -0.006 |
lamb | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ways | +0.023 |
vals | +0.022 |
ad | +0.021 |
ven | +0.021 |
arom | +0.021 |
Neg logit contributions | |
wagon | -0.013 |
mole | -0.013 |
leash | -0.013 |
lamb | -0.013 |
sled | -0.013 |
Token | there |
Token ID | 612 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ways | +0.030 |
ad | +0.027 |
arom | +0.026 |
vals | +0.026 |
mastered | +0.026 |
Neg logit contributions | |
Woo | -0.028 |
lamb | -0.027 |
mole | -0.027 |
yacht | -0.027 |
wagon | -0.027 |
Token | were |
Token ID | 547 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ways | +0.024 |
vals | +0.022 |
ven | +0.021 |
ad | +0.021 |
arom | +0.021 |
Neg logit contributions | |
leash | -0.018 |
wagon | -0.018 |
Woo | -0.018 |
yacht | -0.017 |
mole | -0.017 |
Token | tad |
Token ID | 36264 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
ways | +0.039 |
vals | +0.037 |
ad | +0.036 |
ven | +0.035 |
arom | +0.035 |
Neg logit contributions | |
yacht | -0.024 |
wagon | -0.024 |
raft | -0.024 |
leash | -0.024 |
Woo | -0.023 |
Token | p |
Token ID | 79 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ways | +0.123 |
ad | +0.112 |
ven | +0.112 |
arom | +0.105 |
mastered | +0.105 |
Neg logit contributions | |
lamb | -0.137 |
leash | -0.135 |
mole | -0.132 |
raft | -0.129 |
paddle | -0.127 |
Token | oles |
Token ID | 4316 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ways | +0.053 |
equations | +0.052 |
subtract | +0.048 |
ven | +0.048 |
subt | +0.047 |
Neg logit contributions | |
duck | -0.054 |
lamb | -0.053 |
leash | -0.052 |
raft | -0.052 |
sled | -0.051 |
Token | swimming |
Token ID | 14899 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
ways | +0.024 |
ad | +0.022 |
od | +0.020 |
vals | +0.020 |
ven | +0.020 |
Neg logit contributions | |
Woo | -0.026 |
wagon | -0.026 |
leash | -0.025 |
lamb | -0.025 |
yacht | -0.025 |
Token | around |
Token ID | 1088 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
wagon | +0.009 |
Woo | +0.009 |
leash | +0.009 |
yacht | +0.009 |
raft | +0.009 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.016 |
vals | -0.016 |
ven | -0.015 |
mastered | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
Woo | +0.017 |
wagon | +0.017 |
mole | +0.017 |
yacht | +0.017 |
leash | +0.017 |
Neg logit contributions | |
ways | -0.022 |
vals | -0.020 |
ad | -0.019 |
ven | -0.019 |
mastered | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
ways | +0.019 |
ad | +0.018 |
vals | +0.018 |
agg | +0.018 |
mastered | +0.018 |
Neg logit contributions | |
wagon | -0.011 |
Woo | -0.010 |
sled | -0.010 |
yacht | -0.010 |
duck | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
agg | +0.026 |
oph | +0.026 |
ad | +0.025 |
arom | +0.025 |
ways | +0.025 |
Neg logit contributions | |
wagon | -0.019 |
leash | -0.018 |
sled | -0.018 |
who | -0.018 |
ball | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.004 |
od | +0.004 |
vals | +0.004 |
ven | +0.004 |
Neg logit contributions | |
wagon | -0.003 |
leash | -0.003 |
Woo | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ways | +0.012 |
ad | +0.011 |
arom | +0.010 |
vals | +0.010 |
agg | +0.010 |
Neg logit contributions | |
wagon | -0.009 |
Woo | -0.009 |
yacht | -0.009 |
paddle | -0.009 |
sled | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
ways | +0.086 |
ven | +0.078 |
vals | +0.077 |
ad | +0.077 |
mastered | +0.076 |
Neg logit contributions | |
wagon | -0.058 |
sled | -0.057 |
Woo | -0.057 |
yacht | -0.056 |
raft | -0.055 |
Token | gar |
Token ID | 5482 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
Woo | +0.004 |
wagon | +0.004 |
lamb | +0.004 |
leash | +0.004 |
yacht | +0.004 |
Neg logit contributions | |
ways | -0.006 |
ad | -0.005 |
vals | -0.005 |
od | -0.005 |
arom | -0.005 |
Token | land |
Token ID | 1044 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
mastered | +0.115 |
ways | +0.110 |
equations | +0.108 |
ement | +0.106 |
oph | +0.106 |
Neg logit contributions | |
leash | -0.118 |
sled | -0.116 |
paddle | -0.111 |
boat | -0.107 |
who | -0.107 |
Token | with |
Token ID | 351 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
viously | +0.059 |
agg | +0.059 |
subtract | +0.057 |
von | +0.057 |
ad | +0.056 |
Neg logit contributions | |
dog | -0.032 |
who | -0.032 |
boat | -0.029 |
where | -0.028 |
under | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ways | +0.003 |
ven | +0.003 |
agg | +0.003 |
vals | +0.003 |
oph | +0.003 |
Neg logit contributions | |
wagon | -0.002 |
Woo | -0.002 |
sled | -0.002 |
yacht | -0.002 |
duck | -0.001 |
Token | string |
Token ID | 4731 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.021 |
Woo | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
ways | -0.038 |
ad | -0.036 |
od | -0.033 |
ven | -0.033 |
agg | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
wagon | +0.033 |
leash | +0.033 |
yacht | +0.032 |
sled | +0.032 |
Woo | +0.032 |
Neg logit contributions | |
ways | -0.033 |
ad | -0.030 |
agg | -0.028 |
arom | -0.028 |
ven | -0.028 |
Token | number |
Token ID | 1271 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ways | +0.049 |
ad | +0.046 |
agg | +0.044 |
od | +0.043 |
vals | +0.043 |
Neg logit contributions | |
wagon | -0.023 |
leash | -0.021 |
sled | -0.020 |
yacht | -0.020 |
pistol | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
ways | +0.031 |
agg | +0.030 |
ad | +0.029 |
arom | +0.029 |
von | +0.028 |
Neg logit contributions | |
wagon | -0.028 |
sled | -0.028 |
boat | -0.027 |
yacht | -0.027 |
who | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ad | +0.014 |
arom | +0.014 |
vals | +0.014 |
ways | +0.014 |
od | +0.013 |
Neg logit contributions | |
Woo | -0.006 |
wagon | -0.006 |
sled | -0.006 |
dog | -0.006 |
leash | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
Woo | +0.016 |
wagon | +0.016 |
yacht | +0.016 |
leash | +0.015 |
lamb | +0.015 |
Neg logit contributions | |
ways | -0.035 |
ad | -0.033 |
vals | -0.031 |
od | -0.031 |
ven | -0.031 |
Token | weigh |
Token ID | 10164 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Woo | +0.022 |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.041 |
vals | -0.039 |
od | -0.039 |
ven | -0.039 |
Token | 40 |
Token ID | 2319 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
ways | +0.034 |
ad | +0.031 |
mastered | +0.031 |
agg | +0.031 |
arom | +0.030 |
Neg logit contributions | |
sled | -0.020 |
leash | -0.019 |
wagon | -0.019 |
Woo | -0.019 |
yacht | -0.018 |
Token | pounds |
Token ID | 8059 |
Feature activation | +4.87e-04 |
Pos logit contributions | |
von | +0.139 |
ad | +0.139 |
ways | +0.138 |
oph | +0.127 |
mastered | +0.125 |
Neg logit contributions | |
sled | -0.115 |
who | -0.105 |
wagon | -0.096 |
boat | -0.095 |
horse | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
sled | +0.001 |
wagon | +0.001 |
leash | +0.001 |
Woo | +0.001 |
dog | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
agg | -0.001 |
arom | -0.001 |
vals | -0.001 |
Token | That |
Token ID | 1320 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
ways | +0.010 |
ad | +0.010 |
arom | +0.009 |
vals | +0.009 |
od | +0.009 |
Neg logit contributions | |
Woo | -0.007 |
wagon | -0.006 |
leash | -0.006 |
lamb | -0.006 |
yacht | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
wagon | +0.010 |
sled | +0.010 |
bicycle | +0.009 |
yacht | +0.009 |
dog | +0.009 |
Neg logit contributions | |
ways | -0.016 |
ad | -0.015 |
agg | -0.014 |
von | -0.013 |
mastered | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ways | +0.057 |
agg | +0.052 |
ad | +0.051 |
od | +0.049 |
ement | +0.049 |
Neg logit contributions | |
sled | -0.037 |
leash | -0.036 |
wagon | -0.036 |
paddle | -0.034 |
raft | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
ways | +0.048 |
ad | +0.047 |
agg | +0.047 |
arom | +0.046 |
vals | +0.045 |
Neg logit contributions | |
Woo | -0.032 |
leash | -0.030 |
wagon | -0.030 |
dog | -0.029 |
Spot | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
Woo | +0.004 |
wagon | +0.004 |
yacht | +0.004 |
paddle | +0.003 |
leash | +0.003 |
Neg logit contributions | |
ways | -0.005 |
ad | -0.005 |
agg | -0.004 |
od | -0.004 |
vals | -0.004 |
Token | h |
Token ID | 71 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
Woo | +0.012 |
Spot | +0.012 |
leash | +0.012 |
wagon | +0.012 |
lamb | +0.012 |
Neg logit contributions | |
ways | -0.020 |
ad | -0.018 |
arom | -0.017 |
agg | -0.017 |
mastered | -0.017 |
Token | ocus |
Token ID | 10901 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
ways | +0.067 |
arom | +0.064 |
equations | +0.061 |
shades | +0.059 |
ement | +0.059 |
Neg logit contributions | |
arl | -0.052 |
sled | -0.048 |
paddle | -0.046 |
leash | -0.046 |
Woo | -0.046 |
Token | p |
Token ID | 279 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ways | +0.131 |
ad | +0.122 |
ami | +0.119 |
vals | +0.119 |
agg | +0.116 |
Neg logit contributions | |
duck | -0.093 |
Woo | -0.088 |
sled | -0.088 |
wagon | -0.088 |
yacht | -0.087 |
Token | ocus |
Token ID | 10901 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
arom | +0.045 |
ad | +0.044 |
ways | +0.044 |
agg | +0.043 |
Maria | +0.042 |
Neg logit contributions | |
arl | -0.038 |
sled | -0.037 |
Woo | -0.033 |
paddle | -0.032 |
iffs | -0.032 |
Token | ". |
Token ID | 1911 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ways | +0.146 |
ad | +0.141 |
ami | +0.137 |
vals | +0.136 |
agg | +0.135 |
Neg logit contributions | |
duck | -0.097 |
Woo | -0.096 |
leash | -0.095 |
sled | -0.094 |
wagon | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
ways | +0.035 |
vals | +0.034 |
ad | +0.033 |
br | +0.032 |
arom | +0.032 |
Neg logit contributions | |
Woo | -0.018 |
wagon | -0.016 |
leash | -0.015 |
yacht | -0.015 |
Spot | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.004 |
vals | +0.004 |
arom | +0.004 |
mastered | +0.004 |
Neg logit contributions | |
Woo | -0.002 |
wagon | -0.002 |
leash | -0.002 |
Spot | -0.002 |
sled | -0.002 |
Token | But |
Token ID | 1537 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
ways | +0.007 |
ad | +0.007 |
vals | +0.006 |
arom | +0.006 |
od | +0.006 |
Neg logit contributions | |
Woo | -0.005 |
wagon | -0.005 |
leash | -0.005 |
lamb | -0.005 |
yacht | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.60e-04 |
Pos logit contributions | |
Woo | +0.007 |
wagon | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
leash | +0.007 |
Neg logit contributions | |
ways | -0.011 |
ad | -0.011 |
vals | -0.010 |
br | -0.010 |
mastered | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
inda | +0.150 |
ways | +0.146 |
issy | +0.143 |
aries | +0.141 |
ary | +0.141 |
Neg logit contributions | |
sled | -0.075 |
boy | -0.075 |
dog | -0.073 |
slide | -0.068 |
ball | -0.066 |
Token | eighteen |
Token ID | 29095 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
ways | +0.062 |
ad | +0.057 |
agg | +0.056 |
mastered | +0.055 |
inda | +0.051 |
Neg logit contributions | |
sled | -0.086 |
wagon | -0.084 |
yacht | -0.083 |
paddle | -0.082 |
duck | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ways | +0.129 |
ad | +0.126 |
von | +0.124 |
inda | +0.123 |
ol | +0.122 |
Neg logit contributions | |
sled | -0.072 |
boy | -0.070 |
dog | -0.069 |
who | -0.068 |
ball | -0.064 |
Token | nineteen |
Token ID | 43063 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
ways | +0.060 |
ad | +0.055 |
agg | +0.054 |
mastered | +0.053 |
oph | +0.049 |
Neg logit contributions | |
sled | -0.081 |
wagon | -0.079 |
yacht | -0.078 |
paddle | -0.077 |
boat | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
ways | +0.152 |
ad | +0.149 |
aries | +0.144 |
issy | +0.142 |
von | +0.141 |
Neg logit contributions | |
who | -0.082 |
sled | -0.079 |
wagon | -0.078 |
boy | -0.078 |
boat | -0.076 |
Token | twenty |
Token ID | 8208 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
ways | +0.054 |
ad | +0.051 |
agg | +0.046 |
mastered | +0.046 |
books | +0.045 |
Neg logit contributions | |
sled | -0.081 |
wagon | -0.079 |
paddle | -0.078 |
yacht | -0.077 |
boat | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ways | +0.132 |
von | +0.131 |
ad | +0.130 |
oph | +0.127 |
mastered | +0.123 |
Neg logit contributions | |
sled | -0.103 |
boy | -0.103 |
who | -0.097 |
boat | -0.096 |
truck | -0.093 |
Token | They |
Token ID | 1119 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ways | +0.029 |
ad | +0.028 |
arom | +0.027 |
vals | +0.026 |
mastered | +0.026 |
Neg logit contributions | |
Woo | -0.016 |
wagon | -0.015 |
leash | -0.014 |
yacht | -0.014 |
mole | -0.014 |
Token | are |
Token ID | 389 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ways | +0.055 |
agg | +0.049 |
arom | +0.049 |
ad | +0.049 |
ement | +0.048 |
Neg logit contributions | |
paddle | -0.021 |
sled | -0.019 |
wagon | -0.019 |
yacht | -0.018 |
slide | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
ways | +0.035 |
ad | +0.033 |
ol | +0.033 |
omed | +0.032 |
ides | +0.032 |
Neg logit contributions | |
sled | -0.009 |
leash | -0.009 |
yacht | -0.009 |
dog | -0.009 |
wagon | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.004 |
ven | +0.004 |
vals | +0.004 |
br | +0.004 |
Neg logit contributions | |
dog | -0.004 |
sled | -0.004 |
yacht | -0.004 |
Woo | -0.004 |
wagon | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ways | +0.031 |
ad | +0.028 |
vals | +0.027 |
ven | +0.027 |
mastered | +0.026 |
Neg logit contributions | |
Woo | -0.022 |
wagon | -0.021 |
yacht | -0.021 |
lamb | -0.021 |
leash | -0.020 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ways | +0.027 |
ad | +0.025 |
vals | +0.024 |
ven | +0.023 |
br | +0.023 |
Neg logit contributions | |
Woo | -0.024 |
yacht | -0.023 |
paddle | -0.023 |
wagon | -0.023 |
sled | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
ways | +0.022 |
vals | +0.021 |
ad | +0.021 |
ven | +0.020 |
agg | +0.019 |
Neg logit contributions | |
wagon | -0.017 |
Woo | -0.016 |
dog | -0.016 |
yacht | -0.016 |
leash | -0.016 |
Token | ate |
Token ID | 15063 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Woo | +0.009 |
leash | +0.009 |
yacht | +0.009 |
wagon | +0.009 |
paddle | +0.008 |
Neg logit contributions | |
ways | -0.011 |
ad | -0.010 |
vals | -0.010 |
od | -0.010 |
ven | -0.010 |
Token | ch |
Token ID | 442 |
Feature activation | -9.07e-03 |
Pos logit contributions | |
ways | +0.030 |
ad | +0.029 |
vals | +0.028 |
ven | +0.027 |
mastered | +0.026 |
Neg logit contributions | |
wagon | -0.021 |
Woo | -0.021 |
sled | -0.020 |
yacht | -0.020 |
leash | -0.020 |
Token | ocol |
Token ID | 4668 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
ways | +0.014 |
ven | +0.012 |
oph | +0.012 |
mastered | +0.011 |
equations | +0.011 |
Neg logit contributions | |
arl | -0.016 |
sled | -0.014 |
paddle | -0.014 |
Woo | -0.014 |
duck | -0.014 |
Token | ates |
Token ID | 689 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
ways | +0.140 |
mastered | +0.121 |
arom | +0.118 |
equations | +0.117 |
oph | +0.112 |
Neg logit contributions | |
sled | -0.111 |
Spot | -0.109 |
burn | -0.101 |
amb | -0.099 |
arl | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.013 |
agg | +0.012 |
equations | +0.012 |
Neg logit contributions | |
sled | -0.013 |
leash | -0.012 |
yacht | -0.012 |
Woo | -0.012 |
wagon | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -2.55e-03 |
Pos logit contributions | |
ways | +0.006 |
ad | +0.006 |
od | +0.005 |
vals | +0.005 |
arom | +0.005 |
Neg logit contributions | |
wagon | -0.004 |
leash | -0.004 |
Woo | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.004 |
vals | +0.004 |
od | +0.004 |
ven | +0.004 |
Neg logit contributions | |
Woo | -0.004 |
wagon | -0.003 |
leash | -0.003 |
yacht | -0.003 |
lamb | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ways | +0.007 |
ement | +0.007 |
vals | +0.007 |
ad | +0.007 |
ven | +0.006 |
Neg logit contributions | |
Woo | -0.004 |
sled | -0.004 |
leash | -0.004 |
Spot | -0.004 |
dog | -0.004 |
Token | glad |
Token ID | 9675 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
ways | +0.003 |
vals | +0.003 |
equations | +0.003 |
ad | +0.003 |
arom | +0.003 |
Neg logit contributions | |
Woo | -0.001 |
lamb | -0.001 |
leash | -0.001 |
yacht | -0.001 |
mole | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +8.58e-03 |
Pos logit contributions | |
Woo | +0.011 |
lamb | +0.010 |
wagon | +0.010 |
leash | +0.010 |
yacht | +0.009 |
Neg logit contributions | |
ways | -0.020 |
ad | -0.019 |
vals | -0.018 |
ven | -0.018 |
od | -0.018 |
Token | could |
Token ID | 714 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Woo | +0.011 |
leash | +0.010 |
wagon | +0.010 |
paddle | +0.010 |
lamb | +0.010 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.015 |
vals | -0.015 |
arom | -0.014 |
equations | -0.014 |
Token | help |
Token ID | 1037 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ways | +0.031 |
ad | +0.027 |
arom | +0.027 |
vals | +0.027 |
od | +0.026 |
Neg logit contributions | |
leash | -0.016 |
wagon | -0.016 |
Woo | -0.016 |
paddle | -0.016 |
sled | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
ways | +0.023 |
vals | +0.021 |
ad | +0.020 |
agg | +0.020 |
mastered | +0.020 |
Neg logit contributions | |
Woo | -0.013 |
leash | -0.013 |
lamb | -0.012 |
dog | -0.012 |
wagon | -0.012 |
Token | tad |
Token ID | 36264 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
vals | +0.013 |
od | +0.013 |
ven | +0.013 |
Neg logit contributions | |
Woo | -0.009 |
wagon | -0.009 |
leash | -0.009 |
lamb | -0.009 |
yacht | -0.009 |
Token | p |
Token ID | 79 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
ways | +0.133 |
ad | +0.124 |
ven | +0.116 |
mastered | +0.114 |
arom | +0.113 |
Neg logit contributions | |
lamb | -0.124 |
leash | -0.123 |
wagon | -0.119 |
mole | -0.119 |
yacht | -0.118 |
Token | oles |
Token ID | 4316 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ways | +0.051 |
ad | +0.046 |
arom | +0.044 |
ven | +0.043 |
equations | +0.043 |
Neg logit contributions | |
leash | -0.042 |
lamb | -0.041 |
wagon | -0.041 |
yacht | -0.040 |
raft | -0.040 |
Token | ". |
Token ID | 1911 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
ways | +0.032 |
ad | +0.030 |
od | +0.028 |
vals | +0.028 |
ven | +0.027 |
Neg logit contributions | |
Woo | -0.031 |
wagon | -0.031 |
leash | -0.031 |
lamb | -0.030 |
yacht | -0.030 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.40e-04 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.012 |
ven | +0.012 |
arom | +0.012 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.007 |
leash | -0.007 |
lamb | -0.007 |
yacht | -0.007 |
Token | One |
Token ID | 3198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
Woo | +0.001 |
Spot | +0.001 |
wagon | +0.001 |
dog | +0.001 |
lamb | +0.001 |
Neg logit contributions | |
ways | -0.002 |
vals | -0.002 |
ad | -0.002 |
arom | -0.002 |
ven | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.001 |
od | +0.001 |
ven | +0.001 |
vals | +0.001 |
Neg logit contributions | |
Woo | -0.001 |
wagon | -0.001 |
leash | -0.001 |
lamb | -0.001 |
yacht | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
Woo | +0.018 |
wagon | +0.017 |
lamb | +0.017 |
leash | +0.017 |
yacht | +0.017 |
Neg logit contributions | |
ways | -0.027 |
ad | -0.025 |
arom | -0.023 |
br | -0.023 |
mastered | -0.023 |
Token | box |
Token ID | 3091 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
Woo | +0.028 |
wagon | +0.027 |
leash | +0.027 |
lamb | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.041 |
arom | -0.038 |
vals | -0.038 |
od | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.012 |
arom | +0.012 |
agg | +0.012 |
Neg logit contributions | |
wagon | -0.018 |
leash | -0.018 |
yacht | -0.018 |
Woo | -0.018 |
mole | -0.017 |
Token | ch |
Token ID | 442 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
ways | +0.042 |
ad | +0.039 |
arom | +0.036 |
vals | +0.036 |
od | +0.036 |
Neg logit contributions | |
Woo | -0.035 |
wagon | -0.033 |
leash | -0.033 |
lamb | -0.033 |
yacht | -0.033 |
Token | ocol |
Token ID | 4668 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
wagon | +0.004 |
leash | +0.004 |
mole | +0.004 |
lamb | +0.004 |
arl | +0.004 |
Neg logit contributions | |
ways | -0.003 |
books | -0.003 |
arom | -0.003 |
ven | -0.003 |
bows | -0.003 |
Token | ates |
Token ID | 689 |
Feature activation | -3.40e-04 |
Pos logit contributions | |
ways | +0.132 |
mastered | +0.113 |
arom | +0.112 |
equations | +0.112 |
von | +0.103 |
Neg logit contributions | |
sled | -0.116 |
leash | -0.111 |
Spot | -0.107 |
arl | -0.106 |
wagon | -0.106 |
Token | ! |
Token ID | 0 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
ways | +0.000 |
ad | +0.000 |
vals | +0.000 |
arom | +0.000 |
agg | +0.000 |
Neg logit contributions | |
wagon | -0.001 |
leash | -0.001 |
yacht | -0.001 |
Woo | -0.001 |
sled | -0.001 |
Token | |
Token ID | 220 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.017 |
vals | +0.017 |
ven | +0.017 |
br | +0.016 |
Neg logit contributions | |
Woo | -0.011 |
wagon | -0.011 |
dog | -0.010 |
lamb | -0.010 |
mole | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
ways | +0.048 |
ad | +0.046 |
arom | +0.045 |
vals | +0.045 |
mastered | +0.043 |
Neg logit contributions | |
Woo | -0.019 |
wagon | -0.018 |
leash | -0.017 |
Spot | -0.017 |
sled | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
wagon | +0.010 |
yacht | +0.010 |
lamb | +0.010 |
Woo | +0.010 |
leash | +0.010 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
od | -0.013 |
agg | -0.013 |
ven | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.023 |
vals | +0.023 |
arom | +0.022 |
od | +0.022 |
Neg logit contributions | |
sled | -0.010 |
paddle | -0.010 |
wagon | -0.010 |
raft | -0.009 |
dog | -0.009 |
Token | see |
Token ID | 766 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
ways | +0.030 |
ad | +0.028 |
vals | +0.027 |
arom | +0.027 |
od | +0.026 |
Neg logit contributions | |
wagon | -0.016 |
Woo | -0.016 |
leash | -0.016 |
sled | -0.015 |
paddle | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ways | +0.071 |
ad | +0.066 |
vals | +0.061 |
od | +0.061 |
ven | +0.060 |
Neg logit contributions | |
Woo | -0.057 |
wagon | -0.057 |
leash | -0.056 |
lamb | -0.055 |
yacht | -0.055 |
Token | land |
Token ID | 1956 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
ways | +0.046 |
ad | +0.043 |
vals | +0.040 |
od | +0.040 |
ven | +0.039 |
Neg logit contributions | |
wagon | -0.038 |
leash | -0.037 |
Woo | -0.037 |
lamb | -0.036 |
sled | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
vals | +0.015 |
arom | +0.015 |
agg | +0.015 |
ways | +0.015 |
ad | +0.015 |
Neg logit contributions | |
yacht | -0.011 |
wagon | -0.011 |
raft | -0.011 |
boat | -0.011 |
sled | -0.010 |
Token | Imp |
Token ID | 9855 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
ways | +0.027 |
ad | +0.025 |
vals | +0.024 |
od | +0.023 |
ven | +0.023 |
Neg logit contributions | |
Woo | -0.020 |
wagon | -0.020 |
leash | -0.020 |
lamb | -0.019 |
yacht | -0.019 |
Token | ressive |
Token ID | 3314 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
br | +0.113 |
lic | +0.110 |
ways | +0.110 |
mastered | +0.105 |
agg | +0.104 |
Neg logit contributions | |
bike | -0.116 |
Spot | -0.107 |
forth | -0.107 |
paddle | -0.104 |
sled | -0.104 |
Token | Things |
Token ID | 11597 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
agg | +0.041 |
ways | +0.040 |
vals | +0.039 |
ad | +0.039 |
ais | +0.038 |
Neg logit contributions | |
wagon | -0.045 |
dog | -0.044 |
sled | -0.043 |
hill | -0.043 |
boat | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.015 |
agg | +0.014 |
vals | +0.014 |
arom | +0.014 |
Neg logit contributions | |
yacht | -0.014 |
wagon | -0.014 |
Woo | -0.014 |
leash | -0.013 |
paddle | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.012 |
arom | +0.012 |
od | +0.012 |
Neg logit contributions | |
Woo | -0.009 |
wagon | -0.009 |
leash | -0.009 |
lamb | -0.009 |
sled | -0.009 |
Token | definitely |
Token ID | 4753 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ways | +0.028 |
ad | +0.026 |
vals | +0.025 |
agg | +0.025 |
ami | +0.025 |
Neg logit contributions | |
wagon | -0.018 |
raft | -0.017 |
paddle | -0.017 |
sled | -0.017 |
yacht | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ways | +0.094 |
ad | +0.094 |
von | +0.087 |
mastered | +0.085 |
inda | +0.085 |
Neg logit contributions | |
sled | -0.068 |
yacht | -0.067 |
boat | -0.067 |
horse | -0.065 |
duck | -0.065 |
Token | 8 |
Token ID | 807 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
ways | +0.050 |
ad | +0.047 |
mastered | +0.044 |
vals | +0.043 |
agg | +0.043 |
Neg logit contributions | |
wagon | -0.046 |
Woo | -0.045 |
sled | -0.045 |
yacht | -0.045 |
leash | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ways | +0.105 |
ad | +0.105 |
von | +0.097 |
mastered | +0.094 |
oph | +0.093 |
Neg logit contributions | |
sled | -0.077 |
who | -0.073 |
boat | -0.073 |
yacht | -0.072 |
duck | -0.072 |
Token | 7 |
Token ID | 767 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
ways | +0.054 |
ad | +0.050 |
mastered | +0.046 |
arom | +0.046 |
vals | +0.045 |
Neg logit contributions | |
wagon | -0.055 |
Woo | -0.054 |
sled | -0.054 |
leash | -0.054 |
yacht | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ways | +0.118 |
ad | +0.118 |
von | +0.111 |
oph | +0.109 |
inda | +0.107 |
Neg logit contributions | |
sled | -0.077 |
who | -0.075 |
dog | -0.073 |
horse | -0.073 |
boat | -0.072 |
Token | 6 |
Token ID | 718 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
ways | +0.056 |
ad | +0.051 |
mastered | +0.048 |
arom | +0.047 |
agg | +0.047 |
Neg logit contributions | |
wagon | -0.054 |
Woo | -0.054 |
sled | -0.054 |
leash | -0.053 |
lamb | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
ways | +0.142 |
ad | +0.140 |
inda | +0.136 |
von | +0.135 |
oph | +0.135 |
Neg logit contributions | |
sled | -0.106 |
who | -0.099 |
boat | -0.095 |
dog | -0.095 |
horse | -0.094 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
ways | +0.063 |
ad | +0.059 |
mastered | +0.054 |
agg | +0.054 |
od | +0.053 |
Neg logit contributions | |
wagon | -0.066 |
sled | -0.066 |
Woo | -0.065 |
leash | -0.065 |
lamb | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
ad | +0.109 |
ways | +0.107 |
von | +0.101 |
oph | +0.099 |
agg | +0.097 |
Neg logit contributions | |
sled | -0.068 |
who | -0.068 |
horse | -0.067 |
dog | -0.067 |
boat | -0.066 |
Token | 4 |
Token ID | 604 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
ways | +0.061 |
ad | +0.056 |
mastered | +0.052 |
agg | +0.052 |
arom | +0.051 |
Neg logit contributions | |
wagon | -0.061 |
sled | -0.061 |
Woo | -0.060 |
leash | -0.060 |
lamb | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
ways | +0.130 |
ad | +0.125 |
von | +0.121 |
inda | +0.118 |
mastered | +0.116 |
Neg logit contributions | |
who | -0.080 |
sled | -0.080 |
dog | -0.078 |
horse | -0.077 |
boat | -0.076 |
Token | It |
Token ID | 632 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ways | +0.054 |
ad | +0.051 |
vals | +0.050 |
ven | +0.049 |
arom | +0.048 |
Neg logit contributions | |
Woo | -0.039 |
wagon | -0.036 |
lamb | -0.035 |
mole | -0.034 |
yacht | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ways | +0.069 |
vals | +0.066 |
ides | +0.063 |
ad | +0.063 |
sentences | +0.062 |
Neg logit contributions | |
wagon | -0.029 |
mole | -0.028 |
puppy | -0.027 |
duck | -0.027 |
Woo | -0.027 |
Token | filled |
Token ID | 5901 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ways | +0.072 |
vals | +0.069 |
ides | +0.067 |
ven | +0.065 |
ce | +0.062 |
Neg logit contributions | |
Woo | -0.041 |
wagon | -0.038 |
puppy | -0.037 |
yacht | -0.037 |
mole | -0.036 |
Token | with |
Token ID | 351 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
ways | +0.076 |
vals | +0.071 |
ad | +0.069 |
mastered | +0.069 |
br | +0.069 |
Neg logit contributions | |
Woo | -0.025 |
leash | -0.023 |
yacht | -0.023 |
wagon | -0.023 |
mole | -0.022 |
Token | ch |
Token ID | 442 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ways | +0.047 |
ven | +0.043 |
vals | +0.042 |
ad | +0.042 |
od | +0.040 |
Neg logit contributions | |
wagon | -0.036 |
Woo | -0.036 |
yacht | -0.035 |
leash | -0.035 |
lamb | -0.035 |
Token | ocol |
Token ID | 4668 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
ways | +0.028 |
ven | +0.025 |
books | +0.025 |
bows | +0.024 |
oph | +0.023 |
Neg logit contributions | |
arl | -0.028 |
wagon | -0.027 |
yacht | -0.027 |
paddle | -0.027 |
leash | -0.027 |
Token | ates |
Token ID | 689 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
ways | +0.137 |
mastered | +0.117 |
arom | +0.116 |
equations | +0.114 |
von | +0.108 |
Neg logit contributions | |
sled | -0.107 |
Spot | -0.102 |
mole | -0.098 |
pistols | -0.097 |
reins | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ways | +0.032 |
ad | +0.030 |
vals | +0.030 |
agg | +0.029 |
equations | +0.029 |
Neg logit contributions | |
yacht | -0.022 |
wagon | -0.022 |
leash | -0.021 |
sled | -0.021 |
raft | -0.021 |
Token | coins |
Token ID | 10796 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
ways | +0.031 |
ad | +0.030 |
ven | +0.029 |
vals | +0.028 |
agg | +0.028 |
Neg logit contributions | |
Woo | -0.025 |
wagon | -0.024 |
yacht | -0.024 |
mole | -0.024 |
leash | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ways | +0.004 |
agg | +0.003 |
ad | +0.003 |
vals | +0.003 |
arom | +0.003 |
Neg logit contributions | |
yacht | -0.004 |
leash | -0.004 |
wagon | -0.004 |
paddle | -0.004 |
raft | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ways | +0.026 |
ad | +0.024 |
ven | +0.023 |
br | +0.023 |
vals | +0.023 |
Neg logit contributions | |
Woo | -0.019 |
lamb | -0.018 |
wagon | -0.018 |
mole | -0.017 |
yacht | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
vals | +0.019 |
ways | +0.018 |
br | +0.018 |
centimeters | +0.018 |
iddles | +0.017 |
Neg logit contributions | |
who | -0.007 |
dog | -0.006 |
there | -0.006 |
duck | -0.006 |
boy | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ways | +0.035 |
vals | +0.035 |
ad | +0.034 |
ides | +0.033 |
ami | +0.032 |
Neg logit contributions | |
wagon | -0.020 |
Woo | -0.020 |
leash | -0.018 |
who | -0.018 |
Spot | -0.018 |
Token | box |
Token ID | 3091 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
wagon | +0.020 |
leash | +0.020 |
Woo | +0.020 |
lamb | +0.019 |
yacht | +0.019 |
Neg logit contributions | |
ways | -0.030 |
ad | -0.028 |
vals | -0.026 |
od | -0.026 |
ven | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ways | +0.033 |
ad | +0.031 |
vals | +0.029 |
arom | +0.029 |
ven | +0.029 |
Neg logit contributions | |
wagon | -0.031 |
leash | -0.031 |
yacht | -0.031 |
Woo | -0.030 |
lamb | -0.030 |
Token | ch |
Token ID | 442 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
ways | +0.061 |
ad | +0.057 |
vals | +0.053 |
ven | +0.053 |
od | +0.053 |
Neg logit contributions | |
wagon | -0.051 |
Woo | -0.050 |
leash | -0.050 |
yacht | -0.049 |
lamb | -0.049 |
Token | ocol |
Token ID | 4668 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
ways | +0.005 |
books | +0.005 |
bows | +0.005 |
ven | +0.005 |
lit | +0.004 |
Neg logit contributions | |
arl | -0.005 |
lamb | -0.005 |
wagon | -0.005 |
leash | -0.005 |
mole | -0.005 |
Token | ates |
Token ID | 689 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
ways | +0.131 |
arom | +0.114 |
mastered | +0.114 |
equations | +0.108 |
von | +0.103 |
Neg logit contributions | |
sled | -0.112 |
leash | -0.108 |
reins | -0.103 |
wagon | -0.103 |
mole | -0.103 |
Token | ! |
Token ID | 0 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ways | +0.011 |
ad | +0.010 |
vals | +0.010 |
arom | +0.010 |
agg | +0.010 |
Neg logit contributions | |
wagon | -0.011 |
leash | -0.011 |
yacht | -0.011 |
sled | -0.011 |
Woo | -0.011 |
Token | Alice |
Token ID | 14862 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ad | +0.025 |
ways | +0.024 |
vals | +0.023 |
od | +0.023 |
ven | +0.022 |
Neg logit contributions | |
Woo | -0.020 |
wagon | -0.020 |
leash | -0.019 |
lamb | -0.019 |
yacht | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ways | +0.040 |
vals | +0.037 |
ad | +0.036 |
br | +0.036 |
bows | +0.035 |
Neg logit contributions | |
who | -0.020 |
wagon | -0.020 |
paddle | -0.019 |
duck | -0.019 |
dog | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +9.17e-03 |
Pos logit contributions | |
Woo | +0.022 |
wagon | +0.021 |
leash | +0.021 |
lamb | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.016 |
od | -0.014 |
arom | -0.014 |
mastered | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ways | +0.027 |
ad | +0.025 |
vals | +0.023 |
od | +0.023 |
arom | +0.022 |
Neg logit contributions | |
wagon | -0.023 |
Woo | -0.023 |
leash | -0.022 |
lamb | -0.022 |
yacht | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
ways | +0.049 |
ad | +0.045 |
od | +0.044 |
vals | +0.044 |
ven | +0.043 |
Neg logit contributions | |
wagon | -0.033 |
Woo | -0.033 |
leash | -0.033 |
sled | -0.032 |
yacht | -0.031 |
Token | box |
Token ID | 3091 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
Woo | +0.013 |
lamb | +0.012 |
drown | +0.012 |
wagon | +0.012 |
Spot | +0.012 |
Neg logit contributions | |
ways | -0.016 |
br | -0.015 |
ad | -0.015 |
arom | -0.014 |
vals | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ways | +0.043 |
ad | +0.040 |
arom | +0.038 |
agg | +0.038 |
vals | +0.038 |
Neg logit contributions | |
wagon | -0.032 |
leash | -0.031 |
Woo | -0.031 |
yacht | -0.031 |
sled | -0.030 |
Token | ch |
Token ID | 442 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
ways | +0.061 |
ad | +0.057 |
vals | +0.053 |
od | +0.053 |
ven | +0.052 |
Neg logit contributions | |
Woo | -0.047 |
wagon | -0.047 |
leash | -0.046 |
lamb | -0.046 |
yacht | -0.045 |
Token | ocol |
Token ID | 4668 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
ways | +0.003 |
ven | +0.003 |
mastered | +0.003 |
arom | +0.003 |
books | +0.003 |
Neg logit contributions | |
wagon | -0.004 |
lamb | -0.004 |
sled | -0.004 |
arl | -0.004 |
leash | -0.004 |
Token | ates |
Token ID | 689 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
ways | +0.128 |
mastered | +0.110 |
arom | +0.107 |
equations | +0.105 |
shades | +0.103 |
Neg logit contributions | |
sled | -0.121 |
leash | -0.113 |
Spot | -0.112 |
wagon | -0.110 |
reins | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
agg | +0.012 |
arom | +0.012 |
vals | +0.012 |
Neg logit contributions | |
wagon | -0.015 |
yacht | -0.015 |
leash | -0.014 |
sled | -0.014 |
Woo | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.012 |
od | +0.011 |
ven | +0.010 |
mastered | +0.010 |
Neg logit contributions | |
leash | -0.012 |
lamb | -0.012 |
wagon | -0.011 |
yacht | -0.011 |
bicycle | -0.011 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ways | +0.045 |
ad | +0.044 |
vals | +0.042 |
br | +0.040 |
arom | +0.040 |
Neg logit contributions | |
wagon | -0.026 |
Woo | -0.026 |
sled | -0.025 |
dog | -0.024 |
lamb | -0.024 |
Token | ch |
Token ID | 442 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
Woo | +0.030 |
wagon | +0.029 |
sled | +0.028 |
yacht | +0.028 |
leash | +0.028 |
Neg logit contributions | |
ways | -0.047 |
ad | -0.043 |
vals | -0.042 |
mastered | -0.042 |
ven | -0.042 |
Token | woods |
Token ID | 16479 |
Feature activation | +9.40e-04 |
Pos logit contributions | |
Woo | +0.006 |
arl | +0.006 |
paddle | +0.006 |
lamb | +0.006 |
yacht | +0.006 |
Neg logit contributions | |
ways | -0.008 |
ad | -0.007 |
br | -0.007 |
arom | -0.006 |
vals | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
wagon | +0.002 |
leash | +0.002 |
Woo | +0.002 |
yacht | +0.002 |
sled | +0.002 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
vals | -0.001 |
arom | -0.001 |
ven | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.015 |
vals | +0.015 |
ven | +0.015 |
od | +0.015 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.010 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
ways | +0.009 |
ad | +0.008 |
vals | +0.008 |
od | +0.008 |
arom | +0.008 |
Neg logit contributions | |
Woo | -0.006 |
wagon | -0.006 |
leash | -0.006 |
mole | -0.006 |
lamb | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
vals | +0.002 |
od | +0.002 |
ven | +0.002 |
Neg logit contributions | |
Woo | -0.002 |
leash | -0.002 |
wagon | -0.001 |
sled | -0.001 |
lamb | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
Woo | +0.041 |
Spot | +0.037 |
lamb | +0.036 |
bases | +0.035 |
amb | +0.035 |
Neg logit contributions | |
br | -0.046 |
ways | -0.045 |
ad | -0.042 |
mastered | -0.042 |
arom | -0.042 |
Token | gun |
Token ID | 2485 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Woo | +0.042 |
Spot | +0.038 |
lamb | +0.037 |
yacht | +0.034 |
drown | +0.034 |
Neg logit contributions | |
ways | -0.071 |
ad | -0.071 |
br | -0.065 |
arom | -0.065 |
mastered | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
Woo | +0.030 |
lamb | +0.029 |
wagon | +0.029 |
leash | +0.029 |
yacht | +0.028 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.033 |
od | -0.030 |
mastered | -0.030 |
ven | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Woo | +0.006 |
wagon | +0.006 |
leash | +0.006 |
lamb | +0.006 |
yacht | +0.006 |
Neg logit contributions | |
ways | -0.006 |
ad | -0.005 |
vals | -0.005 |
od | -0.005 |
ven | -0.005 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
Woo | +0.041 |
Spot | +0.036 |
lamb | +0.036 |
wagon | +0.035 |
yacht | +0.035 |
Neg logit contributions | |
ways | -0.064 |
br | -0.062 |
ad | -0.059 |
arom | -0.057 |
mastered | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
Woo | +0.036 |
wagon | +0.035 |
lamb | +0.035 |
leash | +0.035 |
yacht | +0.034 |
Neg logit contributions | |
ways | -0.025 |
ad | -0.023 |
od | -0.020 |
vals | -0.020 |
ven | -0.019 |
Token | world |
Token ID | 995 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ways | +0.037 |
ad | +0.035 |
vals | +0.032 |
od | +0.032 |
ven | +0.032 |
Neg logit contributions | |
Woo | -0.028 |
wagon | -0.027 |
leash | -0.027 |
lamb | -0.027 |
yacht | -0.027 |
Token | around |
Token ID | 1088 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
agg | +0.049 |
ad | +0.048 |
ways | +0.048 |
arom | +0.047 |
vals | +0.045 |
Neg logit contributions | |
who | -0.035 |
yacht | -0.035 |
wagon | -0.034 |
boat | -0.032 |
alone | -0.032 |
Token | us |
Token ID | 514 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
yacht | +0.013 |
Woo | +0.012 |
wagon | +0.012 |
mole | +0.012 |
lamb | +0.012 |
Neg logit contributions | |
ways | -0.021 |
ad | -0.019 |
ven | -0.019 |
vals | -0.019 |
mastered | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
ways | +0.034 |
ad | +0.030 |
agg | +0.030 |
oph | +0.029 |
ven | +0.029 |
Neg logit contributions | |
yacht | -0.028 |
who | -0.028 |
wagon | -0.027 |
paddle | -0.027 |
leash | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
leash | +0.014 |
wagon | +0.014 |
yacht | +0.013 |
lamb | +0.013 |
paddle | +0.013 |
Neg logit contributions | |
ad | -0.014 |
ways | -0.014 |
od | -0.013 |
vals | -0.012 |
ven | -0.012 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
Woo | +0.011 |
wagon | +0.011 |
leash | +0.010 |
sled | +0.010 |
lamb | +0.010 |
Neg logit contributions | |
ways | -0.024 |
ad | -0.022 |
vals | -0.022 |
arom | -0.021 |
ven | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
leash | +0.058 |
Woo | +0.058 |
lamb | +0.058 |
wagon | +0.057 |
paddle | +0.055 |
Neg logit contributions | |
ways | -0.061 |
ad | -0.058 |
od | -0.055 |
agg | -0.053 |
ven | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.002 |
lamb | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
od | -0.001 |
vals | -0.001 |
ven | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ways | +0.016 |
ad | +0.014 |
od | +0.012 |
agg | +0.012 |
ven | +0.012 |
Neg logit contributions | |
Woo | -0.043 |
wagon | -0.042 |
lamb | -0.042 |
yacht | -0.042 |
leash | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -7.32e-04 |
Pos logit contributions | |
ways | +0.048 |
ad | +0.044 |
vals | +0.041 |
mastered | +0.039 |
arom | +0.039 |
Neg logit contributions | |
Woo | -0.062 |
wagon | -0.061 |
leash | -0.060 |
yacht | -0.059 |
sled | -0.059 |
Token | there |
Token ID | 612 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ways | +0.001 |
od | +0.001 |
ad | +0.001 |
br | +0.001 |
ven | +0.001 |
Neg logit contributions | |
leash | -0.001 |
yacht | -0.001 |
reins | -0.001 |
Woo | -0.001 |
paddle | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -8.69e-04 |
Pos logit contributions | |
ad | +0.030 |
ways | +0.029 |
vals | +0.029 |
von | +0.028 |
ven | +0.028 |
Neg logit contributions | |
lamb | -0.019 |
yacht | -0.018 |
Woo | -0.018 |
who | -0.018 |
dog | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
vals | +0.001 |
arom | +0.001 |
od | +0.001 |
Neg logit contributions | |
Woo | -0.001 |
wagon | -0.001 |
yacht | -0.001 |
leash | -0.001 |
lamb | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
von | +0.014 |
arom | +0.014 |
vals | +0.014 |
Neg logit contributions | |
leash | -0.010 |
who | -0.010 |
Woo | -0.010 |
yacht | -0.010 |
dog | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
ways | +0.024 |
ad | +0.022 |
vals | +0.021 |
arom | +0.020 |
agg | +0.020 |
Neg logit contributions | |
yacht | -0.024 |
leash | -0.024 |
wagon | -0.024 |
Woo | -0.023 |
sled | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
wagon | +0.011 |
leash | +0.011 |
Woo | +0.011 |
lamb | +0.011 |
yacht | +0.011 |
Neg logit contributions | |
ways | -0.018 |
ad | -0.017 |
od | -0.016 |
vals | -0.016 |
arom | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Woo | +0.016 |
wagon | +0.015 |
leash | +0.014 |
sled | +0.014 |
Spot | +0.014 |
Neg logit contributions | |
ways | -0.037 |
ad | -0.034 |
vals | -0.034 |
arom | -0.033 |
ven | -0.033 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
leash | +0.063 |
Woo | +0.062 |
lamb | +0.062 |
wagon | +0.061 |
paddle | +0.059 |
Neg logit contributions | |
ways | -0.064 |
ad | -0.060 |
od | -0.057 |
agg | -0.056 |
ven | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
wagon | +0.003 |
Woo | +0.003 |
leash | +0.002 |
lamb | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
ways | -0.002 |
ad | -0.002 |
od | -0.002 |
arom | -0.002 |
mastered | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.012 |
od | +0.010 |
ven | +0.010 |
arom | +0.010 |
Neg logit contributions | |
Woo | -0.034 |
wagon | -0.034 |
lamb | -0.034 |
yacht | -0.034 |
leash | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +8.97e-04 |
Pos logit contributions | |
ways | +0.046 |
ad | +0.042 |
vals | +0.039 |
mastered | +0.038 |
arom | +0.038 |
Neg logit contributions | |
Woo | -0.062 |
wagon | -0.062 |
leash | -0.061 |
yacht | -0.060 |
sled | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
leash | +0.001 |
Woo | +0.001 |
reins | +0.001 |
paddle | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
ways | -0.001 |
od | -0.001 |
br | -0.001 |
ven | -0.001 |
ad | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
ways | +0.008 |
ad | +0.008 |
vals | +0.007 |
br | +0.007 |
od | +0.007 |
Neg logit contributions | |
wagon | -0.004 |
Woo | -0.004 |
sled | -0.004 |
lamb | -0.004 |
yacht | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
wagon | +0.004 |
Woo | +0.004 |
yacht | +0.004 |
lamb | +0.004 |
sled | +0.003 |
Neg logit contributions | |
ways | -0.005 |
ad | -0.005 |
vals | -0.004 |
br | -0.004 |
mastered | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
Woo | +0.026 |
leash | +0.025 |
wagon | +0.025 |
lamb | +0.025 |
yacht | +0.024 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.034 |
od | -0.032 |
ven | -0.032 |
arom | -0.032 |
Token | we |
Token ID | 356 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.016 |
ven | +0.015 |
vals | +0.015 |
od | +0.015 |
Neg logit contributions | |
leash | -0.008 |
Woo | -0.008 |
wagon | -0.008 |
lamb | -0.008 |
mole | -0.008 |
Token | ride |
Token ID | 6594 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ways | +0.022 |
ad | +0.021 |
vals | +0.020 |
ven | +0.020 |
od | +0.020 |
Neg logit contributions | |
Woo | -0.014 |
wagon | -0.013 |
lamb | -0.013 |
leash | -0.013 |
mole | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Woo | +0.035 |
wagon | +0.035 |
leash | +0.035 |
lamb | +0.035 |
yacht | +0.034 |
Neg logit contributions | |
ways | -0.046 |
ad | -0.043 |
od | -0.040 |
ven | -0.040 |
vals | -0.039 |
Token | boat |
Token ID | 8848 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Woo | +0.045 |
leash | +0.043 |
lamb | +0.041 |
mole | +0.041 |
wagon | +0.040 |
Neg logit contributions | |
ways | -0.079 |
ad | -0.074 |
br | -0.070 |
ven | -0.070 |
arom | -0.070 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Woo | +0.019 |
wagon | +0.018 |
leash | +0.018 |
yacht | +0.018 |
lamb | +0.018 |
Neg logit contributions | |
ways | -0.029 |
ad | -0.027 |
od | -0.025 |
vals | -0.025 |
arom | -0.025 |
Token | His |
Token ID | 2399 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.017 |
od | +0.016 |
arom | +0.016 |
ven | +0.015 |
Neg logit contributions | |
wagon | -0.014 |
leash | -0.014 |
Woo | -0.014 |
yacht | -0.014 |
lamb | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
Woo | +0.021 |
lamb | +0.018 |
Spot | +0.017 |
drown | +0.017 |
leash | +0.017 |
Neg logit contributions | |
ad | -0.027 |
ways | -0.026 |
agg | -0.025 |
shades | -0.025 |
arom | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ways | +0.017 |
vals | +0.016 |
br | +0.016 |
arom | +0.016 |
mastered | +0.015 |
Neg logit contributions | |
wagon | -0.005 |
who | -0.005 |
Woo | -0.004 |
lamb | -0.004 |
bicycle | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Woo | +0.009 |
paddle | +0.009 |
leash | +0.009 |
wagon | +0.009 |
lamb | +0.009 |
Neg logit contributions | |
ways | -0.019 |
ad | -0.017 |
arom | -0.016 |
od | -0.016 |
agg | -0.016 |
Token | fly |
Token ID | 6129 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.021 |
arom | +0.020 |
vals | +0.020 |
od | +0.020 |
Neg logit contributions | |
Woo | -0.012 |
leash | -0.012 |
wagon | -0.012 |
paddle | -0.012 |
lamb | -0.012 |
Token | again |
Token ID | 757 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ways | +0.007 |
ad | +0.006 |
vals | +0.006 |
arom | +0.006 |
agg | +0.006 |
Neg logit contributions | |
Woo | -0.005 |
wagon | -0.004 |
leash | -0.004 |
lamb | -0.004 |
yacht | -0.004 |
Token | ." |
Token ID | 526 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
ways | +0.026 |
ad | +0.025 |
vals | +0.023 |
arom | +0.023 |
od | +0.023 |
Neg logit contributions | |
Woo | -0.018 |
wagon | -0.018 |
leash | -0.018 |
lamb | -0.017 |
sled | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.002 |
lamb | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
vals | -0.003 |
od | -0.003 |
ven | -0.003 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Woo | +0.011 |
wagon | +0.011 |
leash | +0.011 |
sled | +0.010 |
Spot | +0.010 |
Neg logit contributions | |
ways | -0.026 |
ad | -0.024 |
vals | -0.024 |
arom | -0.023 |
ven | -0.023 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.47e-04 |
Pos logit contributions | |
leash | +0.074 |
Woo | +0.073 |
lamb | +0.072 |
wagon | +0.072 |
paddle | +0.070 |
Neg logit contributions | |
ways | -0.073 |
ad | -0.069 |
od | -0.066 |
agg | -0.063 |
ven | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
wagon | +0.001 |
Woo | +0.001 |
lamb | +0.001 |
yacht | +0.001 |
leash | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
od | -0.001 |
mastered | -0.001 |
arom | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.013 |
agg | +0.011 |
ven | +0.011 |
od | +0.011 |
Neg logit contributions | |
Woo | -0.042 |
wagon | -0.042 |
lamb | -0.042 |
yacht | -0.041 |
leash | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
ways | +0.045 |
ad | +0.041 |
vals | +0.038 |
mastered | +0.037 |
od | +0.037 |
Neg logit contributions | |
Woo | -0.062 |
wagon | -0.061 |
leash | -0.060 |
yacht | -0.060 |
lamb | -0.060 |
Token | there |
Token ID | 612 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
leash | +0.004 |
reins | +0.004 |
yacht | +0.004 |
paddle | +0.004 |
Woo | +0.004 |
Neg logit contributions | |
od | -0.003 |
ways | -0.003 |
br | -0.003 |
ad | -0.003 |
ven | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +1.39e-04 |
Pos logit contributions | |
lamb | +0.001 |
leash | +0.001 |
yacht | +0.001 |
wagon | +0.001 |
mole | +0.001 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
ven | -0.001 |
od | -0.001 |
mastered | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
Woo | +0.000 |
leash | +0.000 |
wagon | +0.000 |
lamb | +0.000 |
yacht | +0.000 |
Neg logit contributions | |
ways | -0.000 |
ad | -0.000 |
ven | -0.000 |
mastered | -0.000 |
od | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
Woo | +0.004 |
wagon | +0.004 |
leash | +0.004 |
lamb | +0.003 |
yacht | +0.003 |
Neg logit contributions | |
ways | -0.006 |
ad | -0.005 |
od | -0.005 |
mastered | -0.005 |
arom | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ways | +0.004 |
ad | +0.004 |
vals | +0.003 |
od | +0.003 |
ven | +0.003 |
Neg logit contributions | |
Woo | -0.003 |
wagon | -0.003 |
leash | -0.003 |
yacht | -0.003 |
lamb | -0.003 |
Token | ' |
Token ID | 705 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ways | +0.036 |
vals | +0.034 |
shades | +0.033 |
ad | +0.033 |
ami | +0.032 |
Neg logit contributions | |
Woo | -0.028 |
yacht | -0.026 |
sled | -0.025 |
dog | -0.025 |
duck | -0.025 |
Token | I |
Token ID | 40 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Woo | +0.022 |
Spot | +0.022 |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.021 |
Neg logit contributions | |
ways | -0.047 |
ad | -0.044 |
od | -0.043 |
agg | -0.042 |
arom | -0.042 |
Token | think |
Token ID | 892 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Woo | +0.018 |
wagon | +0.017 |
leash | +0.017 |
paddle | +0.017 |
yacht | +0.017 |
Neg logit contributions | |
ways | -0.039 |
ad | -0.035 |
vals | -0.034 |
od | -0.034 |
arom | -0.034 |
Token | we |
Token ID | 356 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ways | +0.035 |
ad | +0.032 |
vals | +0.031 |
shades | +0.030 |
mastered | +0.030 |
Neg logit contributions | |
Woo | -0.018 |
yacht | -0.018 |
wagon | -0.018 |
leash | -0.017 |
sled | -0.017 |
Token | found |
Token ID | 1043 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
ways | +0.026 |
ad | +0.024 |
vals | +0.023 |
arom | +0.023 |
od | +0.022 |
Neg logit contributions | |
wagon | -0.012 |
Woo | -0.012 |
yacht | -0.012 |
leash | -0.012 |
lamb | -0.012 |
Token | what |
Token ID | 644 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
ways | +0.069 |
ad | +0.062 |
vals | +0.060 |
mastered | +0.059 |
ven | +0.058 |
Neg logit contributions | |
wagon | -0.042 |
Woo | -0.042 |
yacht | -0.041 |
lamb | -0.041 |
mole | -0.040 |
Token | we |
Token ID | 356 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ways | +0.008 |
ad | +0.007 |
vals | +0.007 |
arom | +0.007 |
agg | +0.007 |
Neg logit contributions | |
dog | -0.004 |
yacht | -0.004 |
wagon | -0.004 |
mole | -0.004 |
Woo | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
Woo | +0.058 |
wagon | +0.058 |
leash | +0.057 |
lamb | +0.057 |
yacht | +0.057 |
Neg logit contributions | |
ways | -0.055 |
ad | -0.052 |
od | -0.047 |
ven | -0.046 |
vals | -0.046 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Woo | +0.008 |
wagon | +0.008 |
lamb | +0.008 |
leash | +0.008 |
mole | +0.008 |
Neg logit contributions | |
ways | -0.013 |
ad | -0.011 |
vals | -0.011 |
arom | -0.011 |
od | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
Woo | +0.028 |
wagon | +0.027 |
lamb | +0.026 |
leash | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.036 |
ad | -0.033 |
vals | -0.032 |
arom | -0.031 |
od | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
ways | +0.019 |
ad | +0.017 |
vals | +0.017 |
arom | +0.017 |
od | +0.016 |
Neg logit contributions | |
wagon | -0.010 |
Woo | -0.010 |
lamb | -0.010 |
mole | -0.010 |
leash | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
Woo | +0.006 |
leash | +0.006 |
dog | +0.006 |
jacket | +0.005 |
bat | +0.005 |
Neg logit contributions | |
ways | -0.015 |
vals | -0.014 |
ement | -0.014 |
ami | -0.013 |
br | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
leash | +0.002 |
Woo | +0.002 |
wagon | +0.002 |
paddle | +0.002 |
lamb | +0.002 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
vals | -0.003 |
od | -0.003 |
arom | -0.003 |
Token | brave |
Token ID | 14802 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
leash | +0.012 |
Woo | +0.011 |
wagon | +0.011 |
lamb | +0.011 |
yacht | +0.011 |
Neg logit contributions | |
ways | -0.021 |
ad | -0.019 |
vals | -0.019 |
od | -0.019 |
ven | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
wagon | +0.033 |
Woo | +0.033 |
leash | +0.033 |
lamb | +0.033 |
yacht | +0.032 |
Neg logit contributions | |
ways | -0.035 |
ad | -0.032 |
vals | -0.031 |
ven | -0.030 |
od | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
Woo | +0.019 |
wagon | +0.019 |
leash | +0.018 |
lamb | +0.018 |
yacht | +0.018 |
Neg logit contributions | |
ways | -0.028 |
ad | -0.027 |
vals | -0.025 |
od | -0.025 |
ven | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
wagon | +0.007 |
yacht | +0.007 |
Woo | +0.007 |
lamb | +0.007 |
leash | +0.006 |
Neg logit contributions | |
ways | -0.010 |
ad | -0.010 |
agg | -0.009 |
od | -0.009 |
mastered | -0.009 |
Token | M |
Token ID | 44 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
agg | +0.002 |
mastered | +0.002 |
od | +0.002 |
Neg logit contributions | |
wagon | -0.002 |
yacht | -0.002 |
Woo | -0.002 |
paddle | -0.002 |
lamb | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
wagon | +0.015 |
lamb | +0.015 |
yacht | +0.015 |
leash | +0.014 |
Woo | +0.014 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.016 |
od | -0.015 |
agg | -0.015 |
br | -0.014 |
Token | Then |
Token ID | 6423 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ways | +0.008 |
ad | +0.008 |
arom | +0.007 |
od | +0.007 |
vals | +0.007 |
Neg logit contributions | |
Woo | -0.004 |
Spot | -0.004 |
leash | -0.004 |
wagon | -0.004 |
yacht | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.022 |
ami | +0.021 |
od | +0.021 |
vals | +0.020 |
Neg logit contributions | |
dog | -0.017 |
wagon | -0.017 |
boat | -0.016 |
yacht | -0.016 |
mole | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
mole | +0.002 |
yacht | +0.002 |
lamb | +0.002 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
vals | -0.002 |
od | -0.002 |
mastered | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
wagon | +0.014 |
leash | +0.013 |
yacht | +0.013 |
lamb | +0.013 |
mole | +0.013 |
Neg logit contributions | |
ways | -0.027 |
ad | -0.026 |
vals | -0.024 |
od | -0.024 |
ven | -0.024 |
Token | came |
Token ID | 1625 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
ways | +0.040 |
ad | +0.036 |
ven | +0.035 |
vals | +0.034 |
agg | +0.034 |
Neg logit contributions | |
lamb | -0.034 |
wagon | -0.033 |
Woo | -0.033 |
mole | -0.033 |
dog | -0.033 |
Token | into |
Token ID | 656 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ways | +0.010 |
ad | +0.010 |
vals | +0.009 |
ven | +0.009 |
arom | +0.009 |
Neg logit contributions | |
Woo | -0.006 |
lamb | -0.005 |
wagon | -0.005 |
leash | -0.005 |
sled | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
ways | +0.029 |
ad | +0.026 |
vals | +0.026 |
ven | +0.025 |
br | +0.025 |
Neg logit contributions | |
Woo | -0.020 |
wagon | -0.019 |
leash | -0.019 |
lamb | -0.019 |
yacht | -0.019 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ways | +0.013 |
arom | +0.012 |
shades | +0.012 |
ce | +0.011 |
ad | +0.011 |
Neg logit contributions | |
Woo | -0.014 |
Spot | -0.012 |
paddle | -0.012 |
leash | -0.012 |
sled | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ways | +0.045 |
ad | +0.044 |
ven | +0.041 |
br | +0.041 |
vals | +0.041 |
Neg logit contributions | |
wagon | -0.049 |
yacht | -0.048 |
leash | -0.048 |
dog | -0.048 |
Woo | -0.048 |
Token | She |
Token ID | 1375 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
vals | +0.037 |
ven | +0.036 |
ad | +0.036 |
centimeters | +0.036 |
ways | +0.036 |
Neg logit contributions | |
dog | -0.016 |
Woo | -0.016 |
Spot | -0.015 |
wagon | -0.015 |
puppy | -0.014 |
Token | From |
Token ID | 4863 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
paddle | +0.015 |
yacht | +0.015 |
lamb | +0.015 |
wagon | +0.015 |
mole | +0.015 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.011 |
br | -0.010 |
mastered | -0.010 |
books | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
drown | +0.014 |
paddle | +0.013 |
sled | +0.012 |
reins | +0.012 |
Drop | +0.012 |
Neg logit contributions | |
ad | -0.009 |
ways | -0.007 |
written | -0.007 |
ami | -0.006 |
ven | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
paddle | +0.073 |
raft | +0.070 |
wagon | +0.070 |
lamb | +0.070 |
wounds | +0.070 |
Neg logit contributions | |
ad | -0.039 |
ways | -0.033 |
od | -0.033 |
mastered | -0.032 |
br | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
wagon | +0.011 |
lamb | +0.011 |
mole | +0.011 |
yacht | +0.011 |
Woo | +0.011 |
Neg logit contributions | |
ways | -0.022 |
ad | -0.021 |
br | -0.020 |
mastered | -0.020 |
ven | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.012 |
vals | +0.011 |
od | +0.011 |
ven | +0.011 |
Neg logit contributions | |
Woo | -0.020 |
wagon | -0.020 |
leash | -0.020 |
lamb | -0.020 |
yacht | -0.020 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
Woo | +0.028 |
wagon | +0.027 |
leash | +0.027 |
lamb | +0.026 |
yacht | +0.026 |
Neg logit contributions | |
ways | -0.049 |
ad | -0.046 |
vals | -0.043 |
od | -0.043 |
ven | -0.043 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Woo | +0.003 |
wagon | +0.003 |
leash | +0.003 |
lamb | +0.003 |
yacht | +0.003 |
Neg logit contributions | |
ways | -0.003 |
ad | -0.003 |
vals | -0.003 |
od | -0.003 |
ven | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ways | +0.020 |
ad | +0.020 |
od | +0.018 |
mastered | +0.018 |
ven | +0.017 |
Neg logit contributions | |
wagon | -0.015 |
lamb | -0.014 |
Woo | -0.014 |
yacht | -0.014 |
leash | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
wagon | +0.053 |
leash | +0.052 |
paddle | +0.052 |
sled | +0.050 |
yacht | +0.050 |
Neg logit contributions | |
ad | -0.056 |
ways | -0.055 |
od | -0.052 |
mastered | -0.050 |
arom | -0.049 |
Token | 's |
Token ID | 338 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
ways | +0.009 |
ad | +0.008 |
vals | +0.007 |
od | +0.007 |
arom | +0.007 |
Neg logit contributions | |
Woo | -0.007 |
wagon | -0.007 |
leash | -0.007 |
lamb | -0.007 |
yacht | -0.007 |
Token | always |
Token ID | 1464 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
yacht | +0.002 |
wagon | +0.002 |
paddle | +0.002 |
sled | +0.002 |
Woo | +0.002 |
Neg logit contributions | |
ways | -0.001 |
ad | -0.001 |
ven | -0.001 |
mastered | -0.001 |
vals | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
Woo | +0.018 |
leash | +0.018 |
drown | +0.018 |
wagon | +0.017 |
paddle | +0.017 |
Neg logit contributions | |
ways | -0.050 |
ad | -0.050 |
arom | -0.048 |
br | -0.047 |
od | -0.047 |
Token | called |
Token ID | 1444 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
ways | +0.025 |
ad | +0.024 |
od | +0.023 |
vals | +0.022 |
arom | +0.022 |
Neg logit contributions | |
wagon | -0.010 |
Woo | -0.010 |
leash | -0.009 |
yacht | -0.009 |
paddle | -0.009 |
Token | Amy |
Token ID | 14235 |
Feature activation | -9.89e-03 |
Pos logit contributions | |
ways | +0.013 |
vals | +0.013 |
ement | +0.013 |
mastered | +0.012 |
ad | +0.012 |
Neg logit contributions | |
Woo | -0.006 |
Spot | -0.005 |
dog | -0.005 |
mole | -0.005 |
lamb | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.013 |
vals | +0.013 |
ven | +0.012 |
arom | +0.012 |
Neg logit contributions | |
Woo | -0.018 |
wagon | -0.017 |
lamb | -0.017 |
leash | -0.017 |
mole | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.005 |
vals | +0.005 |
arom | +0.005 |
ven | +0.004 |
Neg logit contributions | |
wagon | -0.004 |
Woo | -0.004 |
dog | -0.004 |
Spot | -0.004 |
mole | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ways | +0.024 |
ad | +0.023 |
vals | +0.022 |
ven | +0.021 |
od | +0.021 |
Neg logit contributions | |
Woo | -0.013 |
wagon | -0.013 |
leash | -0.013 |
lamb | -0.013 |
yacht | -0.013 |
Token | only |
Token ID | 691 |
Feature activation | -4.56e-04 |
Pos logit contributions | |
wagon | +0.019 |
leash | +0.018 |
Woo | +0.018 |
yacht | +0.018 |
sled | +0.018 |
Neg logit contributions | |
ways | -0.018 |
ad | -0.017 |
od | -0.015 |
vals | -0.015 |
arom | -0.015 |
Token | three |
Token ID | 1115 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ways | +0.001 |
ad | +0.001 |
vals | +0.001 |
ven | +0.001 |
ement | +0.001 |
Neg logit contributions | |
lamb | -0.001 |
Woo | -0.001 |
dog | -0.001 |
leash | -0.001 |
mole | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ways | +0.036 |
vals | +0.034 |
ad | +0.034 |
ven | +0.032 |
mastered | +0.031 |
Neg logit contributions | |
leash | -0.049 |
lamb | -0.048 |
dog | -0.048 |
wagon | -0.048 |
sled | -0.047 |
Token | old |
Token ID | 1468 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
vals | +0.048 |
ways | +0.048 |
ad | +0.047 |
ven | +0.046 |
mastered | +0.045 |
Neg logit contributions | |
yacht | -0.022 |
wagon | -0.022 |
lamb | -0.022 |
leash | -0.021 |
dog | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
dog | +0.034 |
puppy | +0.033 |
wagon | +0.032 |
lamb | +0.031 |
mole | +0.031 |
Neg logit contributions | |
ways | -0.050 |
vals | -0.049 |
ad | -0.047 |
ven | -0.046 |
agg | -0.046 |
Token | down |
Token ID | 866 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
drown | +0.007 |
Woo | +0.006 |
paddle | +0.006 |
mole | +0.006 |
leash | +0.006 |
Neg logit contributions | |
ways | -0.011 |
ad | -0.010 |
ement | -0.010 |
ven | -0.009 |
ami | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
vals | +0.003 |
arom | +0.003 |
od | +0.003 |
Neg logit contributions | |
wagon | -0.001 |
Woo | -0.001 |
leash | -0.001 |
yacht | -0.001 |
sled | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ways | +0.020 |
vals | +0.019 |
ad | +0.019 |
ven | +0.018 |
agg | +0.018 |
Neg logit contributions | |
Woo | -0.012 |
wagon | -0.012 |
dog | -0.011 |
leash | -0.011 |
sled | -0.011 |
Token | couch |
Token ID | 18507 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
ways | +0.057 |
ad | +0.053 |
arom | +0.050 |
od | +0.049 |
vals | +0.049 |
Neg logit contributions | |
Woo | -0.031 |
lamb | -0.030 |
wagon | -0.029 |
leash | -0.029 |
mole | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ad | +0.004 |
ways | +0.004 |
vals | +0.004 |
arom | +0.004 |
agg | +0.004 |
Neg logit contributions | |
wagon | -0.002 |
leash | -0.002 |
yacht | -0.002 |
Woo | -0.002 |
sled | -0.002 |
Token | watched |
Token ID | 7342 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
Woo | +0.015 |
wagon | +0.015 |
leash | +0.015 |
lamb | +0.014 |
yacht | +0.014 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.016 |
vals | -0.015 |
od | -0.015 |
ven | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
ways | +0.057 |
ad | +0.053 |
vals | +0.053 |
ven | +0.051 |
mastered | +0.050 |
Neg logit contributions | |
Woo | -0.033 |
wagon | -0.032 |
yacht | -0.032 |
lamb | -0.030 |
leash | -0.030 |
Token | show |
Token ID | 905 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ways | +0.003 |
ad | +0.003 |
vals | +0.003 |
ven | +0.003 |
od | +0.003 |
Neg logit contributions | |
wagon | -0.002 |
leash | -0.002 |
yacht | -0.002 |
Woo | -0.002 |
lamb | -0.002 |
Token | about |
Token ID | 546 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ways | +0.038 |
ad | +0.036 |
vals | +0.036 |
arom | +0.036 |
agg | +0.036 |
Neg logit contributions | |
yacht | -0.023 |
leash | -0.022 |
wagon | -0.022 |
Woo | -0.022 |
dog | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
ways | +0.032 |
ad | +0.030 |
vals | +0.030 |
ven | +0.029 |
agg | +0.028 |
Neg logit contributions | |
wagon | -0.021 |
Woo | -0.021 |
yacht | -0.020 |
lamb | -0.020 |
leash | -0.020 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
wagon | +0.012 |
Woo | +0.012 |
leash | +0.011 |
yacht | +0.011 |
lamb | +0.011 |
Neg logit contributions | |
ways | -0.016 |
ad | -0.016 |
vals | -0.014 |
od | -0.014 |
ven | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
Woo | +0.000 |
wagon | +0.000 |
leash | +0.000 |
lamb | +0.000 |
yacht | +0.000 |
Neg logit contributions | |
ways | -0.000 |
ad | -0.000 |
od | -0.000 |
vals | -0.000 |
ven | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.016 |
vals | +0.015 |
od | +0.015 |
ven | +0.015 |
Neg logit contributions | |
Woo | -0.012 |
wagon | -0.011 |
leash | -0.011 |
lamb | -0.011 |
yacht | -0.011 |
Token | named |
Token ID | 3706 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
wagon | +0.005 |
leash | +0.005 |
paddle | +0.005 |
Woo | +0.005 |
sled | +0.005 |
Neg logit contributions | |
ways | -0.004 |
ad | -0.004 |
od | -0.004 |
vals | -0.004 |
arom | -0.004 |
Token | Jake |
Token ID | 14757 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
ways | +0.019 |
ad | +0.018 |
od | +0.017 |
vals | +0.017 |
ven | +0.017 |
Neg logit contributions | |
Woo | -0.012 |
wagon | -0.011 |
leash | -0.011 |
lamb | -0.011 |
yacht | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ways | +0.021 |
ad | +0.020 |
vals | +0.019 |
ven | +0.019 |
mastered | +0.019 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.010 |
leash | -0.010 |
yacht | -0.009 |
lamb | -0.009 |
Token | Jill |
Token ID | 22772 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Woo | +0.023 |
wagon | +0.022 |
leash | +0.022 |
lamb | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.041 |
vals | -0.039 |
od | -0.038 |
ven | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
ways | +0.047 |
ad | +0.042 |
ven | +0.040 |
vals | +0.040 |
mastered | +0.040 |
Neg logit contributions | |
wagon | -0.054 |
Woo | -0.053 |
leash | -0.053 |
yacht | -0.053 |
lamb | -0.052 |
Token | Jake |
Token ID | 14757 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ways | +0.002 |
ad | +0.002 |
br | +0.002 |
arom | +0.002 |
agg | +0.002 |
Neg logit contributions | |
wagon | -0.001 |
Woo | -0.001 |
sled | -0.001 |
yacht | -0.001 |
dog | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ways | +0.028 |
ad | +0.027 |
vals | +0.026 |
br | +0.025 |
arom | +0.025 |
Neg logit contributions | |
wagon | -0.014 |
yacht | -0.014 |
Woo | -0.014 |
dog | -0.014 |
mole | -0.013 |
Token | Jill |
Token ID | 22772 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
Woo | +0.024 |
wagon | +0.023 |
dog | +0.023 |
yacht | +0.023 |
boy | +0.022 |
Neg logit contributions | |
ways | -0.016 |
vals | -0.015 |
centimeters | -0.014 |
br | -0.014 |
ven | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
ways | +0.075 |
ad | +0.071 |
vals | +0.068 |
br | +0.067 |
arom | +0.066 |
Neg logit contributions | |
wagon | -0.032 |
yacht | -0.031 |
Woo | -0.030 |
leash | -0.029 |
lamb | -0.029 |
Token | other |
Token ID | 584 |
Feature activation | +9.24e-03 |
Pos logit contributions | |
ways | +0.020 |
ad | +0.018 |
vals | +0.017 |
arom | +0.017 |
od | +0.017 |
Neg logit contributions | |
Woo | -0.011 |
wagon | -0.011 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
Token | children |
Token ID | 1751 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
wagon | +0.010 |
dog | +0.010 |
lamb | +0.010 |
leash | +0.009 |
mole | +0.009 |
Neg logit contributions | |
ways | -0.020 |
ad | -0.019 |
vals | -0.019 |
od | -0.019 |
ven | -0.019 |
Token | played |
Token ID | 2826 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
ways | +0.013 |
ad | +0.013 |
vals | +0.012 |
od | +0.012 |
ven | +0.012 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.010 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
Token | together |
Token ID | 1978 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.002 |
yacht | +0.002 |
lamb | +0.002 |
Neg logit contributions | |
ways | -0.004 |
ad | -0.004 |
vals | -0.003 |
od | -0.003 |
ven | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
ways | +0.010 |
ad | +0.009 |
vals | +0.009 |
arom | +0.009 |
ven | +0.009 |
Neg logit contributions | |
wagon | -0.006 |
leash | -0.006 |
yacht | -0.005 |
sled | -0.005 |
Woo | -0.005 |
Token | |
Token ID | 220 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
ways | +0.012 |
ad | +0.011 |
arom | +0.010 |
mastered | +0.010 |
od | +0.010 |
Neg logit contributions | |
leash | -0.011 |
lamb | -0.011 |
mole | -0.011 |
wagon | -0.011 |
raft | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
ways | +0.049 |
ad | +0.047 |
vals | +0.044 |
od | +0.044 |
arom | +0.043 |
Neg logit contributions | |
Woo | -0.026 |
wagon | -0.026 |
leash | -0.025 |
lamb | -0.024 |
yacht | -0.024 |
Token | At |
Token ID | 2953 |
Feature activation | -2.44e-04 |
Pos logit contributions | |
ways | +0.010 |
ad | +0.009 |
od | +0.008 |
mastered | +0.008 |
ven | +0.008 |
Neg logit contributions | |
wagon | -0.009 |
lamb | -0.009 |
mole | -0.009 |
raft | -0.008 |
leash | -0.008 |
Token | one |
Token ID | 530 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ways | +0.000 |
ad | +0.000 |
ven | +0.000 |
mastered | +0.000 |
agg | +0.000 |
Neg logit contributions | |
lamb | -0.000 |
wagon | -0.000 |
leash | -0.000 |
Woo | -0.000 |
mole | -0.000 |
Token | corner |
Token ID | 5228 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
Woo | +0.025 |
wagon | +0.024 |
yacht | +0.024 |
leash | +0.024 |
lamb | +0.024 |
Neg logit contributions | |
ways | -0.026 |
ad | -0.024 |
mastered | -0.022 |
vals | -0.022 |
ven | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
ways | +0.005 |
vals | +0.005 |
ad | +0.005 |
arom | +0.005 |
od | +0.005 |
Neg logit contributions | |
wagon | -0.005 |
dog | -0.005 |
yacht | -0.005 |
sled | -0.005 |
Woo | -0.005 |
Token | work |
Token ID | 670 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ways | +0.025 |
ad | +0.023 |
ven | +0.022 |
br | +0.021 |
od | +0.021 |
Neg logit contributions | |
wagon | -0.019 |
leash | -0.019 |
yacht | -0.019 |
lamb | -0.018 |
mole | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
ways | +0.036 |
ad | +0.034 |
agg | +0.034 |
ven | +0.034 |
von | +0.033 |
Neg logit contributions | |
yacht | -0.025 |
boat | -0.025 |
leash | -0.025 |
wagon | -0.024 |
who | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.004 |
vals | +0.004 |
od | +0.004 |
ven | +0.004 |
Neg logit contributions | |
Woo | -0.004 |
wagon | -0.003 |
leash | -0.003 |
lamb | -0.003 |
yacht | -0.003 |
Token | felt |
Token ID | 2936 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
ways | +0.027 |
ad | +0.025 |
vals | +0.024 |
br | +0.024 |
arom | +0.023 |
Neg logit contributions | |
Woo | -0.016 |
lamb | -0.016 |
wagon | -0.016 |
yacht | -0.015 |
duck | -0.015 |
Token | so |
Token ID | 523 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Woo | +0.007 |
wagon | +0.007 |
leash | +0.007 |
lamb | +0.007 |
yacht | +0.007 |
Neg logit contributions | |
ways | -0.014 |
ad | -0.013 |
vals | -0.012 |
od | -0.012 |
ven | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
ways | +0.036 |
ad | +0.034 |
vals | +0.032 |
od | +0.032 |
ven | +0.032 |
Neg logit contributions | |
Woo | -0.015 |
wagon | -0.014 |
leash | -0.014 |
yacht | -0.014 |
lamb | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.017 |
ven | +0.017 |
vals | +0.017 |
arom | +0.016 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.007 |
yacht | -0.007 |
leash | -0.007 |
lamb | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
Woo | +0.045 |
wagon | +0.043 |
yacht | +0.043 |
lamb | +0.043 |
leash | +0.042 |
Neg logit contributions | |
ways | -0.050 |
ad | -0.046 |
vals | -0.044 |
ven | -0.043 |
od | -0.042 |
Token | had |
Token ID | 550 |
Feature activation | +8.62e-04 |
Pos logit contributions | |
ways | +0.005 |
ad | +0.005 |
vals | +0.004 |
od | +0.004 |
ven | +0.004 |
Neg logit contributions | |
Woo | -0.004 |
wagon | -0.004 |
leash | -0.004 |
yacht | -0.004 |
lamb | -0.004 |
Token | planted |
Token ID | 18969 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Woo | +0.001 |
duck | +0.001 |
bat | +0.001 |
who | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
ways | -0.002 |
ement | -0.002 |
equations | -0.002 |
ad | -0.002 |
iner | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ways | +0.044 |
ven | +0.039 |
ad | +0.038 |
vals | +0.038 |
mastered | +0.037 |
Neg logit contributions | |
Woo | -0.027 |
mole | -0.027 |
lamb | -0.027 |
wagon | -0.026 |
duck | -0.026 |
Token | ement |
Token ID | 972 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
vals | +0.016 |
ways | +0.015 |
equations | +0.012 |
mastered | +0.012 |
arom | +0.012 |
Neg logit contributions | |
wagon | -0.040 |
yacht | -0.040 |
bicycle | -0.039 |
jacket | -0.039 |
Woo | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
vals | +0.027 |
ways | +0.026 |
br | +0.026 |
equations | +0.026 |
ad | +0.026 |
Neg logit contributions | |
sled | -0.020 |
wagon | -0.019 |
yacht | -0.019 |
who | -0.019 |
leash | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
ways | +0.016 |
ad | +0.016 |
vals | +0.016 |
ier | +0.016 |
arom | +0.015 |
Neg logit contributions | |
Woo | -0.008 |
wagon | -0.007 |
dog | -0.007 |
Spot | -0.007 |
bicycle | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
wagon | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
Woo | +0.007 |
leash | +0.007 |
Neg logit contributions | |
ways | -0.009 |
ad | -0.009 |
od | -0.008 |
agg | -0.008 |
mastered | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ways | +0.018 |
ad | +0.018 |
vals | +0.017 |
arom | +0.017 |
od | +0.016 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.010 |
leash | -0.010 |
lamb | -0.010 |
Spot | -0.010 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
ways | +0.054 |
ad | +0.052 |
vals | +0.050 |
od | +0.049 |
ven | +0.049 |
Neg logit contributions | |
wagon | -0.012 |
dog | -0.010 |
leash | -0.010 |
mole | -0.009 |
boy | -0.009 |
Token | went |
Token ID | 1816 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ways | +0.037 |
vals | +0.035 |
ad | +0.035 |
br | +0.035 |
arom | +0.034 |
Neg logit contributions | |
wagon | -0.018 |
sled | -0.017 |
who | -0.017 |
mole | -0.017 |
dog | -0.017 |
Token | closer |
Token ID | 5699 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Woo | +0.024 |
wagon | +0.024 |
lamb | +0.023 |
leash | +0.023 |
yacht | +0.023 |
Neg logit contributions | |
ways | -0.042 |
ad | -0.040 |
od | -0.036 |
ven | -0.036 |
mastered | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.022 |
vals | +0.022 |
arom | +0.021 |
ven | +0.021 |
Neg logit contributions | |
wagon | -0.011 |
sled | -0.011 |
leash | -0.011 |
Woo | -0.011 |
lamb | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ways | +0.021 |
ad | +0.020 |
od | +0.019 |
arom | +0.018 |
vals | +0.018 |
Neg logit contributions | |
Woo | -0.015 |
wagon | -0.014 |
leash | -0.014 |
lamb | -0.014 |
yacht | -0.014 |
Token | stack |
Token ID | 8931 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ad | +0.046 |
agg | +0.046 |
ways | +0.045 |
ides | +0.045 |
br | +0.044 |
Neg logit contributions | |
wagon | -0.022 |
boy | -0.022 |
fence | -0.022 |
dog | -0.021 |
slide | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
Woo | +0.009 |
wagon | +0.009 |
leash | +0.009 |
lamb | +0.008 |
yacht | +0.008 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
vals | -0.013 |
od | -0.013 |
ven | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
Woo | +0.025 |
wagon | +0.024 |
lamb | +0.023 |
leash | +0.023 |
mole | +0.023 |
Neg logit contributions | |
ways | -0.035 |
ad | -0.033 |
vals | -0.032 |
ven | -0.031 |
mastered | -0.030 |
Token | like |
Token ID | 588 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ways | +0.006 |
ad | +0.005 |
od | +0.005 |
vals | +0.005 |
ven | +0.005 |
Neg logit contributions | |
Woo | -0.006 |
wagon | -0.006 |
leash | -0.006 |
lamb | -0.006 |
yacht | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -5.96e-04 |
Pos logit contributions | |
Woo | +0.035 |
wagon | +0.032 |
dog | +0.031 |
leash | +0.031 |
lamb | +0.031 |
Neg logit contributions | |
ways | -0.046 |
vals | -0.044 |
ad | -0.042 |
agg | -0.042 |
ven | -0.042 |
Token | usually |
Token ID | 3221 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
ways | +0.001 |
ad | +0.001 |
vals | +0.001 |
od | +0.001 |
ven | +0.001 |
Neg logit contributions | |
Woo | -0.001 |
wagon | -0.001 |
leash | -0.001 |
lamb | -0.001 |
yacht | -0.001 |
Token | did |
Token ID | 750 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
Woo | +0.030 |
leash | +0.029 |
wagon | +0.028 |
dog | +0.028 |
sled | +0.027 |
Neg logit contributions | |
ways | -0.050 |
ad | -0.048 |
od | -0.047 |
vals | -0.046 |
agg | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
ways | +0.089 |
ad | +0.087 |
vals | +0.085 |
agg | +0.083 |
arom | +0.083 |
Neg logit contributions | |
Woo | -0.078 |
leash | -0.074 |
yacht | -0.073 |
wagon | -0.072 |
sled | -0.071 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
Woo | +0.007 |
wagon | +0.007 |
leash | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.012 |
vals | -0.011 |
od | -0.011 |
ven | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
wagon | +0.005 |
Woo | +0.005 |
leash | +0.005 |
yacht | +0.005 |
lamb | +0.005 |
Neg logit contributions | |
ways | -0.005 |
ad | -0.004 |
mastered | -0.004 |
od | -0.004 |
ven | -0.004 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
wagon | +0.037 |
Woo | +0.035 |
yacht | +0.035 |
sled | +0.035 |
raft | +0.034 |
Neg logit contributions | |
ways | -0.064 |
ad | -0.061 |
od | -0.057 |
mastered | -0.057 |
arom | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
wagon | +0.059 |
paddle | +0.059 |
leash | +0.059 |
yacht | +0.058 |
Spot | +0.058 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.039 |
mastered | -0.036 |
od | -0.036 |
br | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
ways | +0.022 |
ad | +0.022 |
vals | +0.020 |
od | +0.020 |
arom | +0.020 |
Neg logit contributions | |
wagon | -0.015 |
Woo | -0.015 |
leash | -0.015 |
yacht | -0.014 |
sled | -0.014 |
Token | milk |
Token ID | 7545 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Woo | +0.011 |
wagon | +0.010 |
leash | +0.010 |
lamb | +0.010 |
yacht | +0.010 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.012 |
vals | -0.011 |
arom | -0.011 |
od | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
Woo | +0.024 |
wagon | +0.024 |
lamb | +0.024 |
leash | +0.024 |
yacht | +0.023 |
Neg logit contributions | |
ways | -0.022 |
ad | -0.020 |
vals | -0.018 |
ven | -0.018 |
od | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
wagon | +0.002 |
Woo | +0.002 |
leash | +0.002 |
yacht | +0.002 |
sled | +0.002 |
Neg logit contributions | |
ways | -0.002 |
ad | -0.002 |
vals | -0.002 |
od | -0.002 |
arom | -0.002 |
Token | How |
Token ID | 1374 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
wagon | +0.012 |
leash | +0.012 |
yacht | +0.011 |
raft | +0.011 |
lamb | +0.011 |
Neg logit contributions | |
ways | -0.015 |
ad | -0.014 |
vals | -0.014 |
ven | -0.013 |
od | -0.013 |
Token | does |
Token ID | 857 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
ways | +0.024 |
ad | +0.023 |
arom | +0.022 |
vals | +0.021 |
ples | +0.021 |
Neg logit contributions | |
dog | -0.013 |
Woo | -0.013 |
wagon | -0.013 |
sled | -0.012 |
yacht | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ways | +0.148 |
ad | +0.139 |
vals | +0.131 |
od | +0.130 |
mastered | +0.129 |
Neg logit contributions | |
Woo | -0.070 |
yacht | -0.068 |
wagon | -0.066 |
leash | -0.064 |
lamb | -0.062 |
Token | sound |
Token ID | 2128 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
wagon | +0.005 |
yacht | +0.005 |
Woo | +0.005 |
leash | +0.005 |
lamb | +0.004 |
Neg logit contributions | |
ways | -0.007 |
ad | -0.006 |
vals | -0.006 |
od | -0.006 |
mastered | -0.006 |
Token | ?" |
Token ID | 1701 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
ways | +0.034 |
ad | +0.033 |
vals | +0.030 |
od | +0.030 |
arom | +0.030 |
Neg logit contributions | |
Woo | -0.018 |
wagon | -0.018 |
yacht | -0.017 |
leash | -0.017 |
lamb | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.012 |
od | +0.012 |
ven | +0.012 |
Neg logit contributions | |
Woo | -0.007 |
wagon | -0.007 |
leash | -0.007 |
lamb | -0.007 |
yacht | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.84e-03 |
Pos logit contributions | |
wagon | +0.011 |
yacht | +0.011 |
lamb | +0.011 |
leash | +0.011 |
Woo | +0.011 |
Neg logit contributions | |
ways | -0.014 |
ad | -0.014 |
od | -0.012 |
agg | -0.012 |
mastered | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
Woo | +0.008 |
leash | +0.008 |
wagon | +0.008 |
yacht | +0.008 |
lamb | +0.007 |
Neg logit contributions | |
ways | -0.018 |
ad | -0.017 |
vals | -0.016 |
arom | -0.016 |
ven | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
Woo | +0.007 |
wagon | +0.007 |
leash | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
Neg logit contributions | |
ways | -0.006 |
ad | -0.005 |
vals | -0.005 |
ven | -0.005 |
od | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
wagon | +0.015 |
leash | +0.015 |
yacht | +0.014 |
lamb | +0.014 |
raft | +0.014 |
Neg logit contributions | |
ways | -0.022 |
ad | -0.020 |
od | -0.019 |
mastered | -0.019 |
vals | -0.019 |
Token | S |
Token ID | 50 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Woo | +0.017 |
wagon | +0.016 |
leash | +0.016 |
lamb | +0.016 |
sled | +0.016 |
Neg logit contributions | |
ways | -0.023 |
ad | -0.021 |
vals | -0.020 |
arom | -0.020 |
ven | -0.020 |
Token | ara |
Token ID | 3301 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
ways | +0.039 |
ad | +0.034 |
arom | +0.034 |
vals | +0.033 |
br | +0.033 |
Neg logit contributions | |
Woo | -0.026 |
wagon | -0.025 |
sled | -0.024 |
leash | -0.024 |
yacht | -0.024 |
Token | did |
Token ID | 750 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
ways | +0.017 |
ad | +0.016 |
vals | +0.015 |
od | +0.015 |
ven | +0.015 |
Neg logit contributions | |
Woo | -0.010 |
wagon | -0.010 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
ways | +0.093 |
ad | +0.088 |
vals | +0.085 |
ami | +0.081 |
mastered | +0.081 |
Neg logit contributions | |
Woo | -0.084 |
yacht | -0.080 |
wagon | -0.078 |
leash | -0.078 |
sled | -0.077 |
Token | like |
Token ID | 588 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ways | +0.047 |
agg | +0.044 |
ement | +0.043 |
arom | +0.043 |
ven | +0.043 |
Neg logit contributions | |
leash | -0.019 |
Woo | -0.019 |
paddle | -0.018 |
yacht | -0.017 |
wagon | -0.017 |
Token | bath |
Token ID | 7837 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
Woo | +0.018 |
wagon | +0.018 |
yacht | +0.017 |
leash | +0.017 |
lamb | +0.017 |
Neg logit contributions | |
ways | -0.029 |
ad | -0.027 |
vals | -0.026 |
arom | -0.026 |
ven | -0.025 |
Token | time |
Token ID | 640 |
Feature activation | +3.25e-05 |
Pos logit contributions | |
Woo | +0.009 |
wagon | +0.008 |
leash | +0.008 |
yacht | +0.008 |
dog | +0.008 |
Neg logit contributions | |
ways | -0.008 |
ad | -0.008 |
vals | -0.007 |
agg | -0.007 |
ven | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
Woo | +0.000 |
yacht | +0.000 |
leash | +0.000 |
wagon | +0.000 |
dog | +0.000 |
Neg logit contributions | |
ways | -0.000 |
ad | -0.000 |
vals | -0.000 |
agg | -0.000 |
arom | -0.000 |
Token | man |
Token ID | 805 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
wagon | +0.005 |
Woo | +0.005 |
leash | +0.005 |
yacht | +0.005 |
sled | +0.005 |
Neg logit contributions | |
ways | -0.009 |
ad | -0.009 |
mastered | -0.008 |
od | -0.008 |
ven | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
ways | +0.015 |
ad | +0.014 |
ven | +0.013 |
agg | +0.013 |
vals | +0.013 |
Neg logit contributions | |
wagon | -0.017 |
leash | -0.017 |
yacht | -0.017 |
Woo | -0.017 |
lamb | -0.017 |
Token | When |
Token ID | 1649 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
ways | +0.014 |
ad | +0.013 |
vals | +0.012 |
od | +0.012 |
ven | +0.012 |
Neg logit contributions | |
wagon | -0.013 |
Woo | -0.013 |
yacht | -0.013 |
leash | -0.013 |
mole | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
wagon | +0.007 |
yacht | +0.007 |
Woo | +0.007 |
sled | +0.007 |
raft | +0.007 |
Neg logit contributions | |
ways | -0.017 |
ad | -0.017 |
vals | -0.016 |
od | -0.016 |
br | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
ways | +0.044 |
ad | +0.039 |
vals | +0.037 |
arom | +0.036 |
ven | +0.036 |
Neg logit contributions | |
Woo | -0.047 |
wagon | -0.047 |
yacht | -0.047 |
sled | -0.045 |
mole | -0.045 |
Token | done |
Token ID | 1760 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
ways | +0.011 |
vals | +0.011 |
ad | +0.011 |
arom | +0.010 |
shades | +0.010 |
Neg logit contributions | |
sled | -0.016 |
leash | -0.016 |
yacht | -0.016 |
wagon | -0.016 |
Woo | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
ways | +0.096 |
vals | +0.090 |
ad | +0.090 |
shades | +0.087 |
equations | +0.085 |
Neg logit contributions | |
yacht | -0.083 |
Woo | -0.079 |
sled | -0.079 |
wagon | -0.078 |
raft | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
Woo | +0.002 |
wagon | +0.002 |
leash | +0.002 |
lamb | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
ways | -0.002 |
ad | -0.002 |
vals | -0.002 |
od | -0.002 |
ven | -0.002 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ad | +0.011 |
mastered | +0.010 |
ways | +0.010 |
written | +0.010 |
br | +0.010 |
Neg logit contributions | |
Woo | -0.005 |
yacht | -0.005 |
drown | -0.005 |
amb | -0.005 |
lves | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
wagon | +0.021 |
dog | +0.021 |
Woo | +0.021 |
leash | +0.021 |
duck | +0.020 |
Neg logit contributions | |
ways | -0.034 |
ad | -0.032 |
vals | -0.032 |
od | -0.030 |
agg | -0.030 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Woo | +0.006 |
leash | +0.006 |
wagon | +0.006 |
yacht | +0.006 |
sled | +0.006 |
Neg logit contributions | |
ways | -0.010 |
ad | -0.009 |
vals | -0.009 |
arom | -0.009 |
ven | -0.009 |
Token | o |
Token ID | 78 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
Woo | +0.006 |
wagon | +0.006 |
leash | +0.006 |
lamb | +0.006 |
yacht | +0.005 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.011 |
od | -0.010 |
vals | -0.010 |
ven | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-04 |
Pos logit contributions | |
wagon | +0.010 |
Woo | +0.010 |
leash | +0.010 |
lamb | +0.009 |
bicycle | +0.009 |
Neg logit contributions | |
ways | -0.010 |
ad | -0.010 |
od | -0.010 |
vals | -0.009 |
arom | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Woo | +0.000 |
wagon | +0.000 |
dog | +0.000 |
mole | +0.000 |
sled | +0.000 |
Neg logit contributions | |
ways | -0.001 |
vals | -0.001 |
mastered | -0.001 |
ad | -0.001 |
ven | -0.001 |
Token | liked |
Token ID | 8288 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ways | +0.023 |
ad | +0.022 |
vals | +0.020 |
od | +0.020 |
ven | +0.020 |
Neg logit contributions | |
Woo | -0.015 |
wagon | -0.015 |
leash | -0.015 |
lamb | -0.015 |
yacht | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Woo | +0.038 |
wagon | +0.038 |
leash | +0.037 |
lamb | +0.036 |
yacht | +0.036 |
Neg logit contributions | |
ways | -0.044 |
ad | -0.041 |
od | -0.038 |
arom | -0.037 |
vals | -0.037 |
Token | bake |
Token ID | 28450 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
ways | +0.022 |
ad | +0.021 |
vals | +0.019 |
od | +0.019 |
arom | +0.019 |
Neg logit contributions | |
Woo | -0.011 |
wagon | -0.010 |
leash | -0.010 |
lamb | -0.010 |
yacht | -0.010 |
Token | every |
Token ID | 790 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
mastered | +0.103 |
ways | +0.101 |
von | +0.095 |
vals | +0.095 |
ad | +0.094 |
Neg logit contributions | |
leash | -0.052 |
wagon | -0.051 |
dog | -0.050 |
Woo | -0.050 |
Spot | -0.050 |
Token | day |
Token ID | 1110 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
wagon | +0.038 |
leash | +0.036 |
mole | +0.036 |
lamb | +0.036 |
yacht | +0.036 |
Neg logit contributions | |
ways | -0.074 |
ad | -0.070 |
ven | -0.066 |
od | -0.066 |
mastered | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
ad | +0.026 |
agg | +0.026 |
ways | +0.025 |
ven | +0.024 |
von | +0.024 |
Neg logit contributions | |
who | -0.017 |
wagon | -0.016 |
yacht | -0.016 |
dog | -0.016 |
Woo | -0.016 |
Token | One |
Token ID | 1881 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
Woo | +0.006 |
wagon | +0.006 |
dog | +0.006 |
Spot | +0.006 |
sled | +0.006 |
Neg logit contributions | |
ways | -0.010 |
vals | -0.010 |
ier | -0.009 |
mastered | -0.009 |
arom | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
Woo | +0.007 |
wagon | +0.007 |
leash | +0.007 |
yacht | +0.007 |
lamb | +0.007 |
Neg logit contributions | |
ways | -0.012 |
ad | -0.011 |
od | -0.011 |
vals | -0.010 |
arom | -0.010 |