TOP ACTIVATIONS
MAX = 0.089

can play hop sc ot ch again . But you have
He tri pped , fell , and dropped things . He
bug that bites and makes Ben itch . Ben does not
be ep , and scree ch . One day
making snow men and throwing snow balls . "
made snow men , threw snow balls , and slid down
no ball , no bike , no k ite . They
thirteen , fourteen , fifteen , sixteen , seventeen , eighteen
twelve , thirteen , fourteen , fifteen , sixteen , seventeen
ball , no k ite , no mole . They have
. He trips and falls , and the ball rolls away
You can play hop sc ot ch again . But you
thirteen , fourteen , fifteen , sixteen , seventeen , eighteen
no soup , no water , no ship , no treasure
fifteen , sixteen , seventeen , eighteen , nineteen , twenty
you will have no toys , no stories and no hugs
twelve , thirteen , fourteen , fifteen , sixteen , seventeen
" ch oo cho o cho o ". They
We put eggs , flour , sugar , milk , and
water guns , no toys , and no TV . They

MIN ACTIVATIONS
MIN = -0.091

day , a curious 3 year old named John was playing
John was a curious three year old . He liked to
John was a curious 3 year old . On Tuesday ,
y was a curious 3 year old . She was always
very intelligent and curious three year old girl . She loved
S ally , a 3 year old child , saw the
obby was a curious three year old . He liked to
necessary . <|endoftext|> A 3 year old girl named Ann was
<|endoftext|> Billy was a 3 year old boy who was very
Inside , a little three year old boy was standing .
enny was a happy 3 year old who loved to explore
was a very curious three year old . She wanted to
was a ch ubby three year old who loved cocoa .
Sam was a curious 3 year old . One day ,
ie was a curious three year old . One day ,
<|endoftext|> John was a 3 year old boy with a big
was a very polite three year old . He always said
man asked a little 3 year old boy who was playing
day , a little 3 year old girl decided to play
Johnny was a smart 3 year old . He liked to

INTERVAL 0.044 - 0.089
CONTAINS 1.520%

in . One day , a little boy with
says Tim . " Yeah , let 's make
pur red happily and gave Bob a big kitten hug .
Ben shouts . " Ben , Anna , run
y . You should take a break . â

INTERVAL -0.001 - 0.044
CONTAINS 48.822%

got hurt . Her mom took her to the hospital ,
. She found some y ummy food and put it on
and he had learned an important lesson . From then on
L ila and Blink played for a long time .
said . <|endoftext|> One day , two friends Jack and Jane

INTERVAL -0.046 - -0.001
CONTAINS 49.245%

secret ! He told his friends what the special words meant
, you are mean ! You are not my friend !
The boy did not understand , so he asked
saw him fall and came to help . Sam said ,
little girl who went to the park with her dad .

INTERVAL -0.091 - -0.046
CONTAINS 0.413%

a little man standing in front of her . The man
in the grass near the flower . The little girl felt
girl who was three years old . Her name was Tin
wasn 't so terrible after all ! â <|endoftext|> Once
" No , sweet heart . But you can play with
Token can
Token ID460
Feature activation+2.56e-02

Pos logit contributions
Mac+0.000
balls+0.000
 eighteen+0.000
bled+0.000
MY+0.000
Neg logit contributions
adow-0.000
 about-0.000
arium-0.000
 day-0.000
 zone-0.000
Token play
Token ID711
Feature activation+5.33e-02

Pos logit contributions
bled+0.054
MY+0.053
balls+0.053
Mac+0.051
ula+0.051
Neg logit contributions
 lived-0.029
adow-0.029
 about-0.028
 night-0.027
 day-0.027
Token hop
Token ID1725
Feature activation+4.96e-02

Pos logit contributions
bled+0.106
MY+0.106
Marcus+0.105
 seventeen+0.105
Mac+0.104
Neg logit contributions
 about-0.072
 lived-0.069
 today-0.068
 day-0.064
 of-0.064
Tokensc
Token ID1416
Feature activation+4.05e-02

Pos logit contributions
bled+0.092
Mac+0.091
MY+0.091
balls+0.091
Marcus+0.088
Neg logit contributions
adow-0.066
 lived-0.065
 about-0.065
 night-0.063
 day-0.063
Tokenot
Token ID313
Feature activation+8.29e-02

Pos logit contributions
bled+0.065
Mac+0.064
MY+0.064
balls+0.064
Marcus+0.061
Neg logit contributions
adow-0.065
 lived-0.062
 about-0.062
 day-0.060
 of-0.060
Tokench
Token ID354
Feature activation+8.87e-02

Pos logit contributions
bled+0.133
balls+0.131
MY+0.131
Mac+0.129
z+0.124
Neg logit contributions
adow-0.132
 lived-0.128
 about-0.127
 night-0.125
 day-0.123
Token again
Token ID757
Feature activation+2.74e-02

Pos logit contributions
bled+0.175
MY+0.175
Mac+0.173
balls+0.172
Marcus+0.167
Neg logit contributions
adow-0.107
 lived-0.103
 about-0.102
 night-0.099
 day-0.098
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
bled+0.055
balls+0.055
MY+0.055
Mac+0.054
z+0.053
Neg logit contributions
adow-0.033
 lived-0.031
 about-0.031
 night-0.030
 day-0.029
Token But
Token ID887
Feature activation-2.83e-03

Pos logit contributions
adow+0.010
 lived+0.009
 about+0.009
 night+0.009
 day+0.009
Neg logit contributions
balls-0.015
bled-0.015
MY-0.015
Mac-0.015
z-0.015
Token you
Token ID345
Feature activation-2.86e-03

Pos logit contributions
adow+0.003
 lived+0.003
 about+0.003
 night+0.003
 day+0.003
Neg logit contributions
MY-0.006
balls-0.005
bled-0.005
Mac-0.005
z-0.005
Token have
Token ID423
Feature activation+1.49e-02

Pos logit contributions
adow+0.004
 lived+0.004
 about+0.004
 zone+0.004
 day+0.004
Neg logit contributions
Mac-0.005
balls-0.005
MY-0.005
 eighteen-0.004
 seventeen-0.004
Token He
Token ID679
Feature activation+2.25e-02

Pos logit contributions
bled+0.027
MY+0.027
balls+0.026
z+0.026
Mac+0.026
Neg logit contributions
adow-0.010
 about-0.010
 lived-0.010
 night-0.009
 of-0.009
Token tri
Token ID1333
Feature activation+4.28e-02

Pos logit contributions
MY+0.044
bled+0.043
balls+0.043
Mac+0.042
ula+0.042
Neg logit contributions
 lived-0.029
adow-0.028
 about-0.027
 night-0.027
 day-0.026
Tokenpped
Token ID1496
Feature activation+6.08e-02

Pos logit contributions
 wrists+0.067
 chip+0.064
 seventeen+0.063
 extract+0.063
balls+0.062
Neg logit contributions
adow-0.074
 of-0.073
 about-0.071
 lived-0.069
 night-0.067
Token,
Token ID11
Feature activation+7.64e-02

Pos logit contributions
bled+0.110
MY+0.109
balls+0.109
Mac+0.107
z+0.104
Neg logit contributions
 about-0.082
 night-0.082
adow-0.082
 lived-0.081
 day-0.080
Token fell
Token ID3214
Feature activation+4.16e-02

Pos logit contributions
MY+0.130
bled+0.128
balls+0.128
Mac+0.125
z+0.123
Neg logit contributions
adow-0.113
 lived-0.112
 about-0.112
 night-0.110
 of-0.108
Token,
Token ID11
Feature activation+8.62e-02

Pos logit contributions
balls+0.072
bled+0.072
MY+0.072
Mac+0.071
z+0.069
Neg logit contributions
adow-0.061
 lived-0.059
 about-0.058
 night-0.057
 day-0.055
Token and
Token ID290
Feature activation+3.23e-02

Pos logit contributions
MY+0.156
Mac+0.151
balls+0.151
bled+0.151
z+0.146
Neg logit contributions
 about-0.118
 lived-0.117
 night-0.117
 of-0.116
 day-0.113
Token dropped
Token ID5710
Feature activation+4.11e-02

Pos logit contributions
MY+0.053
bled+0.051
balls+0.051
Mac+0.051
z+0.049
Neg logit contributions
 lived-0.051
 night-0.049
adow-0.049
 about-0.049
 day-0.048
Token things
Token ID1243
Feature activation+2.93e-02

Pos logit contributions
MY+0.086
bled+0.085
Mac+0.085
balls+0.084
z+0.083
Neg logit contributions
 about-0.044
 lived-0.044
adow-0.044
 night-0.044
 of-0.042
Token.
Token ID13
Feature activation+2.37e-02

Pos logit contributions
balls+0.057
bled+0.054
MY+0.052
z+0.052
ula+0.051
Neg logit contributions
adow-0.042
 lived-0.038
 sorts-0.035
arium-0.035
 zone-0.034
Token He
Token ID679
Feature activation+3.43e-02

Pos logit contributions
bled+0.057
balls+0.056
MY+0.056
Mac+0.055
z+0.055
Neg logit contributions
adow-0.019
 lived-0.018
 about-0.018
 night-0.017
 day-0.016
Token bug
Token ID5434
Feature activation+4.09e-03

Pos logit contributions
adow+0.000
 lived+0.000
 about+0.000
 night+0.000
 day+0.000
Neg logit contributions
balls-0.000
MY-0.000
bled-0.000
Mac-0.000
z-0.000
Token that
Token ID326
Feature activation+1.45e-02

Pos logit contributions
balls+0.008
MY+0.008
z+0.008
 chip+0.007
Mac+0.007
Neg logit contributions
adow-0.005
 lived-0.004
 sorts-0.004
 night-0.004
arium-0.004
Token bites
Token ID26081
Feature activation+1.42e-02

Pos logit contributions
balls+0.023
Mac+0.022
bled+0.021
MY+0.021
z+0.021
Neg logit contributions
adow-0.024
 about-0.022
 lived-0.022
 night-0.021
 adventure-0.021
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
balls+0.028
bled+0.027
Mac+0.026
ula+0.026
MY+0.026
Neg logit contributions
adow-0.019
 lived-0.017
 about-0.016
 adventure-0.016
arium-0.016
Token makes
Token ID1838
Feature activation+3.61e-02

Pos logit contributions
MY+0.025
bled+0.025
balls+0.024
Mac+0.024
z+0.023
Neg logit contributions
adow-0.028
 lived-0.028
 about-0.027
 night-0.026
 day-0.026
Token Ben
Token ID3932
Feature activation+8.59e-02

Pos logit contributions
MY+0.060
bled+0.060
balls+0.059
Mac+0.059
z+0.057
Neg logit contributions
adow-0.056
 lived-0.054
 about-0.054
 night-0.052
 day-0.051
Token itch
Token ID49700
Feature activation+4.08e-02

Pos logit contributions
bled+0.141
MY+0.139
balls+0.138
Mac+0.136
ula+0.131
Neg logit contributions
adow-0.139
 lived-0.132
 about-0.131
 night-0.128
 day-0.125
Token.
Token ID13
Feature activation+2.01e-02

Pos logit contributions
balls+0.090
bled+0.087
MY+0.086
z+0.085
Mac+0.085
Neg logit contributions
adow-0.041
 lived-0.040
 night-0.035
 about-0.035
 day-0.035
Token Ben
Token ID3932
Feature activation+5.28e-02

Pos logit contributions
bled+0.045
z+0.044
MY+0.044
balls+0.043
Mac+0.041
Neg logit contributions
 about-0.021
 lived-0.020
adow-0.019
 of-0.018
 night-0.018
Token does
Token ID857
Feature activation+2.16e-02

Pos logit contributions
bled+0.108
ula+0.104
MY+0.103
balls+0.098
z+0.098
Neg logit contributions
 lived-0.072
 about-0.069
adow-0.067
 night-0.063
 of-0.060
Token not
Token ID407
Feature activation-3.82e-03

Pos logit contributions
MY+0.040
bled+0.039
z+0.039
 seventeen+0.038
 wrists+0.038
Neg logit contributions
 about-0.032
 today-0.028
 of-0.028
 lived-0.028
 because-0.028
Token be
Token ID307
Feature activation+3.88e-02

Pos logit contributions
MY+0.116
bled+0.115
Mac+0.111
balls+0.111
Marcus+0.109
Neg logit contributions
 about-0.094
 lived-0.093
adow-0.093
 night-0.089
 day-0.089
Tokenep
Token ID538
Feature activation+2.81e-02

Pos logit contributions
MY+0.057
bled+0.056
balls+0.055
Mac+0.055
ula+0.054
Neg logit contributions
 about-0.068
adow-0.068
 lived-0.068
 day-0.066
 of-0.065
Token,
Token ID11
Feature activation+7.10e-02

Pos logit contributions
balls+0.057
bled+0.057
MY+0.056
Mac+0.056
z+0.055
Neg logit contributions
adow-0.033
 lived-0.032
 about-0.031
 night-0.030
 day-0.029
Token and
Token ID290
Feature activation+1.58e-02

Pos logit contributions
MY+0.117
bled+0.117
balls+0.116
Mac+0.115
z+0.111
Neg logit contributions
adow-0.110
 lived-0.107
 about-0.105
 night-0.102
 day-0.101
Token scree
Token ID43465
Feature activation+2.40e-02

Pos logit contributions
balls+0.025
Mac+0.024
bled+0.024
 eighteen+0.023
 seventeen+0.023
Neg logit contributions
adow-0.027
 lived-0.025
 about-0.024
 night-0.024
 day-0.023
Tokench
Token ID354
Feature activation+8.54e-02

Pos logit contributions
bled+0.042
balls+0.042
 wrists+0.041
Marcus+0.041
MY+0.041
Neg logit contributions
 about-0.034
 of-0.033
 lived-0.033
adow-0.033
 night-0.033
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
bled+0.184
MY+0.183
balls+0.182
Mac+0.182
Marcus+0.176
Neg logit contributions
adow-0.088
 lived-0.084
 about-0.083
 night-0.079
 day-0.077
Token
Token ID198
Feature activation+1.16e-02

Pos logit contributions
bled+0.031
MY+0.031
balls+0.030
Mac+0.030
z+0.030
Neg logit contributions
adow-0.017
 lived-0.016
 about-0.016
 night-0.015
 day-0.015
Token
Token ID198
Feature activation+8.67e-03

Pos logit contributions
bled+0.023
balls+0.023
MY+0.023
Mac+0.022
z+0.021
Neg logit contributions
adow-0.014
 lived-0.014
 about-0.014
 night-0.013
 day-0.013
TokenOne
Token ID3198
Feature activation-1.87e-02

Pos logit contributions
bled+0.016
MY+0.016
balls+0.016
Mac+0.015
z+0.015
Neg logit contributions
adow-0.012
 lived-0.012
 about-0.011
 day-0.011
 night-0.011
Token day
Token ID1110
Feature activation+5.42e-02

Pos logit contributions
adow+0.014
 privacy+0.013
arium+0.012
yard+0.012
 shouldn+0.012
Neg logit contributions
 chip-0.040
z-0.038
Mac-0.038
Anna-0.038
balls-0.038
Token making
Token ID1642
Feature activation+2.40e-02

Pos logit contributions
bled+0.010
MY+0.010
balls+0.010
Mac+0.010
 eighteen+0.009
Neg logit contributions
adow-0.007
 lived-0.007
 about-0.007
 night-0.007
 day-0.007
Token snow
Token ID6729
Feature activation+6.93e-02

Pos logit contributions
MY+0.043
bled+0.042
Mac+0.041
balls+0.041
 seventeen+0.040
Neg logit contributions
 about-0.036
adow-0.035
 lived-0.034
 night-0.033
 adventure-0.033
Tokenmen
Token ID3653
Feature activation+3.74e-02

Pos logit contributions
MY+0.102
Mac+0.101
Marcus+0.100
bled+0.099
ula+0.098
Neg logit contributions
adow-0.118
 about-0.117
 lived-0.116
 night-0.113
 day-0.112
Token and
Token ID290
Feature activation+2.09e-02

Pos logit contributions
balls+0.071
MY+0.069
bled+0.069
Mac+0.069
z+0.067
Neg logit contributions
adow-0.049
 lived-0.048
 about-0.046
 night-0.045
 day-0.044
Token throwing
Token ID9644
Feature activation+5.96e-02

Pos logit contributions
balls+0.030
Mac+0.029
bled+0.029
MY+0.029
 eighteen+0.028
Neg logit contributions
adow-0.037
 lived-0.035
 about-0.035
 night-0.034
 day-0.034
Token snow
Token ID6729
Feature activation+8.46e-02

Pos logit contributions
bled+0.106
MY+0.103
Marcus+0.100
Mac+0.099
ula+0.098
Neg logit contributions
 night-0.090
 lived-0.090
 day-0.087
 about-0.087
 of-0.085
Tokenballs
Token ID21591
Feature activation+5.67e-02

Pos logit contributions
Mac+0.133
MY+0.132
bled+0.131
Marcus+0.129
 seventeen+0.126
Neg logit contributions
adow-0.134
 lived-0.131
 about-0.130
 night-0.129
 day-0.127
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
balls+0.108
bled+0.103
MY+0.100
ula+0.100
z+0.098
Neg logit contributions
adow-0.079
 lived-0.077
 night-0.068
 sorts-0.068
 about-0.068
Token
Token ID198
Feature activation+1.77e-02

Pos logit contributions
bled+0.049
MY+0.048
balls+0.048
Mac+0.047
z+0.047
Neg logit contributions
 lived-0.021
adow-0.021
 about-0.020
 night-0.019
 day-0.019
Token
Token ID198
Feature activation+1.34e-02

Pos logit contributions
bled+0.042
balls+0.042
MY+0.041
 wrists+0.041
 seventeen+0.040
Neg logit contributions
 lived-0.015
 of-0.015
 about-0.015
 day-0.014
adow-0.013
Token"
Token ID1
Feature activation+4.94e-02

Pos logit contributions
bled+0.024
balls+0.024
MY+0.023
 extract+0.023
 wrists+0.023
Neg logit contributions
 lived-0.019
 of-0.018
 today-0.018
 day-0.018
adow-0.017
Token made
Token ID925
Feature activation+2.76e-02

Pos logit contributions
balls+0.012
bled+0.011
Mac+0.011
MY+0.011
 wrists+0.011
Neg logit contributions
adow-0.010
 about-0.009
 zone-0.009
 day-0.008
 night-0.008
Token snow
Token ID6729
Feature activation+6.97e-02

Pos logit contributions
MY+0.054
 seventeen+0.051
Mac+0.051
 eighteen+0.050
bled+0.050
Neg logit contributions
 about-0.040
 night-0.039
 lived-0.038
 of-0.037
 day-0.036
Tokenmen
Token ID3653
Feature activation+3.57e-02

Pos logit contributions
Marcus+0.096
Er+0.094
MY+0.093
ula+0.093
Mac+0.092
Neg logit contributions
 about-0.132
adow-0.130
 lived-0.128
 night-0.126
 of-0.125
Token,
Token ID11
Feature activation+6.42e-02

Pos logit contributions
bled+0.070
MY+0.069
balls+0.069
Mac+0.069
ula+0.066
Neg logit contributions
adow-0.046
 lived-0.043
 about-0.043
 night-0.041
 day-0.040
Token threw
Token ID9617
Feature activation+5.07e-02

Pos logit contributions
balls+0.098
bled+0.097
MY+0.097
Mac+0.096
z+0.092
Neg logit contributions
adow-0.108
 lived-0.105
 about-0.103
 night-0.101
 day-0.099
Token snow
Token ID6729
Feature activation+8.44e-02

Pos logit contributions
bled+0.100
MY+0.100
irling+0.097
ula+0.096
Marcus+0.096
Neg logit contributions
 night-0.072
 day-0.067
 lived-0.066
 of-0.065
 about-0.064
Tokenballs
Token ID21591
Feature activation+5.91e-02

Pos logit contributions
Marcus+0.118
Er+0.117
Mac+0.117
MY+0.113
Re+0.111
Neg logit contributions
 about-0.150
 lived-0.149
adow-0.148
 night-0.147
 day-0.147
Token,
Token ID11
Feature activation+7.72e-02

Pos logit contributions
balls+0.110
bled+0.109
MY+0.106
Mac+0.104
z+0.103
Neg logit contributions
adow-0.082
 lived-0.079
 about-0.073
 night-0.072
 day-0.070
Token and
Token ID290
Feature activation+2.39e-02

Pos logit contributions
MY+0.157
bled+0.153
Mac+0.150
ula+0.150
z+0.150
Neg logit contributions
 about-0.091
 lived-0.089
 night-0.089
 of-0.089
adow-0.088
Token slid
Token ID27803
Feature activation+3.71e-02

Pos logit contributions
balls+0.037
bled+0.037
MY+0.037
Mac+0.036
z+0.035
Neg logit contributions
adow-0.039
 lived-0.038
 about-0.038
 night-0.037
 day-0.036
Token down
Token ID866
Feature activation+5.16e-02

Pos logit contributions
ula+0.069
Marcus+0.069
Er+0.068
MY+0.068
Mac+0.068
Neg logit contributions
 night-0.052
 about-0.050
 lived-0.050
 day-0.049
adow-0.047
Token no
Token ID645
Feature activation+2.05e-02

Pos logit contributions
balls+0.022
bled+0.022
Mac+0.022
MY+0.021
 eighteen+0.021
Neg logit contributions
adow-0.024
 lived-0.022
 about-0.022
 night-0.021
 day-0.021
Token ball
Token ID2613
Feature activation+3.18e-02

Pos logit contributions
balls+0.031
 wrists+0.029
 eighteen+0.029
 chip+0.028
 seventeen+0.028
Neg logit contributions
adow-0.034
 lived-0.032
 about-0.031
 zone-0.030
arium-0.030
Token,
Token ID11
Feature activation+7.68e-02

Pos logit contributions
balls+0.059
bled+0.054
ula+0.053
z+0.052
 chip+0.052
Neg logit contributions
adow-0.048
 lived-0.043
 sorts-0.043
arium-0.041
 night-0.039
Token no
Token ID645
Feature activation+2.89e-03

Pos logit contributions
balls+0.117
Mac+0.109
bled+0.108
 eighteen+0.107
MY+0.105
Neg logit contributions
adow-0.134
 lived-0.127
 night-0.122
 about-0.120
 sorts-0.119
Token bike
Token ID7161
Feature activation+3.13e-02

Pos logit contributions
balls+0.004
 wrists+0.004
 eighteen+0.004
 chip+0.004
 seventeen+0.004
Neg logit contributions
adow-0.005
 lived-0.005
arium-0.005
 about-0.005
 night-0.004
Token,
Token ID11
Feature activation+8.43e-02

Pos logit contributions
balls+0.060
z+0.057
 chip+0.054
MY+0.053
bled+0.052
Neg logit contributions
adow-0.045
 sorts-0.039
arium-0.039
 lived-0.038
 night-0.038
Token no
Token ID645
Feature activation+3.32e-03

Pos logit contributions
balls+0.121
bled+0.115
Mac+0.114
 eighteen+0.112
MY+0.111
Neg logit contributions
adow-0.152
 lived-0.146
 about-0.140
 night-0.139
 day-0.136
Token k
Token ID479
Feature activation+2.00e-02

Pos logit contributions
balls+0.005
 eighteen+0.005
 wrists+0.004
 chip+0.004
 seventeen+0.004
Neg logit contributions
adow-0.006
 lived-0.006
arium-0.005
 about-0.005
 night-0.005
Tokenite
Token ID578
Feature activation+2.60e-02

Pos logit contributions
bled+0.035
MY+0.035
Mac+0.034
balls+0.034
 seventeen+0.034
Neg logit contributions
adow-0.029
 of-0.027
 lived-0.027
 about-0.026
 night-0.025
Token.
Token ID13
Feature activation+1.92e-02

Pos logit contributions
balls+0.052
z+0.049
bled+0.046
 chip+0.046
 eighteen+0.046
Neg logit contributions
adow-0.035
arium-0.031
 sorts-0.029
 lived-0.029
 night-0.028
Token They
Token ID1119
Feature activation+1.89e-02

Pos logit contributions
balls+0.036
Mac+0.036
MY+0.036
 eighteen+0.035
bled+0.035
Neg logit contributions
adow-0.025
 lived-0.023
 night-0.022
 day-0.022
 adventure-0.022
Token thirteen
Token ID28306
Feature activation+2.96e-02

Pos logit contributions
Marcus+0.105
MY+0.099
bled+0.099
ula+0.095
Tyler+0.093
Neg logit contributions
 of-0.135
 about-0.132
 today-0.126
 night-0.123
 day-0.122
Token,
Token ID11
Feature activation+7.95e-02

Pos logit contributions
bled+0.075
MY+0.074
Mac+0.074
ula+0.074
Marcus+0.073
Neg logit contributions
 about-0.021
adow-0.021
 night-0.020
 of-0.019
 day-0.019
Token fourteen
Token ID29167
Feature activation+1.80e-02

Pos logit contributions
Marcus+0.104
MY+0.101
bled+0.099
ula+0.098
irling+0.093
Neg logit contributions
 of-0.161
 about-0.157
 night-0.151
 today-0.148
 day-0.143
Token,
Token ID11
Feature activation+8.36e-02

Pos logit contributions
bled+0.044
MY+0.043
ula+0.043
z+0.043
balls+0.043
Neg logit contributions
 night-0.014
 of-0.014
 day-0.014
 about-0.014
 lived-0.014
Token fifteen
Token ID17280
Feature activation+3.96e-02

Pos logit contributions
Marcus+0.107
bled+0.105
MY+0.104
ula+0.100
irling+0.097
Neg logit contributions
 of-0.172
 about-0.166
 today-0.161
 night-0.159
 lived-0.155
Token,
Token ID11
Feature activation+8.43e-02

Pos logit contributions
bled+0.096
Marcus+0.091
ula+0.091
MY+0.091
balls+0.090
Neg logit contributions
 of-0.037
 about-0.036
 day-0.033
 night-0.033
adow-0.032
Token sixteen
Token ID27913
Feature activation+1.98e-02

Pos logit contributions
Marcus+0.099
bled+0.090
MY+0.087
ula+0.086
Tyler+0.086
Neg logit contributions
 of-0.189
 about-0.181
 night-0.173
 day-0.171
 today-0.171
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
bled+0.049
MY+0.047
balls+0.047
ula+0.047
Marcus+0.046
Neg logit contributions
 of-0.017
 about-0.017
adow-0.016
 day-0.016
 night-0.015
Token seventeen
Token ID38741
Feature activation+4.18e-02

Pos logit contributions
Marcus+0.092
bled+0.080
ula+0.078
Tyler+0.078
MY+0.076
Neg logit contributions
 of-0.189
 about-0.181
 day-0.175
 night-0.173
 lived-0.172
Token,
Token ID11
Feature activation+8.24e-02

Pos logit contributions
bled+0.114
ula+0.112
MY+0.109
balls+0.109
Marcus+0.106
Neg logit contributions
 about-0.028
 of-0.025
 day-0.022
 today-0.022
adow-0.022
Token eighteen
Token ID29095
Feature activation+3.00e-02

Pos logit contributions
Marcus+0.097
bled+0.086
MY+0.085
Tyler+0.085
ula+0.084
Neg logit contributions
 of-0.184
 about-0.180
 day-0.168
 today-0.168
 lived-0.167
Token twelve
Token ID14104
Feature activation+6.23e-03

Pos logit contributions
Marcus+0.102
bled+0.098
MY+0.096
ula+0.092
Tyler+0.091
Neg logit contributions
 of-0.125
 about-0.119
 today-0.116
 day-0.114
 night-0.114
Token,
Token ID11
Feature activation+6.98e-02

Pos logit contributions
bled+0.015
MY+0.014
balls+0.014
Mac+0.014
Marcus+0.014
Neg logit contributions
 about-0.006
adow-0.006
 of-0.005
 lived-0.005
 night-0.005
Token thirteen
Token ID28306
Feature activation+2.96e-02

Pos logit contributions
Marcus+0.105
MY+0.099
bled+0.099
ula+0.095
Tyler+0.093
Neg logit contributions
 of-0.135
 about-0.132
 today-0.126
 night-0.123
 day-0.122
Token,
Token ID11
Feature activation+7.95e-02

Pos logit contributions
bled+0.075
MY+0.074
Mac+0.074
ula+0.074
Marcus+0.073
Neg logit contributions
 about-0.021
adow-0.021
 night-0.020
 of-0.019
 day-0.019
Token fourteen
Token ID29167
Feature activation+1.80e-02

Pos logit contributions
Marcus+0.104
MY+0.101
bled+0.099
ula+0.098
irling+0.093
Neg logit contributions
 of-0.161
 about-0.157
 night-0.151
 today-0.148
 day-0.143
Token,
Token ID11
Feature activation+8.36e-02

Pos logit contributions
bled+0.044
MY+0.043
ula+0.043
z+0.043
balls+0.043
Neg logit contributions
 night-0.014
 of-0.014
 day-0.014
 about-0.014
 lived-0.014
Token fifteen
Token ID17280
Feature activation+3.96e-02

Pos logit contributions
Marcus+0.107
bled+0.105
MY+0.104
ula+0.100
irling+0.097
Neg logit contributions
 of-0.172
 about-0.166
 today-0.161
 night-0.159
 lived-0.155
Token,
Token ID11
Feature activation+8.43e-02

Pos logit contributions
bled+0.096
Marcus+0.091
ula+0.091
MY+0.091
balls+0.090
Neg logit contributions
 of-0.037
 about-0.036
 day-0.033
 night-0.033
adow-0.032
Token sixteen
Token ID27913
Feature activation+1.98e-02

Pos logit contributions
Marcus+0.099
bled+0.090
MY+0.087
ula+0.086
Tyler+0.086
Neg logit contributions
 of-0.189
 about-0.181
 night-0.173
 day-0.171
 today-0.171
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
bled+0.049
MY+0.047
balls+0.047
ula+0.047
Marcus+0.046
Neg logit contributions
 of-0.017
 about-0.017
adow-0.016
 day-0.016
 night-0.015
Token seventeen
Token ID38741
Feature activation+4.18e-02

Pos logit contributions
Marcus+0.092
bled+0.080
ula+0.078
Tyler+0.078
MY+0.076
Neg logit contributions
 of-0.189
 about-0.181
 day-0.175
 night-0.173
 lived-0.172
Token ball
Token ID2613
Feature activation+3.42e-02

Pos logit contributions
 wrists+0.021
balls+0.021
 chip+0.020
 eighteen+0.020
bled+0.020
Neg logit contributions
adow-0.025
 lived-0.024
 about-0.023
arium-0.022
 zone-0.022
Token,
Token ID11
Feature activation+7.82e-02

Pos logit contributions
balls+0.065
bled+0.058
MY+0.057
z+0.057
 chip+0.057
Neg logit contributions
adow-0.051
 sorts-0.047
 lived-0.045
 kinds-0.041
grand-0.041
Token no
Token ID645
Feature activation+5.71e-04

Pos logit contributions
balls+0.103
bled+0.096
 eighteen+0.093
Mac+0.092
ula+0.091
Neg logit contributions
adow-0.153
 lived-0.143
 sorts-0.140
 night-0.137
 about-0.136
Token k
Token ID479
Feature activation+1.70e-02

Pos logit contributions
balls+0.001
 chip+0.001
 wrists+0.001
 eighteen+0.001
 swirl+0.001
Neg logit contributions
adow-0.001
 lived-0.001
arium-0.001
 about-0.001
 ruled-0.001
Tokenite
Token ID578
Feature activation+2.38e-02

Pos logit contributions
bled+0.034
MY+0.034
balls+0.033
Mac+0.033
Marcus+0.032
Neg logit contributions
adow-0.021
 lived-0.020
 of-0.019
 about-0.019
 night-0.018
Token,
Token ID11
Feature activation+8.31e-02

Pos logit contributions
balls+0.047
z+0.045
 chip+0.042
bled+0.041
MY+0.041
Neg logit contributions
adow-0.032
 sorts-0.029
arium-0.027
 lived-0.026
 lately-0.026
Token no
Token ID645
Feature activation+7.35e-04

Pos logit contributions
balls+0.109
bled+0.103
 eighteen+0.100
Mac+0.098
MY+0.096
Neg logit contributions
adow-0.161
 lived-0.152
 sorts-0.149
 night-0.146
 about-0.145
Token mole
Token ID9411
Feature activation+2.52e-02

Pos logit contributions
balls+0.001
 chip+0.001
 eighteen+0.001
 wrists+0.001
 swirl+0.001
Neg logit contributions
adow-0.001
 lived-0.001
arium-0.001
 about-0.001
grand-0.001
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
balls+0.053
z+0.048
MY+0.048
bled+0.047
 eighteen+0.047
Neg logit contributions
adow-0.029
 sorts-0.028
 lived-0.027
 night-0.026
 about-0.025
Token They
Token ID1119
Feature activation+1.55e-02

Pos logit contributions
bled+0.033
balls+0.033
MY+0.033
Mac+0.033
z+0.032
Neg logit contributions
adow-0.015
 lived-0.015
 about-0.014
 night-0.014
 day-0.013
Token have
Token ID423
Feature activation+2.16e-02

Pos logit contributions
Mac+0.024
balls+0.024
 eighteen+0.023
 wrists+0.023
aults+0.023
Neg logit contributions
adow-0.024
arium-0.022
 zone-0.022
 about-0.022
 sorts-0.021
Token.
Token ID13
Feature activation+8.52e-03

Pos logit contributions
 lived+0.015
adow+0.015
 night+0.013
 sorts+0.012
arium+0.012
Neg logit contributions
balls-0.027
MY-0.026
bled-0.026
z-0.026
 eighteen-0.026
Token He
Token ID679
Feature activation+2.37e-02

Pos logit contributions
balls+0.018
MY+0.018
Mac+0.018
bled+0.018
z+0.017
Neg logit contributions
adow-0.009
 lived-0.009
 about-0.009
 night-0.008
 day-0.008
Token trips
Token ID13229
Feature activation+5.26e-02

Pos logit contributions
MY+0.040
bled+0.040
balls+0.039
ula+0.038
Mac+0.038
Neg logit contributions
 lived-0.037
adow-0.036
 about-0.035
 night-0.034
 day-0.033
Token and
Token ID290
Feature activation+1.84e-02

Pos logit contributions
MY+0.097
Mac+0.094
balls+0.094
 seventeen+0.093
bled+0.093
Neg logit contributions
 about-0.073
 night-0.072
 of-0.072
adow-0.071
 day-0.071
Token falls
Token ID8953
Feature activation+3.68e-02

Pos logit contributions
balls+0.025
bled+0.025
MY+0.024
Mac+0.024
z+0.023
Neg logit contributions
adow-0.034
 lived-0.033
 about-0.033
 night-0.032
 day-0.032
Token,
Token ID11
Feature activation+8.29e-02

Pos logit contributions
balls+0.059
bled+0.057
MY+0.057
Mac+0.056
z+0.055
Neg logit contributions
adow-0.062
 lived-0.059
 about-0.056
arium-0.054
 adventure-0.053
Token and
Token ID290
Feature activation+3.69e-02

Pos logit contributions
MY+0.144
bled+0.141
Mac+0.140
balls+0.139
z+0.136
Neg logit contributions
adow-0.120
 lived-0.120
 about-0.119
 night-0.117
 day-0.114
Token the
Token ID262
Feature activation+3.23e-02

Pos logit contributions
balls+0.056
bled+0.054
Mac+0.054
MY+0.053
z+0.052
Neg logit contributions
adow-0.064
 lived-0.061
 about-0.060
 day-0.057
 night-0.057
Token ball
Token ID2613
Feature activation+2.43e-02

Pos logit contributions
bled+0.051
MY+0.051
Mac+0.050
balls+0.050
z+0.049
Neg logit contributions
adow-0.052
 lived-0.051
 night-0.050
 day-0.049
 about-0.049
Token rolls
Token ID14088
Feature activation+4.83e-02

Pos logit contributions
balls+0.044
bled+0.042
z+0.042
Mac+0.040
MY+0.040
Neg logit contributions
adow-0.037
 lived-0.033
 about-0.032
arium-0.032
 sorts-0.031
Token away
Token ID1497
Feature activation+1.76e-02

Pos logit contributions
balls+0.078
bled+0.076
MY+0.076
z+0.073
Mac+0.072
Neg logit contributions
adow-0.081
 lived-0.075
 about-0.072
 night-0.070
 day-0.069
Token You
Token ID921
Feature activation+9.81e-05

Pos logit contributions
adow+0.023
 lived+0.022
 about+0.021
 night+0.021
 day+0.020
Neg logit contributions
balls-0.032
Mac-0.032
MY-0.032
bled-0.031
 seventeen-0.030
Token can
Token ID460
Feature activation+2.56e-02

Pos logit contributions
Mac+0.000
balls+0.000
 eighteen+0.000
bled+0.000
MY+0.000
Neg logit contributions
adow-0.000
 about-0.000
arium-0.000
 day-0.000
 zone-0.000
Token play
Token ID711
Feature activation+5.33e-02

Pos logit contributions
bled+0.054
MY+0.053
balls+0.053
Mac+0.051
ula+0.051
Neg logit contributions
 lived-0.029
adow-0.029
 about-0.028
 night-0.027
 day-0.027
Token hop
Token ID1725
Feature activation+4.96e-02

Pos logit contributions
bled+0.106
MY+0.106
Marcus+0.105
 seventeen+0.105
Mac+0.104
Neg logit contributions
 about-0.072
 lived-0.069
 today-0.068
 day-0.064
 of-0.064
Tokensc
Token ID1416
Feature activation+4.05e-02

Pos logit contributions
bled+0.092
Mac+0.091
MY+0.091
balls+0.091
Marcus+0.088
Neg logit contributions
adow-0.066
 lived-0.065
 about-0.065
 night-0.063
 day-0.063
Tokenot
Token ID313
Feature activation+8.29e-02

Pos logit contributions
bled+0.065
Mac+0.064
MY+0.064
balls+0.064
Marcus+0.061
Neg logit contributions
adow-0.065
 lived-0.062
 about-0.062
 day-0.060
 of-0.060
Tokench
Token ID354
Feature activation+8.87e-02

Pos logit contributions
bled+0.133
balls+0.131
MY+0.131
Mac+0.129
z+0.124
Neg logit contributions
adow-0.132
 lived-0.128
 about-0.127
 night-0.125
 day-0.123
Token again
Token ID757
Feature activation+2.74e-02

Pos logit contributions
bled+0.175
MY+0.175
Mac+0.173
balls+0.172
Marcus+0.167
Neg logit contributions
adow-0.107
 lived-0.103
 about-0.102
 night-0.099
 day-0.098
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
bled+0.055
balls+0.055
MY+0.055
Mac+0.054
z+0.053
Neg logit contributions
adow-0.033
 lived-0.031
 about-0.031
 night-0.030
 day-0.029
Token But
Token ID887
Feature activation-2.83e-03

Pos logit contributions
adow+0.010
 lived+0.009
 about+0.009
 night+0.009
 day+0.009
Neg logit contributions
balls-0.015
bled-0.015
MY-0.015
Mac-0.015
z-0.015
Token you
Token ID345
Feature activation-2.86e-03

Pos logit contributions
adow+0.003
 lived+0.003
 about+0.003
 night+0.003
 day+0.003
Neg logit contributions
MY-0.006
balls-0.005
bled-0.005
Mac-0.005
z-0.005
Token thirteen
Token ID28306
Feature activation+2.80e-02

Pos logit contributions
Marcus+0.096
bled+0.096
MY+0.095
balls+0.089
ula+0.088
Neg logit contributions
 of-0.123
 today-0.119
 about-0.117
 ago-0.113
 because-0.112
Token,
Token ID11
Feature activation+7.98e-02

Pos logit contributions
Mac+0.068
bled+0.068
MY+0.067
balls+0.067
ula+0.067
Neg logit contributions
adow-0.022
 about-0.022
 night-0.021
 day-0.020
 of-0.020
Token fourteen
Token ID29167
Feature activation+1.58e-02

Pos logit contributions
Marcus+0.097
MY+0.096
bled+0.095
ula+0.091
balls+0.091
Neg logit contributions
 of-0.161
 about-0.156
 today-0.153
 night-0.152
 lived-0.145
Token,
Token ID11
Feature activation+8.24e-02

Pos logit contributions
bled+0.039
MY+0.038
ula+0.038
balls+0.038
z+0.038
Neg logit contributions
 night-0.012
 lived-0.012
 of-0.012
 day-0.012
adow-0.012
Token fifteen
Token ID17280
Feature activation+3.69e-02

Pos logit contributions
bled+0.102
MY+0.100
Marcus+0.099
ula+0.095
irling+0.095
Neg logit contributions
 of-0.166
 today-0.160
 about-0.158
 night-0.155
 lived-0.153
Token,
Token ID11
Feature activation+8.27e-02

Pos logit contributions
bled+0.095
Marcus+0.089
balls+0.089
Mac+0.088
ula+0.088
Neg logit contributions
 of-0.030
adow-0.028
 about-0.028
 day-0.027
 night-0.026
Token sixteen
Token ID27913
Feature activation+1.74e-02

Pos logit contributions
Marcus+0.093
bled+0.090
MY+0.084
Tyler+0.084
ula+0.084
Neg logit contributions
 of-0.179
 about-0.168
 today-0.167
 night-0.164
 day-0.162
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
bled+0.045
balls+0.044
MY+0.043
Marcus+0.043
Mac+0.043
Neg logit contributions
 of-0.013
 about-0.013
adow-0.013
 day-0.012
 lived-0.012
Token seventeen
Token ID38741
Feature activation+4.12e-02

Pos logit contributions
Marcus+0.090
bled+0.084
Tyler+0.079
ula+0.078
MY+0.076
Neg logit contributions
 of-0.176
 about-0.165
 day-0.163
 lived-0.162
 night-0.161
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
bled+0.117
ula+0.114
balls+0.113
MY+0.112
z+0.110
Neg logit contributions
 about-0.021
 today-0.018
 of-0.018
adow-0.017
 day-0.016
Token eighteen
Token ID29095
Feature activation+2.81e-02

Pos logit contributions
Marcus+0.090
bled+0.084
MY+0.082
Tyler+0.081
ula+0.080
Neg logit contributions
 of-0.179
 about-0.171
 today-0.165
 lived-0.163
 day-0.162
Token no
Token ID645
Feature activation+1.03e-02

Pos logit contributions
balls+0.011
bled+0.011
Mac+0.011
 eighteen+0.011
 seventeen+0.011
Neg logit contributions
adow-0.014
 lived-0.012
 about-0.012
 night-0.012
 day-0.012
Token soup
Token ID17141
Feature activation+3.22e-02

Pos logit contributions
balls+0.015
 eighteen+0.015
 seventeen+0.015
 wrists+0.015
bled+0.014
Neg logit contributions
adow-0.018
 lived-0.017
 about-0.016
arium-0.015
 night-0.015
Token,
Token ID11
Feature activation+7.57e-02

Pos logit contributions
balls+0.069
bled+0.065
MY+0.064
 chip+0.062
ula+0.062
Neg logit contributions
adow-0.038
 lived-0.034
 sorts-0.034
 night-0.030
arium-0.030
Token no
Token ID645
Feature activation+1.85e-03

Pos logit contributions
balls+0.113
bled+0.108
 eighteen+0.104
Mac+0.102
MY+0.101
Neg logit contributions
adow-0.133
 lived-0.126
 sorts-0.120
 night-0.120
 about-0.119
Token water
Token ID1660
Feature activation+4.09e-02

Pos logit contributions
balls+0.003
 eighteen+0.003
 seventeen+0.003
 wrists+0.003
bled+0.003
Neg logit contributions
adow-0.003
 lived-0.003
 about-0.003
arium-0.003
 zone-0.003
Token,
Token ID11
Feature activation+8.26e-02

Pos logit contributions
balls+0.085
bled+0.082
MY+0.079
z+0.077
 eighteen+0.077
Neg logit contributions
adow-0.049
 lived-0.044
 sorts-0.043
 about-0.041
 night-0.041
Token no
Token ID645
Feature activation+2.60e-03

Pos logit contributions
balls+0.120
bled+0.116
 eighteen+0.113
Mac+0.109
 seventeen+0.109
Neg logit contributions
adow-0.147
 lived-0.141
 night-0.133
 sorts-0.133
 about-0.133
Token ship
Token ID4074
Feature activation+3.98e-02

Pos logit contributions
balls+0.004
 eighteen+0.004
 seventeen+0.004
 wrists+0.004
bled+0.004
Neg logit contributions
adow-0.005
 lived-0.004
 about-0.004
arium-0.004
 zone-0.004
Token,
Token ID11
Feature activation+8.07e-02

Pos logit contributions
balls+0.081
bled+0.076
z+0.075
MY+0.074
 eighteen+0.073
Neg logit contributions
adow-0.051
 sorts-0.047
 lived-0.045
 night-0.043
arium-0.042
Token no
Token ID645
Feature activation+2.20e-03

Pos logit contributions
balls+0.121
bled+0.117
 eighteen+0.113
Mac+0.109
 seventeen+0.109
Neg logit contributions
adow-0.140
 lived-0.133
 sorts-0.129
 night-0.127
 about-0.126
Token treasure
Token ID14068
Feature activation+2.76e-02

Pos logit contributions
balls+0.003
 eighteen+0.003
 seventeen+0.003
bled+0.003
 wrists+0.003
Neg logit contributions
adow-0.004
 lived-0.004
 about-0.003
arium-0.003
 sorts-0.003
Token fifteen
Token ID17280
Feature activation+3.96e-02

Pos logit contributions
Marcus+0.107
bled+0.105
MY+0.104
ula+0.100
irling+0.097
Neg logit contributions
 of-0.172
 about-0.166
 today-0.161
 night-0.159
 lived-0.155
Token,
Token ID11
Feature activation+8.43e-02

Pos logit contributions
bled+0.096
Marcus+0.091
ula+0.091
MY+0.091
balls+0.090
Neg logit contributions
 of-0.037
 about-0.036
 day-0.033
 night-0.033
adow-0.032
Token sixteen
Token ID27913
Feature activation+1.98e-02

Pos logit contributions
Marcus+0.099
bled+0.090
MY+0.087
ula+0.086
Tyler+0.086
Neg logit contributions
 of-0.189
 about-0.181
 night-0.173
 day-0.171
 today-0.171
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
bled+0.049
MY+0.047
balls+0.047
ula+0.047
Marcus+0.046
Neg logit contributions
 of-0.017
 about-0.017
adow-0.016
 day-0.016
 night-0.015
Token seventeen
Token ID38741
Feature activation+4.18e-02

Pos logit contributions
Marcus+0.092
bled+0.080
ula+0.078
Tyler+0.078
MY+0.076
Neg logit contributions
 of-0.189
 about-0.181
 day-0.175
 night-0.173
 lived-0.172
Token,
Token ID11
Feature activation+8.24e-02

Pos logit contributions
bled+0.114
ula+0.112
MY+0.109
balls+0.109
Marcus+0.106
Neg logit contributions
 about-0.028
 of-0.025
 day-0.022
 today-0.022
adow-0.022
Token eighteen
Token ID29095
Feature activation+3.00e-02

Pos logit contributions
Marcus+0.097
bled+0.086
MY+0.085
Tyler+0.085
ula+0.084
Neg logit contributions
 of-0.184
 about-0.180
 day-0.168
 today-0.168
 lived-0.167
Token,
Token ID11
Feature activation+8.03e-02

Pos logit contributions
bled+0.076
MY+0.075
ula+0.074
Marcus+0.072
Mac+0.072
Neg logit contributions
 about-0.024
 of-0.023
adow-0.022
 day-0.020
 lived-0.020
Token nineteen
Token ID43063
Feature activation-9.18e-03

Pos logit contributions
Marcus+0.097
bled+0.090
MY+0.089
ula+0.087
Tyler+0.085
Neg logit contributions
 of-0.174
 about-0.171
 today-0.160
 lived-0.159
 day-0.159
Token,
Token ID11
Feature activation+5.48e-02

Pos logit contributions
 about+0.008
adow+0.007
 of+0.007
 lived+0.007
 day+0.007
Neg logit contributions
MY-0.023
bled-0.023
balls-0.022
Mac-0.022
z-0.022
Token twenty
Token ID8208
Feature activation+2.29e-02

Pos logit contributions
MY+0.074
Marcus+0.073
bled+0.072
ula+0.068
Tyler+0.067
Neg logit contributions
 about-0.109
 of-0.108
 today-0.100
 night-0.097
 because-0.096
Token you
Token ID345
Feature activation+1.29e-02

Pos logit contributions
balls+0.133
bled+0.132
MY+0.131
Mac+0.130
z+0.127
Neg logit contributions
adow-0.075
 lived-0.072
 about-0.069
 night-0.067
 day-0.065
Token will
Token ID481
Feature activation+1.55e-02

Pos logit contributions
balls+0.022
Mac+0.021
bled+0.020
z+0.020
MY+0.020
Neg logit contributions
adow-0.020
arium-0.018
 lived-0.018
 about-0.017
 sorts-0.017
Token have
Token ID423
Feature activation+2.78e-02

Pos logit contributions
bled+0.027
MY+0.027
balls+0.027
Mac+0.026
z+0.026
Neg logit contributions
adow-0.023
 lived-0.023
 about-0.023
 night-0.022
 day-0.022
Token no
Token ID645
Feature activation+1.46e-02

Pos logit contributions
balls+0.054
MY+0.054
bled+0.054
Mac+0.054
z+0.052
Neg logit contributions
adow-0.035
 lived-0.034
 about-0.033
 night-0.032
 day-0.031
Token toys
Token ID14958
Feature activation+3.23e-02

Pos logit contributions
balls+0.023
bled+0.022
MY+0.022
 eighteen+0.021
Mac+0.021
Neg logit contributions
adow-0.024
 lived-0.024
 about-0.022
arium-0.021
 night-0.021
Token,
Token ID11
Feature activation+8.24e-02

Pos logit contributions
balls+0.060
MY+0.057
bled+0.057
 eighteen+0.056
ula+0.055
Neg logit contributions
adow-0.044
 lived-0.043
 sorts-0.041
arium-0.037
 night-0.036
Token no
Token ID645
Feature activation+4.73e-03

Pos logit contributions
balls+0.140
bled+0.137
MY+0.135
Mac+0.135
 eighteen+0.132
Neg logit contributions
adow-0.125
 lived-0.121
 about-0.114
 night-0.114
 day-0.111
Token stories
Token ID3923
Feature activation+1.31e-02

Pos logit contributions
balls+0.007
 eighteen+0.007
 chip+0.007
MY+0.007
 seventeen+0.006
Neg logit contributions
adow-0.009
 lived-0.008
arium-0.007
 about-0.007
 zone-0.007
Token and
Token ID290
Feature activation+2.61e-02

Pos logit contributions
balls+0.023
MY+0.022
bled+0.022
 eighteen+0.022
z+0.021
Neg logit contributions
adow-0.018
 lived-0.017
 sorts-0.017
arium-0.016
 adventure-0.015
Token no
Token ID645
Feature activation+5.76e-03

Pos logit contributions
balls+0.041
 eighteen+0.038
 wrists+0.038
 seventeen+0.037
 chip+0.036
Neg logit contributions
adow-0.046
 lived-0.041
arium-0.039
 about-0.038
 night-0.038
Token hugs
Token ID40657
Feature activation+1.57e-02

Pos logit contributions
balls+0.009
 eighteen+0.008
 wrists+0.008
 chip+0.008
 seventeen+0.008
Neg logit contributions
adow-0.010
 lived-0.010
arium-0.009
 about-0.009
 zone-0.008
Token twelve
Token ID14104
Feature activation+1.14e-03

Pos logit contributions
bled+0.095
Marcus+0.094
MY+0.093
balls+0.089
ula+0.086
Neg logit contributions
 of-0.116
 today-0.114
 about-0.108
 night-0.107
 day-0.106
Token,
Token ID11
Feature activation+6.70e-02

Pos logit contributions
bled+0.003
MY+0.003
Mac+0.003
Marcus+0.003
balls+0.003
Neg logit contributions
adow-0.001
 about-0.001
 lived-0.001
 of-0.001
 day-0.001
Token thirteen
Token ID28306
Feature activation+2.80e-02

Pos logit contributions
Marcus+0.096
bled+0.096
MY+0.095
balls+0.089
ula+0.088
Neg logit contributions
 of-0.123
 today-0.119
 about-0.117
 ago-0.113
 because-0.112
Token,
Token ID11
Feature activation+7.98e-02

Pos logit contributions
Mac+0.068
bled+0.068
MY+0.067
balls+0.067
ula+0.067
Neg logit contributions
adow-0.022
 about-0.022
 night-0.021
 day-0.020
 of-0.020
Token fourteen
Token ID29167
Feature activation+1.58e-02

Pos logit contributions
Marcus+0.097
MY+0.096
bled+0.095
ula+0.091
balls+0.091
Neg logit contributions
 of-0.161
 about-0.156
 today-0.153
 night-0.152
 lived-0.145
Token,
Token ID11
Feature activation+8.24e-02

Pos logit contributions
bled+0.039
MY+0.038
ula+0.038
balls+0.038
z+0.038
Neg logit contributions
 night-0.012
 lived-0.012
 of-0.012
 day-0.012
adow-0.012
Token fifteen
Token ID17280
Feature activation+3.69e-02

Pos logit contributions
bled+0.102
MY+0.100
Marcus+0.099
ula+0.095
irling+0.095
Neg logit contributions
 of-0.166
 today-0.160
 about-0.158
 night-0.155
 lived-0.153
Token,
Token ID11
Feature activation+8.27e-02

Pos logit contributions
bled+0.095
Marcus+0.089
balls+0.089
Mac+0.088
ula+0.088
Neg logit contributions
 of-0.030
adow-0.028
 about-0.028
 day-0.027
 night-0.026
Token sixteen
Token ID27913
Feature activation+1.74e-02

Pos logit contributions
Marcus+0.093
bled+0.090
MY+0.084
Tyler+0.084
ula+0.084
Neg logit contributions
 of-0.179
 about-0.168
 today-0.167
 night-0.164
 day-0.162
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
bled+0.045
balls+0.044
MY+0.043
Marcus+0.043
Mac+0.043
Neg logit contributions
 of-0.013
 about-0.013
adow-0.013
 day-0.012
 lived-0.012
Token seventeen
Token ID38741
Feature activation+4.12e-02

Pos logit contributions
Marcus+0.090
bled+0.084
Tyler+0.079
ula+0.078
MY+0.076
Neg logit contributions
 of-0.176
 about-0.165
 day-0.163
 lived-0.162
 night-0.161
Token "
Token ID366
Feature activation+4.80e-02

Pos logit contributions
balls+0.045
bled+0.044
MY+0.044
z+0.043
ula+0.042
Neg logit contributions
adow-0.048
 lived-0.047
 about-0.044
 night-0.042
 sorts-0.042
Tokench
Token ID354
Feature activation+6.29e-02

Pos logit contributions
balls+0.067
MY+0.066
bled+0.065
Mac+0.062
ula+0.062
Neg logit contributions
adow-0.087
 lived-0.086
 night-0.085
 day-0.084
 about-0.082
Tokenoo
Token ID2238
Feature activation+1.98e-02

Pos logit contributions
balls+0.105
bled+0.105
MY+0.104
Mac+0.103
z+0.100
Neg logit contributions
adow-0.096
 lived-0.093
 about-0.091
 night-0.088
 day-0.087
Token cho
Token ID1727
Feature activation+7.32e-02

Pos logit contributions
Mac+0.035
bled+0.035
MY+0.035
balls+0.034
Marcus+0.034
Neg logit contributions
adow-0.027
 lived-0.027
 about-0.027
 night-0.026
 day-0.026
Tokeno
Token ID78
Feature activation+6.12e-02

Pos logit contributions
bled+0.112
balls+0.112
MY+0.112
Mac+0.110
Marcus+0.105
Neg logit contributions
adow-0.122
 lived-0.117
 about-0.114
 night-0.112
 day-0.111
Token cho
Token ID1727
Feature activation+8.24e-02

Pos logit contributions
balls+0.097
bled+0.097
MY+0.097
Mac+0.096
z+0.091
Neg logit contributions
adow-0.098
 lived-0.095
 about-0.093
 night-0.091
 day-0.090
Tokeno
Token ID78
Feature activation+6.71e-02

Pos logit contributions
balls+0.126
bled+0.126
MY+0.126
Mac+0.124
Marcus+0.118
Neg logit contributions
adow-0.137
 lived-0.131
 about-0.128
 night-0.127
 day-0.124
Token".
Token ID1911
Feature activation+1.10e-02

Pos logit contributions
balls+0.105
bled+0.105
MY+0.104
Mac+0.103
z+0.099
Neg logit contributions
adow-0.109
 lived-0.106
 about-0.103
 night-0.101
 day-0.099
Token
Token ID198
Feature activation+5.39e-03

Pos logit contributions
bled+0.021
balls+0.021
MY+0.021
Mac+0.021
z+0.020
Neg logit contributions
adow-0.014
 lived-0.014
 about-0.013
 night-0.013
 day-0.013
Token
Token ID198
Feature activation+7.89e-04

Pos logit contributions
bled+0.011
balls+0.011
MY+0.011
Mac+0.010
 seventeen+0.010
Neg logit contributions
adow-0.007
 lived-0.006
 about-0.006
 night-0.006
 day-0.006
TokenThey
Token ID2990
Feature activation-7.09e-04

Pos logit contributions
bled+0.001
balls+0.001
MY+0.001
 seventeen+0.001
 eighteen+0.001
Neg logit contributions
adow-0.002
 lived-0.002
 day-0.001
 about-0.001
 of-0.001
TokenWe
Token ID1135
Feature activation-5.76e-03

Pos logit contributions
MY+0.077
bled+0.077
balls+0.071
z+0.070
irling+0.069
Neg logit contributions
 lived-0.078
 of-0.075
 day-0.073
 today-0.071
 night-0.069
Token put
Token ID1234
Feature activation+4.16e-02

Pos logit contributions
adow+0.007
 about+0.007
 lived+0.007
 night+0.007
 day+0.007
Neg logit contributions
bled-0.011
MY-0.011
balls-0.011
Mac-0.011
z-0.010
Token eggs
Token ID9653
Feature activation+2.06e-02

Pos logit contributions
MY+0.090
Mac+0.090
Marcus+0.088
ula+0.087
balls+0.086
Neg logit contributions
 night-0.050
 day-0.046
 about-0.044
 today-0.044
 of-0.042
Token,
Token ID11
Feature activation+7.35e-02

Pos logit contributions
Mac+0.041
MY+0.040
balls+0.040
Marcus+0.039
bled+0.039
Neg logit contributions
adow-0.027
 about-0.024
 night-0.024
 of-0.024
 lived-0.024
Token flour
Token ID10601
Feature activation+2.47e-02

Pos logit contributions
MY+0.118
bled+0.117
z+0.115
balls+0.114
Mac+0.113
Neg logit contributions
 about-0.119
 lived-0.117
adow-0.116
 of-0.114
 night-0.113
Token,
Token ID11
Feature activation+8.22e-02

Pos logit contributions
Mac+0.063
Marcus+0.061
bled+0.060
irling+0.060
Re+0.059
Neg logit contributions
 of-0.018
 night-0.017
 about-0.017
 today-0.017
adow-0.016
Token sugar
Token ID7543
Feature activation+3.21e-02

Pos logit contributions
MY+0.129
z+0.126
bled+0.126
Marcus+0.124
balls+0.124
Neg logit contributions
 of-0.142
 today-0.137
 about-0.133
 night-0.133
 because-0.128
Token,
Token ID11
Feature activation+7.90e-02

Pos logit contributions
Mac+0.079
Marcus+0.076
bled+0.075
Re+0.075
Cole+0.075
Neg logit contributions
 night-0.025
 of-0.025
 day-0.024
 about-0.024
 today-0.024
Token milk
Token ID7545
Feature activation+2.35e-02

Pos logit contributions
MY+0.131
bled+0.129
Marcus+0.128
Mac+0.127
z+0.127
Neg logit contributions
 of-0.129
 today-0.124
 about-0.121
 night-0.120
 because-0.117
Token,
Token ID11
Feature activation+7.89e-02

Pos logit contributions
Mac+0.056
bled+0.055
Marcus+0.054
irling+0.053
MY+0.053
Neg logit contributions
 night-0.020
 of-0.020
adow-0.019
 about-0.019
 day-0.019
Token and
Token ID290
Feature activation+2.79e-02

Pos logit contributions
MY+0.143
bled+0.141
Mac+0.140
Marcus+0.139
z+0.138
Neg logit contributions
 of-0.116
 today-0.112
 about-0.111
 night-0.107
 because-0.106
Token water
Token ID1660
Feature activation+4.26e-02

Pos logit contributions
balls+0.026
bled+0.024
 eighteen+0.024
MY+0.024
 seventeen+0.024
Neg logit contributions
adow-0.026
 lived-0.025
 about-0.024
 night-0.022
arium-0.022
Token guns
Token ID6541
Feature activation+1.82e-02

Pos logit contributions
balls+0.079
bled+0.077
MY+0.075
z+0.074
ula+0.073
Neg logit contributions
adow-0.059
 lived-0.055
 about-0.053
 night-0.052
 day-0.051
Token,
Token ID11
Feature activation+8.09e-02

Pos logit contributions
balls+0.029
bled+0.028
z+0.027
MY+0.027
 eighteen+0.026
Neg logit contributions
adow-0.030
 sorts-0.028
 lived-0.026
 kinds-0.025
arium-0.025
Token no
Token ID645
Feature activation+4.37e-03

Pos logit contributions
balls+0.132
bled+0.127
Mac+0.125
MY+0.124
 eighteen+0.122
Neg logit contributions
adow-0.130
 lived-0.124
 about-0.119
 night-0.119
 day-0.116
Token toys
Token ID14958
Feature activation+2.15e-02

Pos logit contributions
balls+0.006
 eighteen+0.006
 chip+0.006
 seventeen+0.006
MY+0.006
Neg logit contributions
adow-0.008
 lived-0.007
arium-0.007
 about-0.007
 night-0.007
Token,
Token ID11
Feature activation+8.21e-02

Pos logit contributions
balls+0.038
bled+0.034
MY+0.034
 chip+0.033
z+0.033
Neg logit contributions
adow-0.033
 sorts-0.031
 lived-0.029
arium-0.028
 kinds-0.028
Token and
Token ID290
Feature activation+2.97e-02

Pos logit contributions
balls+0.138
bled+0.133
Mac+0.130
MY+0.130
 eighteen+0.129
Neg logit contributions
adow-0.127
 lived-0.121
 night-0.116
 about-0.116
 day-0.113
Token no
Token ID645
Feature activation+3.19e-03

Pos logit contributions
balls+0.043
 eighteen+0.040
 seventeen+0.039
 chip+0.038
bled+0.038
Neg logit contributions
adow-0.055
 lived-0.048
arium-0.047
 zone-0.046
 night-0.046
Token TV
Token ID3195
Feature activation+2.41e-02

Pos logit contributions
balls+0.005
 eighteen+0.004
bled+0.004
 seventeen+0.004
MY+0.004
Neg logit contributions
adow-0.006
 lived-0.005
 about-0.005
arium-0.005
 night-0.005
Token.
Token ID13
Feature activation+2.04e-02

Pos logit contributions
balls+0.050
MY+0.046
bled+0.046
z+0.046
 chip+0.045
Neg logit contributions
adow-0.030
 sorts-0.025
 lived-0.025
arium-0.024
 about-0.024
Token They
Token ID1119
Feature activation+2.10e-02

Pos logit contributions
balls+0.039
MY+0.039
Mac+0.039
bled+0.038
ula+0.038
Neg logit contributions
adow-0.026
 lived-0.025
 about-0.024
 night-0.023
 adventure-0.023
Token day
Token ID1110
Feature activation+2.51e-02

Pos logit contributions
 zone+0.035
 privacy+0.032
 ago+0.030
arium+0.029
grand+0.028
Neg logit contributions
 chip-0.080
z-0.077
Mac-0.076
Danny-0.075
Pop-0.073
Token,
Token ID11
Feature activation+1.47e-02

Pos logit contributions
balls+0.048
bled+0.047
MY+0.046
z+0.045
Mac+0.045
Neg logit contributions
adow-0.034
 lived-0.031
 about-0.030
 night-0.029
 sorts-0.029
Token a
Token ID257
Feature activation-1.48e-02

Pos logit contributions
bled+0.021
balls+0.021
MY+0.020
Mac+0.020
z+0.020
Neg logit contributions
adow-0.026
 about-0.024
 lived-0.024
 night-0.023
 adventure-0.023
Token curious
Token ID11040
Feature activation-2.14e-02

Pos logit contributions
 day+0.021
 lived+0.020
 night+0.020
adow+0.018
 about+0.018
Neg logit contributions
bled-0.029
balls-0.028
z-0.028
 seventeen-0.027
 wrists-0.027
Token 3
Token ID513
Feature activation-1.67e-02

Pos logit contributions
adow+0.037
 lived+0.036
 about+0.035
 night+0.033
 day+0.032
Neg logit contributions
MY-0.030
balls-0.029
Mac-0.029
 chip-0.029
bled-0.029
Token year
Token ID614
Feature activation-9.13e-02

Pos logit contributions
adow+0.020
 about+0.018
 night+0.017
 lived+0.017
 zone+0.017
Neg logit contributions
MY-0.033
balls-0.032
z-0.031
 chip-0.031
Mac-0.031
Token old
Token ID1468
Feature activation-4.83e-02

Pos logit contributions
adow+0.164
 lived+0.163
 zone+0.154
 belong+0.145
 sorts+0.144
Neg logit contributions
MY-0.126
 chip-0.121
balls-0.117
ula-0.115
 seventeen-0.109
Token named
Token ID3706
Feature activation-4.76e-02

Pos logit contributions
adow+0.085
 about+0.078
 lived+0.072
 belong+0.071
arium+0.071
Neg logit contributions
MY-0.071
 chip-0.069
Mac-0.068
balls-0.066
bled-0.066
Token John
Token ID1757
Feature activation-9.21e-03

Pos logit contributions
adow+0.062
 lived+0.058
 night+0.056
 about+0.055
 day+0.054
Neg logit contributions
MY-0.091
Mac-0.090
balls-0.090
bled-0.088
ula-0.086
Token was
Token ID373
Feature activation-1.79e-02

Pos logit contributions
adow+0.013
 about+0.013
 lately+0.012
arium+0.011
 hour+0.011
Neg logit contributions
z-0.015
Mac-0.015
MY-0.015
Marcus-0.014
Er-0.014
Token playing
Token ID2712
Feature activation+1.97e-02

Pos logit contributions
adow+0.025
 lived+0.023
 about+0.023
arium+0.022
 night+0.022
Neg logit contributions
balls-0.032
bled-0.032
MY-0.030
Mac-0.030
z-0.030
TokenJohn
Token ID7554
Feature activation-2.80e-06

Pos logit contributions
adow+0.010
 lived+0.009
 about+0.009
 night+0.009
 adventure+0.009
Neg logit contributions
balls-0.011
Mac-0.011
bled-0.011
MY-0.011
z-0.010
Token was
Token ID373
Feature activation-1.30e-02

Feature not active on prev token;
no predictions were affected.
Token a
Token ID257
Feature activation-1.43e-02

Pos logit contributions
 about+0.018
adow+0.017
 night+0.017
 lived+0.016
 day+0.016
Neg logit contributions
MY-0.025
balls-0.025
Mac-0.025
bled-0.024
 seventeen-0.024
Token curious
Token ID11040
Feature activation-3.13e-02

Pos logit contributions
 day+0.021
 night+0.021
 lived+0.020
adow+0.020
 about+0.019
Neg logit contributions
bled-0.027
balls-0.027
Mac-0.025
z-0.025
ula-0.025
Token three
Token ID1115
Feature activation-3.78e-02

Pos logit contributions
adow+0.061
 lived+0.059
 belong+0.056
 about+0.055
arium+0.053
Neg logit contributions
MY-0.037
 chip-0.036
Mac-0.033
balls-0.032
ula-0.032
Token year
Token ID614
Feature activation-9.06e-02

Pos logit contributions
adow+0.037
 lived+0.033
 night+0.033
 belong+0.033
 about+0.032
Neg logit contributions
MY-0.079
balls-0.078
z-0.077
 chip-0.076
Mac-0.074
Token old
Token ID1468
Feature activation-5.73e-02

Pos logit contributions
 lived+0.169
adow+0.163
 belong+0.156
 zone+0.153
 sorts+0.145
Neg logit contributions
MY-0.119
 chip-0.113
balls-0.111
ula-0.109
z-0.104
Token.
Token ID13
Feature activation-3.60e-02

Pos logit contributions
adow+0.082
 lived+0.075
 belong+0.074
 about+0.073
 night+0.071
Neg logit contributions
MY-0.097
balls-0.097
 chip-0.097
bled-0.093
 wrists-0.093
Token He
Token ID679
Feature activation-2.27e-02

Pos logit contributions
adow+0.044
arium+0.037
 lived+0.037
 belong+0.037
 night+0.036
Neg logit contributions
 seventeen-0.068
 eighteen-0.066
Mac-0.065
 sixteen-0.064
 chip-0.063
Token liked
Token ID8288
Feature activation-2.28e-02

Pos logit contributions
adow+0.027
 about+0.024
 zone+0.024
 night+0.024
 of+0.024
Neg logit contributions
Mac-0.043
Marcus-0.041
balls-0.041
z-0.041
bled-0.040
Token to
Token ID284
Feature activation-1.06e-02

Pos logit contributions
adow+0.032
 lived+0.029
 zone+0.026
arium+0.026
 belong+0.026
Neg logit contributions
balls-0.042
Mac-0.040
 chip-0.040
bled-0.039
MY-0.039
TokenJohn
Token ID7554
Feature activation+4.19e-04

Pos logit contributions
adow+0.005
 lived+0.005
 about+0.005
 night+0.005
 adventure+0.005
Neg logit contributions
balls-0.006
Mac-0.006
bled-0.006
MY-0.006
z-0.005
Token was
Token ID373
Feature activation-1.63e-02

Pos logit contributions
MY+0.001
bled+0.001
balls+0.001
Mac+0.001
z+0.001
Neg logit contributions
adow-0.001
 about-0.001
 lived-0.001
 night-0.000
 day-0.000
Token a
Token ID257
Feature activation-1.23e-02

Pos logit contributions
 about+0.021
adow+0.021
 lived+0.020
 night+0.020
 day+0.020
Neg logit contributions
MY-0.032
balls-0.032
Mac-0.032
bled-0.031
 seventeen-0.031
Token curious
Token ID11040
Feature activation-2.83e-02

Pos logit contributions
 day+0.018
 night+0.018
 lived+0.017
adow+0.017
 about+0.016
Neg logit contributions
bled-0.023
balls-0.023
ula-0.022
Mac-0.022
z-0.021
Token 3
Token ID513
Feature activation-2.92e-02

Pos logit contributions
adow+0.055
 lived+0.055
 belong+0.051
 about+0.050
arium+0.049
Neg logit contributions
MY-0.033
 chip-0.032
Mac-0.029
Marcus-0.028
balls-0.028
Token year
Token ID614
Feature activation-8.90e-02

Pos logit contributions
adow+0.026
 belong+0.024
 lived+0.024
 night+0.024
arium+0.023
Neg logit contributions
MY-0.062
z-0.061
balls-0.060
 chip-0.059
Marcus-0.058
Token old
Token ID1468
Feature activation-5.42e-02

Pos logit contributions
 lived+0.168
adow+0.161
 belong+0.155
 zone+0.151
 sorts+0.144
Neg logit contributions
MY-0.116
 chip-0.109
balls-0.108
ula-0.106
z-0.101
Token.
Token ID13
Feature activation-3.55e-02

Pos logit contributions
adow+0.083
 lived+0.076
 about+0.075
 belong+0.074
 night+0.073
Neg logit contributions
MY-0.088
balls-0.087
 chip-0.086
bled-0.085
Mac-0.085
Token On
Token ID1550
Feature activation-4.01e-02

Pos logit contributions
adow+0.044
arium+0.038
 lived+0.037
 night+0.037
 belong+0.036
Neg logit contributions
 seventeen-0.067
 eighteen-0.065
Mac-0.064
 sixteen-0.064
MY-0.063
Token Tuesday
Token ID3431
Feature activation-2.86e-02

Pos logit contributions
adow+0.071
 zone+0.063
 about+0.061
 privacy+0.061
 belong+0.059
Neg logit contributions
bled-0.057
z-0.056
Mac-0.056
Marcus-0.055
Er-0.054
Token,
Token ID11
Feature activation+6.69e-04

Pos logit contributions
 privacy+0.048
adow+0.047
 zone+0.042
 belong+0.042
igator+0.041
Neg logit contributions
z-0.041
balls-0.039
 chip-0.038
MY-0.037
ula-0.036
Tokeny
Token ID88
Feature activation-2.51e-02

Pos logit contributions
MY+0.008
bled+0.008
Mac+0.008
balls+0.008
z+0.008
Neg logit contributions
adow-0.006
 about-0.005
 lived-0.005
 night-0.005
 day-0.005
Token was
Token ID373
Feature activation-1.28e-02

Pos logit contributions
adow+0.034
 lived+0.031
 about+0.031
 night+0.030
 day+0.030
Neg logit contributions
balls-0.045
MY-0.045
bled-0.045
Mac-0.044
z-0.043
Token a
Token ID257
Feature activation-1.19e-02

Pos logit contributions
 about+0.017
adow+0.017
 lived+0.016
 night+0.016
 day+0.016
Neg logit contributions
balls-0.025
MY-0.025
Mac-0.025
bled-0.024
 seventeen-0.024
Token curious
Token ID11040
Feature activation-2.74e-02

Pos logit contributions
 day+0.018
 night+0.018
 lived+0.017
adow+0.017
 about+0.016
Neg logit contributions
bled-0.023
balls-0.022
Mac-0.021
z-0.021
 seventeen-0.021
Token 3
Token ID513
Feature activation-2.99e-02

Pos logit contributions
adow+0.053
 lived+0.051
 belong+0.048
 about+0.048
arium+0.046
Neg logit contributions
MY-0.033
 chip-0.032
Mac-0.029
ula-0.029
balls-0.029
Token year
Token ID614
Feature activation-8.90e-02

Pos logit contributions
adow+0.028
 belong+0.026
 night+0.026
 lived+0.025
arium+0.025
Neg logit contributions
MY-0.063
z-0.061
balls-0.061
 chip-0.059
Marcus-0.059
Token old
Token ID1468
Feature activation-5.42e-02

Pos logit contributions
 lived+0.166
adow+0.162
 belong+0.155
 zone+0.152
 sorts+0.144
Neg logit contributions
MY-0.113
 chip-0.106
balls-0.105
ula-0.105
z-0.098
Token.
Token ID13
Feature activation-3.36e-02

Pos logit contributions
adow+0.081
 lived+0.073
 belong+0.072
 about+0.072
 night+0.071
Neg logit contributions
MY-0.090
balls-0.089
 chip-0.088
bled-0.087
Mac-0.086
Token She
Token ID1375
Feature activation-2.29e-02

Pos logit contributions
adow+0.042
 lived+0.037
 belong+0.036
 night+0.035
grand+0.034
Neg logit contributions
balls-0.061
Mac-0.060
 seventeen-0.060
MY-0.060
Marcus-0.059
Token was
Token ID373
Feature activation-2.10e-02

Pos logit contributions
adow+0.028
 about+0.025
 night+0.025
 zone+0.024
arium+0.024
Neg logit contributions
Mac-0.043
balls-0.042
Marcus-0.042
z-0.042
MY-0.041
Token always
Token ID1464
Feature activation-2.99e-02

Pos logit contributions
adow+0.026
 about+0.025
 lived+0.025
 night+0.023
 day+0.023
Neg logit contributions
MY-0.042
balls-0.042
bled-0.042
Mac-0.041
z-0.040
Token very
Token ID845
Feature activation-1.95e-02

Pos logit contributions
 day+0.020
 night+0.020
 lived+0.019
adow+0.019
 adventure+0.018
Neg logit contributions
bled-0.027
balls-0.026
z-0.024
Mac-0.024
 seventeen-0.024
Token intelligent
Token ID12661
Feature activation-4.34e-02

Pos logit contributions
adow+0.031
 lived+0.030
 day+0.030
 night+0.030
 about+0.030
Neg logit contributions
bled-0.032
Mac-0.032
balls-0.031
MY-0.031
z-0.030
Token and
Token ID290
Feature activation-3.88e-02

Pos logit contributions
adow+0.070
 lived+0.068
 about+0.066
 night+0.065
 day+0.063
Neg logit contributions
balls-0.069
bled-0.069
MY-0.068
Mac-0.067
z-0.065
Token curious
Token ID11040
Feature activation-3.38e-02

Pos logit contributions
adow+0.068
 about+0.061
arium+0.061
 night+0.061
 lived+0.060
Neg logit contributions
balls-0.055
bled-0.054
Mac-0.054
MY-0.052
z-0.051
Token three
Token ID1115
Feature activation-3.08e-02

Pos logit contributions
adow+0.061
 lived+0.060
 belong+0.055
 about+0.054
arium+0.054
Neg logit contributions
MY-0.042
 chip-0.042
balls-0.039
ula-0.039
 wrists-0.038
Token year
Token ID614
Feature activation-8.89e-02

Pos logit contributions
adow+0.033
 night+0.030
 lived+0.029
 about+0.028
arium+0.027
Neg logit contributions
balls-0.064
MY-0.064
z-0.063
bled-0.062
Mac-0.062
Token old
Token ID1468
Feature activation-5.29e-02

Pos logit contributions
 lived+0.149
adow+0.148
 night+0.135
 belong+0.134
 zone+0.133
Neg logit contributions
MY-0.131
balls-0.128
ula-0.127
bled-0.123
 chip-0.123
Token girl
Token ID2576
Feature activation-3.04e-02

Pos logit contributions
adow+0.064
 lived+0.055
 night+0.054
 about+0.053
arium+0.052
Neg logit contributions
balls-0.105
MY-0.103
 chip-0.102
 wrists-0.102
Mac-0.100
Token.
Token ID13
Feature activation-2.98e-02

Pos logit contributions
adow+0.030
 night+0.026
 about+0.026
 lived+0.026
 adventure+0.024
Neg logit contributions
balls-0.065
z-0.064
MY-0.064
bled-0.063
Mac-0.063
Token She
Token ID1375
Feature activation-2.08e-02

Pos logit contributions
adow+0.033
 lived+0.029
 night+0.027
arium+0.027
 about+0.026
Neg logit contributions
MY-0.061
Mac-0.060
balls-0.060
z-0.060
 wrists-0.059
Token loved
Token ID6151
Feature activation-2.45e-02

Pos logit contributions
adow+0.024
 about+0.022
 night+0.022
 lived+0.021
 day+0.021
Neg logit contributions
balls-0.041
Mac-0.041
bled-0.041
MY-0.040
z-0.040
TokenS
Token ID50
Feature activation-8.95e-03

Pos logit contributions
adow+0.009
 about+0.009
 night+0.009
 lived+0.009
 zone+0.008
Neg logit contributions
Mac-0.009
MY-0.008
z-0.008
balls-0.008
bled-0.008
Tokenally
Token ID453
Feature activation-2.99e-03

Pos logit contributions
adow+0.016
 lived+0.015
 about+0.015
 night+0.015
 day+0.014
Neg logit contributions
MY-0.013
bled-0.012
Mac-0.012
z-0.012
balls-0.012
Token,
Token ID11
Feature activation+4.94e-04

Pos logit contributions
adow+0.004
 about+0.004
 belong+0.004
 night+0.004
 zone+0.004
Neg logit contributions
z-0.005
Mac-0.005
MY-0.005
bled-0.005
balls-0.005
Token a
Token ID257
Feature activation-2.68e-02

Pos logit contributions
bled+0.001
balls+0.001
Mac+0.001
MY+0.001
z+0.001
Neg logit contributions
adow-0.001
 about-0.001
 lived-0.001
 night-0.001
 of-0.001
Token 3
Token ID513
Feature activation-1.91e-02

Pos logit contributions
 day+0.034
 lived+0.032
 night+0.032
 of+0.030
adow+0.028
Neg logit contributions
bled-0.057
balls-0.055
z-0.054
 seventeen-0.054
MY-0.053
Token year
Token ID614
Feature activation-8.85e-02

Pos logit contributions
adow+0.018
 night+0.016
 about+0.016
 lived+0.016
arium+0.015
Neg logit contributions
z-0.041
balls-0.041
MY-0.040
bled-0.040
Mac-0.039
Token old
Token ID1468
Feature activation-5.26e-02

Pos logit contributions
 lived+0.168
adow+0.168
 zone+0.160
 belong+0.155
 sorts+0.152
Neg logit contributions
MY-0.104
balls-0.101
 chip-0.098
bled-0.098
 seventeen-0.097
Token child
Token ID1200
Feature activation-3.84e-02

Pos logit contributions
adow+0.089
 about+0.083
 lived+0.082
 night+0.080
 day+0.078
Neg logit contributions
MY-0.077
balls-0.077
Mac-0.077
bled-0.077
z-0.075
Token,
Token ID11
Feature activation-7.71e-04

Pos logit contributions
adow+0.038
 night+0.035
 about+0.034
 zone+0.032
 day+0.032
Neg logit contributions
z-0.081
balls-0.080
Mac-0.079
MY-0.078
bled-0.078
Token saw
Token ID2497
Feature activation-1.67e-02

Pos logit contributions
adow+0.001
 night+0.001
 about+0.001
 day+0.001
 zone+0.001
Neg logit contributions
Mac-0.001
balls-0.001
bled-0.001
MY-0.001
z-0.001
Token the
Token ID262
Feature activation+3.89e-03

Pos logit contributions
adow+0.029
 lived+0.027
 about+0.026
 night+0.026
 day+0.026
Neg logit contributions
bled-0.025
balls-0.024
Mac-0.024
MY-0.024
z-0.023
Tokenobby
Token ID11369
Feature activation-4.49e-03

Pos logit contributions
balls+0.012
bled+0.012
MY+0.012
Mac+0.012
z+0.012
Neg logit contributions
adow-0.010
 lived-0.010
 about-0.010
 night-0.009
 day-0.009
Token was
Token ID373
Feature activation-1.45e-02

Pos logit contributions
adow+0.006
 about+0.005
 lived+0.005
 night+0.005
 day+0.005
Neg logit contributions
balls-0.008
bled-0.008
MY-0.008
Mac-0.008
z-0.008
Token a
Token ID257
Feature activation-1.03e-02

Pos logit contributions
 about+0.020
adow+0.019
 night+0.019
 day+0.018
 lived+0.018
Neg logit contributions
MY-0.029
balls-0.029
Mac-0.028
bled-0.027
 seventeen-0.027
Token curious
Token ID11040
Feature activation-2.88e-02

Pos logit contributions
 day+0.016
 night+0.016
 lived+0.015
adow+0.014
 adventure+0.014
Neg logit contributions
bled-0.020
balls-0.019
Mac-0.018
ula-0.018
 seventeen-0.018
Token three
Token ID1115
Feature activation-3.23e-02

Pos logit contributions
adow+0.056
 lived+0.054
 about+0.051
 belong+0.051
arium+0.049
Neg logit contributions
MY-0.035
 chip-0.033
Mac-0.032
balls-0.031
Marcus-0.031
Token year
Token ID614
Feature activation-8.82e-02

Pos logit contributions
adow+0.032
 night+0.028
 lived+0.028
 belong+0.027
 about+0.027
Neg logit contributions
MY-0.069
balls-0.068
z-0.066
 chip-0.066
Mac-0.065
Token old
Token ID1468
Feature activation-5.56e-02

Pos logit contributions
 lived+0.159
adow+0.155
 belong+0.147
 zone+0.143
 sorts+0.137
Neg logit contributions
MY-0.121
balls-0.115
 chip-0.115
ula-0.112
z-0.107
Token.
Token ID13
Feature activation-3.84e-02

Pos logit contributions
adow+0.075
 lived+0.068
 belong+0.066
 about+0.065
 night+0.064
Neg logit contributions
balls-0.101
MY-0.101
 chip-0.099
Mac-0.097
bled-0.097
Token He
Token ID679
Feature activation-2.19e-02

Pos logit contributions
adow+0.038
 lived+0.033
 night+0.031
arium+0.030
 belong+0.030
Neg logit contributions
balls-0.082
MY-0.081
Mac-0.081
bled-0.080
z-0.079
Token liked
Token ID8288
Feature activation-2.04e-02

Pos logit contributions
adow+0.026
 about+0.024
 night+0.023
 of+0.023
 zone+0.023
Neg logit contributions
Mac-0.042
balls-0.040
z-0.040
Marcus-0.040
MY-0.040
Token to
Token ID284
Feature activation-9.80e-03

Pos logit contributions
adow+0.027
 lived+0.025
 night+0.022
 about+0.022
arium+0.021
Neg logit contributions
balls-0.040
Mac-0.038
MY-0.037
bled-0.037
 chip-0.037
Token necessary
Token ID3306
Feature activation-1.96e-03

Pos logit contributions
adow+0.034
 lived+0.031
 zone+0.029
 night+0.029
arium+0.029
Neg logit contributions
bled-0.039
balls-0.039
MY-0.038
ula-0.037
 chip-0.036
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
adow+0.002
 lived+0.002
 night+0.002
 about+0.002
arium+0.002
Neg logit contributions
balls-0.004
bled-0.004
MY-0.004
z-0.004
ula-0.004
Token<|endoftext|>
Token ID50256
Feature activation-6.72e-03

Pos logit contributions
adow+0.038
 lived+0.034
 adventure+0.034
 belong+0.033
igator+0.033
Neg logit contributions
MY-0.032
balls-0.032
Mac-0.032
Marcus-0.031
 chip-0.031
TokenA
Token ID32
Feature activation-1.66e-02

Pos logit contributions
adow+0.009
 lived+0.009
 about+0.009
 night+0.008
 day+0.008
Neg logit contributions
balls-0.012
bled-0.012
MY-0.012
Mac-0.012
z-0.012
Token 3
Token ID513
Feature activation-2.13e-02

Pos logit contributions
adow+0.017
 lived+0.016
 about+0.015
 night+0.014
 belong+0.013
Neg logit contributions
MY-0.037
balls-0.036
Mac-0.036
z-0.035
ula-0.035
Token year
Token ID614
Feature activation-8.80e-02

Pos logit contributions
adow+0.017
 about+0.015
 lived+0.014
 night+0.014
 belong+0.014
Neg logit contributions
MY-0.048
z-0.048
balls-0.048
bled-0.047
Mac-0.047
Token old
Token ID1468
Feature activation-4.54e-02

Pos logit contributions
adow+0.161
 lived+0.158
 zone+0.155
 belong+0.153
 sorts+0.141
Neg logit contributions
MY-0.108
 chip-0.106
bled-0.102
ula-0.100
balls-0.099
Token girl
Token ID2576
Feature activation-2.76e-02

Pos logit contributions
adow+0.076
 about+0.071
 lived+0.071
 night+0.068
 day+0.067
Neg logit contributions
MY-0.067
bled-0.067
balls-0.067
Mac-0.066
z-0.065
Token named
Token ID3706
Feature activation-4.39e-02

Pos logit contributions
adow+0.031
 about+0.028
 lived+0.027
 night+0.027
 day+0.026
Neg logit contributions
MY-0.054
balls-0.054
bled-0.054
Mac-0.054
z-0.053
Token Ann
Token ID5506
Feature activation-1.57e-02

Pos logit contributions
adow+0.064
 lived+0.063
 about+0.061
 night+0.059
 day+0.058
Neg logit contributions
balls-0.077
bled-0.076
MY-0.076
Mac-0.075
z-0.073
Token was
Token ID373
Feature activation-2.11e-02

Pos logit contributions
adow+0.020
 about+0.019
 lived+0.019
 adventure+0.019
 day+0.019
Neg logit contributions
z-0.027
MY-0.027
Mac-0.026
bled-0.026
Marcus-0.025
Token<|endoftext|>
Token ID50256
Feature activation-5.26e-03

Pos logit contributions
adow+0.036
 adventure+0.032
 belong+0.031
igator+0.030
 about+0.030
Neg logit contributions
MY-0.033
Mac-0.032
 chip-0.032
balls-0.032
bled-0.032
TokenBilly
Token ID49640
Feature activation+2.49e-03

Pos logit contributions
adow+0.007
 lived+0.007
 about+0.007
 night+0.007
 day+0.006
Neg logit contributions
balls-0.009
bled-0.009
MY-0.009
Mac-0.009
z-0.009
Token was
Token ID373
Feature activation-2.15e-02

Pos logit contributions
MY+0.005
Mac+0.005
bled+0.005
balls+0.005
z+0.005
Neg logit contributions
adow-0.003
 about-0.003
 lived-0.003
 night-0.003
 day-0.003
Token a
Token ID257
Feature activation-2.16e-02

Pos logit contributions
adow+0.031
 about+0.030
 lived+0.030
 night+0.029
 day+0.028
Neg logit contributions
MY-0.039
balls-0.039
Mac-0.039
bled-0.038
z-0.037
Token 3
Token ID513
Feature activation-2.15e-02

Pos logit contributions
 day+0.032
 night+0.032
 lived+0.031
adow+0.030
 about+0.029
Neg logit contributions
bled-0.041
balls-0.040
z-0.038
Mac-0.038
ula-0.037
Token year
Token ID614
Feature activation-8.78e-02

Pos logit contributions
adow+0.018
 lived+0.016
 about+0.015
 night+0.015
 belong+0.014
Neg logit contributions
MY-0.050
balls-0.049
z-0.048
bled-0.048
Mac-0.047
Token old
Token ID1468
Feature activation-5.31e-02

Pos logit contributions
 lived+0.172
adow+0.164
 zone+0.156
 belong+0.152
 about+0.145
Neg logit contributions
MY-0.110
 chip-0.103
ula-0.102
balls-0.101
bled-0.096
Token boy
Token ID2933
Feature activation-1.86e-02

Pos logit contributions
adow+0.083
 lived+0.080
 about+0.078
 night+0.075
 day+0.073
Neg logit contributions
balls-0.086
MY-0.086
bled-0.085
Mac-0.083
z-0.081
Token who
Token ID508
Feature activation-3.27e-02

Pos logit contributions
adow+0.022
 belong+0.021
 lived+0.021
 adventure+0.020
arium+0.020
Neg logit contributions
z-0.033
 chip-0.032
MY-0.032
ula-0.032
balls-0.032
Token was
Token ID373
Feature activation-3.02e-02

Pos logit contributions
adow+0.042
 about+0.038
arium+0.037
 night+0.036
 zone+0.036
Neg logit contributions
Mac-0.059
balls-0.058
Marcus-0.058
bled-0.057
MY-0.057
Token very
Token ID845
Feature activation-2.96e-02

Pos logit contributions
adow+0.043
 lived+0.041
 about+0.040
 night+0.039
 day+0.038
Neg logit contributions
balls-0.054
bled-0.054
MY-0.054
Mac-0.053
z-0.052
Token Inside
Token ID14384
Feature activation-2.73e-02

Pos logit contributions
adow+0.010
 lived+0.010
 about+0.010
 night+0.009
 day+0.009
Neg logit contributions
bled-0.017
balls-0.017
MY-0.017
Mac-0.017
z-0.017
Token,
Token ID11
Feature activation+2.68e-03

Pos logit contributions
adow+0.041
 about+0.037
 lived+0.037
 night+0.036
 adventure+0.034
Neg logit contributions
bled-0.046
balls-0.045
MY-0.045
z-0.044
Mac-0.044
Token a
Token ID257
Feature activation-2.79e-02

Pos logit contributions
balls+0.005
bled+0.005
MY+0.005
Mac+0.005
z+0.005
Neg logit contributions
adow-0.004
 lived-0.003
 about-0.003
 night-0.003
 day-0.003
Token little
Token ID1310
Feature activation-4.21e-02

Pos logit contributions
 lived+0.043
 day+0.043
 night+0.042
 of+0.042
 about+0.041
Neg logit contributions
bled-0.049
balls-0.046
Mac-0.045
z-0.045
MY-0.045
Token three
Token ID1115
Feature activation-2.28e-02

Pos logit contributions
adow+0.067
 lived+0.065
 about+0.063
 night+0.062
 day+0.061
Neg logit contributions
balls-0.068
bled-0.068
MY-0.067
Mac-0.067
z-0.064
Token year
Token ID614
Feature activation-8.72e-02

Pos logit contributions
adow+0.024
 lived+0.023
 about+0.022
 night+0.022
 day+0.021
Neg logit contributions
balls-0.048
MY-0.048
bled-0.047
Mac-0.047
z-0.047
Token old
Token ID1468
Feature activation-4.93e-02

Pos logit contributions
adow+0.144
 lived+0.143
 zone+0.131
 night+0.130
 belong+0.129
Neg logit contributions
MY-0.132
balls-0.125
 seventeen-0.124
bled-0.123
 chip-0.122
Token boy
Token ID2933
Feature activation-1.84e-02

Pos logit contributions
adow+0.073
 lived+0.070
 about+0.069
 night+0.067
 day+0.066
Neg logit contributions
balls-0.085
bled-0.084
MY-0.084
Mac-0.083
z-0.081
Token was
Token ID373
Feature activation-3.19e-02

Pos logit contributions
adow+0.024
 about+0.022
 night+0.022
 day+0.022
 lived+0.022
Neg logit contributions
balls-0.034
Mac-0.033
z-0.033
MY-0.033
bled-0.033
Token standing
Token ID5055
Feature activation-5.60e-03

Pos logit contributions
adow+0.040
 lived+0.039
 about+0.039
 night+0.036
 day+0.035
Neg logit contributions
balls-0.063
MY-0.063
Mac-0.063
bled-0.062
z-0.060
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
adow+0.006
 about+0.006
 night+0.005
 of+0.005
 day+0.005
Neg logit contributions
 seventeen-0.013
balls-0.012
MY-0.012
Mac-0.012
 eighteen-0.012
Tokenenny
Token ID11870
Feature activation-1.10e-02

Pos logit contributions
 lived+0.014
adow+0.014
 about+0.014
 night+0.014
 day+0.013
Neg logit contributions
MY-0.010
Mac-0.010
bled-0.010
ula-0.010
z-0.010
Token was
Token ID373
Feature activation-1.55e-02

Pos logit contributions
adow+0.015
 about+0.014
 lived+0.013
 night+0.013
 of+0.013
Neg logit contributions
MY-0.019
Mac-0.019
bled-0.019
balls-0.018
z-0.018
Token a
Token ID257
Feature activation-2.02e-02

Pos logit contributions
adow+0.021
 about+0.021
 lived+0.021
 night+0.020
 day+0.020
Neg logit contributions
MY-0.029
Mac-0.029
balls-0.029
bled-0.028
 seventeen-0.028
Token happy
Token ID3772
Feature activation-3.15e-02

Pos logit contributions
 day+0.030
 night+0.030
 lived+0.028
adow+0.028
 about+0.026
Neg logit contributions
bled-0.039
balls-0.038
z-0.036
 seventeen-0.036
Mac-0.036
Token 3
Token ID513
Feature activation-3.22e-02

Pos logit contributions
adow+0.052
 lived+0.050
 about+0.049
 night+0.046
 day+0.045
Neg logit contributions
MY-0.048
balls-0.048
bled-0.047
Mac-0.046
 chip-0.045
Token year
Token ID614
Feature activation-8.62e-02

Pos logit contributions
adow+0.031
 lived+0.028
 about+0.027
arium+0.027
 belong+0.026
Neg logit contributions
MY-0.067
balls-0.066
z-0.066
 chip-0.065
ula-0.064
Token old
Token ID1468
Feature activation-5.44e-02

Pos logit contributions
 lived+0.163
adow+0.159
 zone+0.147
 belong+0.146
 sorts+0.141
Neg logit contributions
MY-0.112
 chip-0.108
balls-0.108
ula-0.106
z-0.097
Token who
Token ID508
Feature activation-3.34e-02

Pos logit contributions
adow+0.096
 about+0.089
 lived+0.088
 night+0.084
 belong+0.084
Neg logit contributions
balls-0.076
MY-0.076
 chip-0.075
bled-0.074
 wrists-0.072
Token loved
Token ID6151
Feature activation-2.53e-02

Pos logit contributions
adow+0.040
 about+0.036
arium+0.035
 night+0.035
 adventure+0.034
Neg logit contributions
Mac-0.063
balls-0.063
bled-0.061
Marcus-0.061
z-0.061
Token to
Token ID284
Feature activation-6.75e-03

Pos logit contributions
adow+0.040
 lived+0.035
 zone+0.033
arium+0.033
 belong+0.031
Neg logit contributions
balls-0.045
 chip-0.043
 wrists-0.042
Mac-0.040
z-0.040
Token explore
Token ID7301
Feature activation-3.05e-02

Pos logit contributions
adow+0.009
 about+0.009
 lived+0.009
 night+0.008
arium+0.008
Neg logit contributions
Mac-0.012
balls-0.012
MY-0.011
bled-0.011
z-0.011
Token was
Token ID373
Feature activation-1.24e-02

Pos logit contributions
adow+0.014
 lived+0.013
 about+0.013
 night+0.013
 day+0.012
Neg logit contributions
balls-0.021
bled-0.021
MY-0.021
Mac-0.021
z-0.020
Token a
Token ID257
Feature activation-1.51e-02

Pos logit contributions
adow+0.016
 about+0.015
 lived+0.015
 night+0.015
 day+0.014
Neg logit contributions
MY-0.024
balls-0.024
Mac-0.024
bled-0.024
 seventeen-0.023
Token very
Token ID845
Feature activation-1.65e-02

Pos logit contributions
 day+0.023
 night+0.022
 lived+0.021
adow+0.020
 of+0.019
Neg logit contributions
bled-0.030
balls-0.029
z-0.027
 seventeen-0.027
Mac-0.027
Token curious
Token ID11040
Feature activation-3.55e-02

Pos logit contributions
adow+0.026
 lived+0.026
 day+0.025
 night+0.025
 about+0.025
Neg logit contributions
bled-0.027
balls-0.027
Mac-0.026
MY-0.026
z-0.026
Token three
Token ID1115
Feature activation-4.03e-02

Pos logit contributions
adow+0.066
 lived+0.065
 about+0.061
 belong+0.060
 night+0.058
Neg logit contributions
MY-0.046
 chip-0.044
Mac-0.043
balls-0.042
ula-0.042
Token year
Token ID614
Feature activation-8.59e-02

Pos logit contributions
adow+0.048
 night+0.044
 lived+0.044
 belong+0.043
 about+0.041
Neg logit contributions
MY-0.077
balls-0.076
z-0.074
 chip-0.073
ula-0.073
Token old
Token ID1468
Feature activation-5.90e-02

Pos logit contributions
 lived+0.150
adow+0.146
 belong+0.136
 zone+0.134
 night+0.131
Neg logit contributions
MY-0.124
ula-0.118
balls-0.117
 chip-0.116
bled-0.111
Token.
Token ID13
Feature activation-3.21e-02

Pos logit contributions
adow+0.079
 lived+0.071
 belong+0.069
 about+0.068
 night+0.068
Neg logit contributions
MY-0.108
balls-0.108
 chip-0.106
Mac-0.105
 wrists-0.104
Token She
Token ID1375
Feature activation-2.38e-02

Pos logit contributions
adow+0.032
 lived+0.029
 night+0.027
 about+0.026
 adventure+0.026
Neg logit contributions
balls-0.070
Mac-0.069
MY-0.069
bled-0.069
ula-0.068
Token wanted
Token ID2227
Feature activation-1.29e-03

Pos logit contributions
adow+0.028
 about+0.025
 night+0.025
 day+0.024
 lived+0.024
Neg logit contributions
Mac-0.046
balls-0.046
bled-0.046
MY-0.046
z-0.045
Token to
Token ID284
Feature activation-1.57e-02

Pos logit contributions
adow+0.002
 lived+0.001
 about+0.001
 night+0.001
 day+0.001
Neg logit contributions
balls-0.003
Mac-0.003
bled-0.003
MY-0.002
ula-0.002
Token was
Token ID373
Feature activation-1.36e-02

Pos logit contributions
MY+0.018
balls+0.018
bled+0.018
Mac+0.018
z+0.017
Neg logit contributions
adow-0.011
 lived-0.010
 about-0.010
 night-0.010
 day-0.010
Token a
Token ID257
Feature activation-1.72e-02

Pos logit contributions
adow+0.018
 about+0.018
 lived+0.018
 night+0.017
 day+0.017
Neg logit contributions
MY-0.026
balls-0.026
Mac-0.026
bled-0.025
 seventeen-0.025
Token ch
Token ID442
Feature activation-4.71e-02

Pos logit contributions
 day+0.026
 night+0.026
 lived+0.025
adow+0.024
 about+0.023
Neg logit contributions
bled-0.032
balls-0.032
z-0.030
Mac-0.030
 seventeen-0.030
Tokenubby
Token ID38393
Feature activation-4.08e-02

Pos logit contributions
adow+0.079
 lived+0.077
 about+0.075
 night+0.073
 day+0.072
Neg logit contributions
balls-0.072
bled-0.072
MY-0.072
Mac-0.071
z-0.068
Token three
Token ID1115
Feature activation-3.55e-02

Pos logit contributions
adow+0.064
 lived+0.063
 about+0.061
 night+0.060
 day+0.059
Neg logit contributions
balls-0.066
bled-0.066
MY-0.065
Mac-0.065
z-0.063
Token year
Token ID614
Feature activation-8.58e-02

Pos logit contributions
adow+0.036
 lived+0.033
 night+0.032
 about+0.032
 belong+0.030
Neg logit contributions
MY-0.075
balls-0.074
z-0.073
Mac-0.072
 chip-0.072
Token old
Token ID1468
Feature activation-5.50e-02

Pos logit contributions
 lived+0.151
adow+0.148
 belong+0.137
 zone+0.135
 night+0.131
Neg logit contributions
MY-0.123
balls-0.117
ula-0.115
 chip-0.115
z-0.112
Token who
Token ID508
Feature activation-3.12e-02

Pos logit contributions
adow+0.072
 lived+0.067
 about+0.064
 night+0.063
 belong+0.062
Neg logit contributions
balls-0.103
MY-0.101
Mac-0.099
bled-0.099
 chip-0.099
Token loved
Token ID6151
Feature activation-2.43e-02

Pos logit contributions
adow+0.039
 about+0.035
arium+0.034
 night+0.034
 adventure+0.033
Neg logit contributions
Mac-0.059
balls-0.059
bled-0.057
z-0.057
Marcus-0.057
Token cocoa
Token ID35845
Feature activation-2.43e-02

Pos logit contributions
adow+0.036
 lived+0.032
arium+0.030
 belong+0.029
 zone+0.029
Neg logit contributions
balls-0.045
 chip-0.042
 wrists-0.041
Mac-0.041
z-0.041
Token.
Token ID13
Feature activation-2.26e-02

Pos logit contributions
adow+0.026
 lived+0.024
arium+0.021
 night+0.021
 about+0.020
Neg logit contributions
balls-0.054
MY-0.051
 chip-0.051
ula-0.050
bled-0.050
TokenSam
Token ID16305
Feature activation+2.05e-03

Pos logit contributions
adow+0.003
 lived+0.003
 about+0.003
 night+0.003
 adventure+0.003
Neg logit contributions
balls-0.004
Mac-0.004
bled-0.004
MY-0.004
z-0.003
Token was
Token ID373
Feature activation-9.62e-03

Pos logit contributions
MY+0.004
bled+0.004
Mac+0.004
balls+0.004
z+0.004
Neg logit contributions
adow-0.002
 lived-0.002
 about-0.002
 night-0.002
 day-0.002
Token a
Token ID257
Feature activation-8.96e-03

Pos logit contributions
 about+0.013
adow+0.013
 lived+0.013
 night+0.013
 day+0.012
Neg logit contributions
MY-0.018
Mac-0.018
balls-0.018
bled-0.018
 seventeen-0.017
Token curious
Token ID11040
Feature activation-2.45e-02

Pos logit contributions
 night+0.013
 day+0.013
 lived+0.013
adow+0.013
 about+0.012
Neg logit contributions
bled-0.017
balls-0.017
z-0.016
Mac-0.016
ula-0.016
Token 3
Token ID513
Feature activation-2.60e-02

Pos logit contributions
adow+0.046
 lived+0.045
 about+0.042
 belong+0.042
arium+0.041
Neg logit contributions
MY-0.030
 chip-0.029
Mac-0.028
balls-0.027
ula-0.027
Token year
Token ID614
Feature activation-8.58e-02

Pos logit contributions
adow+0.023
 belong+0.021
 lived+0.021
 night+0.021
arium+0.020
Neg logit contributions
MY-0.056
z-0.055
balls-0.054
 chip-0.053
bled-0.053
Token old
Token ID1468
Feature activation-5.31e-02

Pos logit contributions
 lived+0.156
adow+0.153
 belong+0.145
 zone+0.144
 sorts+0.136
Neg logit contributions
MY-0.112
 chip-0.106
balls-0.106
ula-0.104
z-0.100
Token.
Token ID13
Feature activation-3.32e-02

Pos logit contributions
adow+0.080
 lived+0.072
 about+0.072
 belong+0.070
 night+0.069
Neg logit contributions
MY-0.088
balls-0.087
 chip-0.086
bled-0.085
Mac-0.084
Token One
Token ID1881
Feature activation-3.85e-02

Pos logit contributions
adow+0.041
 lived+0.037
 night+0.035
 belong+0.035
 privacy+0.034
Neg logit contributions
Mac-0.061
 seventeen-0.061
balls-0.059
 eighteen-0.059
 chip-0.058
Token day
Token ID1110
Feature activation+3.13e-02

Pos logit contributions
arium+0.032
 privacy+0.030
 ago+0.029
 zone+0.027
adow+0.026
Neg logit contributions
 chip-0.077
z-0.072
Mac-0.071
Marcus-0.070
Danny-0.069
Token,
Token ID11
Feature activation+1.57e-02

Pos logit contributions
bled+0.061
balls+0.061
Mac+0.058
MY+0.058
ula+0.057
Neg logit contributions
adow-0.041
 lived-0.036
 about-0.035
 night-0.034
arium-0.034
Tokenie
Token ID494
Feature activation+7.33e-05

Pos logit contributions
adow+0.003
 about+0.003
 lived+0.003
 night+0.003
 adventure+0.002
Neg logit contributions
bled-0.014
z-0.013
balls-0.013
MY-0.013
Mac-0.013
Token was
Token ID373
Feature activation-1.34e-02

Pos logit contributions
balls+0.000
bled+0.000
MY+0.000
Mac+0.000
z+0.000
Neg logit contributions
adow-0.000
 lived-0.000
 about-0.000
 night-0.000
 day-0.000
Token a
Token ID257
Feature activation-1.31e-02

Pos logit contributions
 about+0.017
adow+0.016
 lived+0.016
 day+0.015
 night+0.015
Neg logit contributions
MY-0.028
Mac-0.028
balls-0.027
 seventeen-0.027
bled-0.027
Token curious
Token ID11040
Feature activation-2.76e-02

Pos logit contributions
 day+0.019
 night+0.019
 lived+0.018
adow+0.017
 adventure+0.016
Neg logit contributions
bled-0.027
balls-0.026
z-0.024
 seventeen-0.024
Mac-0.024
Token three
Token ID1115
Feature activation-3.39e-02

Pos logit contributions
adow+0.051
 lived+0.050
 about+0.047
 belong+0.046
 night+0.045
Neg logit contributions
MY-0.036
 chip-0.034
Mac-0.033
balls-0.033
ula-0.032
Token year
Token ID614
Feature activation-8.49e-02

Pos logit contributions
adow+0.034
 night+0.031
 lived+0.031
 belong+0.030
 about+0.030
Neg logit contributions
MY-0.070
balls-0.068
z-0.068
 chip-0.067
ula-0.066
Token old
Token ID1468
Feature activation-5.44e-02

Pos logit contributions
 lived+0.152
adow+0.147
 belong+0.139
 zone+0.138
 night+0.133
Neg logit contributions
MY-0.118
ula-0.110
balls-0.110
 chip-0.110
z-0.106
Token.
Token ID13
Feature activation-3.52e-02

Pos logit contributions
adow+0.075
 lived+0.068
 about+0.067
 belong+0.066
 night+0.065
Neg logit contributions
MY-0.095
balls-0.095
 chip-0.094
Mac-0.093
 wrists-0.092
Token One
Token ID1881
Feature activation-3.85e-02

Pos logit contributions
adow+0.037
 lived+0.034
 belong+0.033
 night+0.032
arium+0.032
Neg logit contributions
Mac-0.071
balls-0.069
MY-0.068
ula-0.068
Er-0.067
Token day
Token ID1110
Feature activation+3.45e-02

Pos logit contributions
arium+0.032
 privacy+0.030
 ago+0.030
adow+0.028
 zone+0.027
Neg logit contributions
 chip-0.078
z-0.073
Mac-0.071
Marcus-0.069
M-0.069
Token,
Token ID11
Feature activation+1.53e-02

Pos logit contributions
balls+0.071
bled+0.071
MY+0.070
Mac+0.070
z+0.068
Neg logit contributions
adow-0.039
 lived-0.037
 about-0.036
 night-0.035
 day-0.034
Token<|endoftext|>
Token ID50256
Feature activation-8.49e-03

Pos logit contributions
adow+0.029
 night+0.027
 adventure+0.027
 lived+0.026
 zone+0.026
Neg logit contributions
Mac-0.030
balls-0.030
MY-0.029
 chip-0.029
 eighteen-0.028
TokenJohn
Token ID7554
Feature activation-3.22e-03

Pos logit contributions
adow+0.013
 lived+0.012
 about+0.012
 night+0.012
 adventure+0.011
Neg logit contributions
balls-0.014
bled-0.014
Mac-0.014
MY-0.014
z-0.014
Token was
Token ID373
Feature activation-1.52e-02

Pos logit contributions
adow+0.004
 lived+0.004
 about+0.004
 night+0.004
 day+0.004
Neg logit contributions
balls-0.006
bled-0.006
MY-0.006
Mac-0.006
z-0.006
Token a
Token ID257
Feature activation-1.50e-02

Pos logit contributions
 about+0.019
adow+0.018
 night+0.017
 day+0.017
 lived+0.017
Neg logit contributions
MY-0.032
balls-0.032
Mac-0.031
bled-0.031
 seventeen-0.030
Token 3
Token ID513
Feature activation-2.29e-02

Pos logit contributions
 day+0.023
 night+0.023
 lived+0.021
adow+0.021
 about+0.020
Neg logit contributions
bled-0.029
balls-0.028
ula-0.026
z-0.026
Mac-0.026
Token year
Token ID614
Feature activation-8.49e-02

Pos logit contributions
adow+0.017
 lived+0.015
 night+0.015
 about+0.014
 belong+0.014
Neg logit contributions
MY-0.054
z-0.053
balls-0.053
bled-0.052
Mac-0.052
Token old
Token ID1468
Feature activation-5.10e-02

Pos logit contributions
 lived+0.162
adow+0.156
 zone+0.149
 belong+0.147
 night+0.137
Neg logit contributions
MY-0.106
balls-0.100
 chip-0.099
ula-0.099
z-0.097
Token boy
Token ID2933
Feature activation-1.57e-02

Pos logit contributions
adow+0.068
 lived+0.065
 about+0.063
 night+0.061
 day+0.060
Neg logit contributions
balls-0.094
MY-0.094
bled-0.093
Mac-0.092
z-0.090
Token with
Token ID351
Feature activation-8.58e-03

Pos logit contributions
adow+0.018
 belong+0.018
 lived+0.017
 night+0.017
arium+0.016
Neg logit contributions
z-0.028
balls-0.028
 chip-0.028
MY-0.028
ula-0.028
Token a
Token ID257
Feature activation+7.36e-03

Pos logit contributions
adow+0.014
 lived+0.014
 about+0.014
 night+0.013
 day+0.013
Neg logit contributions
balls-0.013
bled-0.013
MY-0.013
Mac-0.013
z-0.013
Token big
Token ID1263
Feature activation+6.71e-04

Pos logit contributions
bled+0.013
balls+0.012
z+0.012
MY+0.012
ula+0.012
Neg logit contributions
 day-0.012
 night-0.012
 lived-0.011
adow-0.011
 adventure-0.011
Token was
Token ID373
Feature activation-1.82e-02

Pos logit contributions
MY+0.020
Mac+0.020
balls+0.020
bled+0.020
z+0.020
Neg logit contributions
adow-0.015
 about-0.014
 lived-0.014
 night-0.013
 adventure-0.013
Token a
Token ID257
Feature activation-1.66e-02

Pos logit contributions
adow+0.026
 about+0.025
 lived+0.025
 night+0.024
 day+0.024
Neg logit contributions
MY-0.033
balls-0.033
Mac-0.033
bled-0.032
 seventeen-0.031
Token very
Token ID845
Feature activation-2.28e-02

Pos logit contributions
 day+0.025
 night+0.025
adow+0.024
 lived+0.024
 about+0.023
Neg logit contributions
bled-0.031
balls-0.030
Mac-0.028
z-0.028
 seventeen-0.028
Token polite
Token ID23507
Feature activation-3.90e-02

Pos logit contributions
adow+0.038
 lived+0.037
 about+0.036
 night+0.035
 day+0.035
Neg logit contributions
balls-0.035
bled-0.035
MY-0.035
Mac-0.034
z-0.033
Token three
Token ID1115
Feature activation-3.78e-02

Pos logit contributions
adow+0.066
 lived+0.064
 about+0.061
 night+0.059
 belong+0.058
Neg logit contributions
MY-0.058
balls-0.057
Mac-0.055
bled-0.055
 chip-0.054
Token year
Token ID614
Feature activation-8.49e-02

Pos logit contributions
adow+0.035
 lived+0.032
 belong+0.031
 night+0.030
arium+0.030
Neg logit contributions
MY-0.080
balls-0.080
 chip-0.078
z-0.078
ula-0.076
Token old
Token ID1468
Feature activation-5.59e-02

Pos logit contributions
 lived+0.149
adow+0.147
 belong+0.137
 zone+0.135
 sorts+0.129
Neg logit contributions
MY-0.119
balls-0.116
 chip-0.114
ula-0.112
z-0.107
Token.
Token ID13
Feature activation-3.66e-02

Pos logit contributions
adow+0.081
 belong+0.073
 lived+0.073
 about+0.071
arium+0.069
Neg logit contributions
balls-0.096
 chip-0.095
MY-0.093
 wrists-0.091
Mac-0.089
Token He
Token ID679
Feature activation-2.01e-02

Pos logit contributions
adow+0.042
 lived+0.035
 belong+0.034
 zone+0.032
 adventure+0.032
Neg logit contributions
Mac-0.073
MY-0.072
balls-0.072
Marcus-0.072
 seventeen-0.071
Token always
Token ID1464
Feature activation-2.93e-02

Pos logit contributions
adow+0.024
 about+0.021
 zone+0.021
 night+0.021
arium+0.020
Neg logit contributions
Mac-0.038
balls-0.038
bled-0.037
z-0.037
Marcus-0.037
Token said
Token ID531
Feature activation-5.41e-03

Pos logit contributions
adow+0.036
 about+0.034
 of+0.033
arium+0.033
 adventure+0.031
Neg logit contributions
Mac-0.053
bled-0.052
balls-0.052
z-0.052
Marcus-0.051
Token man
Token ID582
Feature activation-1.01e-02

Pos logit contributions
adow+0.072
 lived+0.069
 about+0.068
 night+0.067
 day+0.065
Neg logit contributions
balls-0.051
bled-0.050
MY-0.050
Mac-0.050
z-0.048
Token asked
Token ID1965
Feature activation-2.61e-02

Pos logit contributions
adow+0.015
 about+0.014
 night+0.014
 lived+0.013
 day+0.013
Neg logit contributions
bled-0.017
balls-0.017
Mac-0.017
z-0.017
MY-0.016
Token a
Token ID257
Feature activation-2.93e-02

Pos logit contributions
adow+0.029
 lived+0.027
 about+0.026
 night+0.026
 day+0.025
Neg logit contributions
balls-0.055
bled-0.055
MY-0.054
Mac-0.054
z-0.053
Token little
Token ID1310
Feature activation-4.05e-02

Pos logit contributions
adow+0.043
 lived+0.042
 about+0.041
 night+0.040
 day+0.039
Neg logit contributions
bled-0.052
balls-0.051
MY-0.051
Mac-0.050
z-0.049
Token 3
Token ID513
Feature activation-2.89e-02

Pos logit contributions
adow+0.070
 lived+0.069
 about+0.066
 night+0.064
 day+0.062
Neg logit contributions
balls-0.059
MY-0.058
Mac-0.058
 chip-0.056
bled-0.056
Token year
Token ID614
Feature activation-8.49e-02

Pos logit contributions
adow+0.048
 lived+0.047
 night+0.046
 zone+0.045
 belong+0.044
Neg logit contributions
MY-0.041
balls-0.040
 chip-0.039
z-0.039
Mac-0.038
Token old
Token ID1468
Feature activation-5.74e-02

Pos logit contributions
 lived+0.161
adow+0.155
 belong+0.148
 zone+0.145
 sorts+0.142
Neg logit contributions
MY-0.107
 chip-0.103
balls-0.100
 seventeen-0.099
ula-0.096
Token boy
Token ID2933
Feature activation-1.93e-02

Pos logit contributions
adow+0.092
 lived+0.086
 night+0.084
 about+0.082
 day+0.082
Neg logit contributions
Mac-0.089
balls-0.088
MY-0.086
 chip-0.085
bled-0.085
Token who
Token ID508
Feature activation-3.39e-02

Pos logit contributions
adow+0.024
 night+0.023
 lived+0.023
 day+0.022
 adventure+0.021
Neg logit contributions
balls-0.036
Mac-0.035
z-0.034
bled-0.034
MY-0.034
Token was
Token ID373
Feature activation-3.33e-02

Pos logit contributions
adow+0.053
 zone+0.047
 about+0.046
arium+0.045
 night+0.045
Neg logit contributions
Mac-0.055
bled-0.052
Marcus-0.052
z-0.051
balls-0.051
Token playing
Token ID2712
Feature activation+2.36e-02

Pos logit contributions
adow+0.047
 about+0.045
 lived+0.045
 night+0.043
 day+0.042
Neg logit contributions
balls-0.061
bled-0.061
MY-0.061
Mac-0.060
 seventeen-0.059
Token day
Token ID1110
Feature activation+4.55e-02

Pos logit contributions
 ago+0.029
 zone+0.028
adow+0.027
 habitats+0.026
 privacy+0.025
Neg logit contributions
 chip-0.076
Mac-0.068
z-0.064
 smaller-0.064
balls-0.064
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
balls+0.091
bled+0.090
MY+0.090
Mac+0.089
z+0.087
Neg logit contributions
adow-0.055
 lived-0.051
 about-0.050
 night-0.048
 day-0.047
Token a
Token ID257
Feature activation-2.32e-02

Pos logit contributions
balls+0.015
bled+0.015
Mac+0.014
 chip+0.013
MY+0.013
Neg logit contributions
adow-0.022
 about-0.020
 lived-0.020
arium-0.019
 night-0.019
Token little
Token ID1310
Feature activation-3.63e-02

Pos logit contributions
 lived+0.034
 day+0.034
 night+0.033
adow+0.033
 about+0.032
Neg logit contributions
bled-0.042
balls-0.040
MY-0.040
z-0.040
Mac-0.039
Token 3
Token ID513
Feature activation-1.64e-02

Pos logit contributions
adow+0.062
 lived+0.059
 about+0.058
 night+0.056
 day+0.054
Neg logit contributions
balls-0.054
MY-0.054
Mac-0.053
bled-0.053
z-0.051
Token year
Token ID614
Feature activation-8.46e-02

Pos logit contributions
adow+0.021
 night+0.019
 about+0.019
 lived+0.019
arium+0.018
Neg logit contributions
MY-0.030
z-0.030
balls-0.030
Mac-0.029
bled-0.029
Token old
Token ID1468
Feature activation-4.69e-02

Pos logit contributions
adow+0.157
 lived+0.157
 zone+0.149
 belong+0.142
 sorts+0.141
Neg logit contributions
MY-0.106
 chip-0.103
balls-0.101
bled-0.098
 seventeen-0.097
Token girl
Token ID2576
Feature activation-2.17e-02

Pos logit contributions
adow+0.083
 about+0.076
 night+0.073
 lived+0.073
 day+0.071
Neg logit contributions
MY-0.066
Mac-0.065
balls-0.065
 chip-0.064
bled-0.064
Token decided
Token ID3066
Feature activation-2.90e-02

Pos logit contributions
adow+0.021
 about+0.019
 night+0.018
 lived+0.017
 day+0.017
Neg logit contributions
MY-0.047
balls-0.047
z-0.047
Mac-0.047
bled-0.047
Token to
Token ID284
Feature activation-1.66e-02

Pos logit contributions
adow+0.043
 lived+0.038
 sorts+0.037
 night+0.036
 zone+0.035
Neg logit contributions
balls-0.050
MY-0.048
bled-0.048
z-0.047
Mac-0.047
Token play
Token ID711
Feature activation+1.61e-02

Pos logit contributions
adow+0.028
 about+0.026
arium+0.026
 lately+0.026
 lived+0.025
Neg logit contributions
Mac-0.023
 swirl-0.021
Marcus-0.021
balls-0.021
 chip-0.021
TokenJohnny
Token ID44960
Feature activation+5.63e-03

Pos logit contributions
adow+0.011
 lived+0.010
 about+0.010
 adventure+0.010
 night+0.010
Neg logit contributions
balls-0.011
Mac-0.011
bled-0.011
MY-0.011
z-0.011
Token was
Token ID373
Feature activation-1.40e-02

Pos logit contributions
MY+0.011
bled+0.011
balls+0.011
Mac+0.011
z+0.010
Neg logit contributions
adow-0.007
 lived-0.007
 about-0.007
 night-0.006
 day-0.006
Token a
Token ID257
Feature activation-1.57e-02

Pos logit contributions
adow+0.018
 about+0.018
 lived+0.017
 night+0.017
 day+0.017
Neg logit contributions
MY-0.027
balls-0.027
Mac-0.027
bled-0.027
 seventeen-0.026
Token smart
Token ID4451
Feature activation-2.40e-02

Pos logit contributions
 day+0.024
 night+0.024
 lived+0.023
adow+0.022
 about+0.021
Neg logit contributions
bled-0.029
balls-0.028
Mac-0.027
z-0.027
MY-0.026
Token 3
Token ID513
Feature activation-3.11e-02

Pos logit contributions
adow+0.037
 lived+0.036
 about+0.036
 night+0.035
 day+0.035
Neg logit contributions
bled-0.041
balls-0.041
Mac-0.040
MY-0.039
z-0.039
Token year
Token ID614
Feature activation-8.45e-02

Pos logit contributions
adow+0.031
 lived+0.028
 belong+0.027
arium+0.027
 night+0.027
Neg logit contributions
MY-0.065
balls-0.063
z-0.063
 chip-0.062
bled-0.061
Token old
Token ID1468
Feature activation-5.29e-02

Pos logit contributions
 lived+0.158
adow+0.153
 belong+0.144
 zone+0.143
 night+0.136
Neg logit contributions
MY-0.110
balls-0.104
 chip-0.104
ula-0.102
z-0.097
Token.
Token ID13
Feature activation-3.25e-02

Pos logit contributions
adow+0.083
 lived+0.076
 about+0.075
 night+0.073
 belong+0.072
Neg logit contributions
balls-0.085
MY-0.085
bled-0.083
 chip-0.082
Mac-0.082
Token He
Token ID679
Feature activation-1.76e-02

Pos logit contributions
adow+0.044
 lived+0.036
arium+0.036
igator+0.036
 privacy+0.035
Neg logit contributions
ula-0.056
Er-0.056
Marcus-0.056
MY-0.056
 seventeen-0.055
Token liked
Token ID8288
Feature activation-1.80e-02

Pos logit contributions
adow+0.021
 about+0.019
 night+0.019
 zone+0.018
arium+0.018
Neg logit contributions
Mac-0.033
balls-0.033
bled-0.032
MY-0.032
z-0.032
Token to
Token ID284
Feature activation-1.06e-02

Pos logit contributions
adow+0.023
 lived+0.021
 about+0.019
 night+0.019
arium+0.019
Neg logit contributions
balls-0.035
Mac-0.034
bled-0.034
MY-0.034
 chip-0.033
Token in
Token ID287
Feature activation-6.13e-03

Pos logit contributions
balls+0.035
z+0.034
bled+0.034
MY+0.033
Mac+0.033
Neg logit contributions
 lived-0.041
adow-0.040
igator-0.036
 about-0.036
 zone-0.036
Token.
Token ID13
Feature activation-8.96e-03

Pos logit contributions
adow+0.008
 lived+0.008
igator+0.008
 belong+0.007
 about+0.007
Neg logit contributions
z-0.010
MY-0.010
Mac-0.010
balls-0.010
ula-0.010
Token
Token ID198
Feature activation+2.11e-04

Pos logit contributions
adow+0.014
 night+0.012
 adventure+0.012
 belong+0.012
 lived+0.012
Neg logit contributions
balls-0.014
Mac-0.014
 eighteen-0.013
 wrists-0.013
MY-0.013
Token
Token ID198
Feature activation+4.46e-03

Pos logit contributions
balls+0.000
Mac+0.000
MY+0.000
bled+0.000
z+0.000
Neg logit contributions
adow-0.000
 lived-0.000
 about-0.000
 night-0.000
 day-0.000
TokenOne
Token ID3198
Feature activation-2.87e-02

Pos logit contributions
Mac+0.008
MY+0.008
balls+0.008
bled+0.008
z+0.007
Neg logit contributions
adow-0.007
 lived-0.006
 about-0.006
 night-0.006
 day-0.006
Token day
Token ID1110
Feature activation+4.47e-02

Pos logit contributions
 zone+0.022
adow+0.021
 privacy+0.021
 lately+0.021
 ago+0.020
Neg logit contributions
 chip-0.060
 Mil-0.056
Mac-0.055
z-0.055
Pop-0.055
Token,
Token ID11
Feature activation+2.37e-02

Pos logit contributions
balls+0.085
bled+0.084
MY+0.083
Mac+0.082
z+0.080
Neg logit contributions
adow-0.060
 lived-0.053
 about-0.053
 night-0.051
 adventure-0.050
Token a
Token ID257
Feature activation-1.75e-02

Pos logit contributions
balls+0.035
bled+0.035
MY+0.034
Mac+0.034
z+0.033
Neg logit contributions
adow-0.042
 lived-0.039
 about-0.039
 night-0.038
 day-0.037
Token little
Token ID1310
Feature activation-3.02e-02

Pos logit contributions
 day+0.024
 lived+0.024
 night+0.024
adow+0.023
 about+0.022
Neg logit contributions
bled-0.033
balls-0.032
z-0.032
Mac-0.031
MY-0.031
Token boy
Token ID2933
Feature activation-2.31e-03

Pos logit contributions
adow+0.053
 lived+0.052
 about+0.051
 night+0.048
 adventure+0.046
Neg logit contributions
balls-0.043
MY-0.043
Mac-0.041
bled-0.041
 chip-0.041
Token with
Token ID351
Feature activation-4.46e-03

Pos logit contributions
adow+0.003
 about+0.003
 privacy+0.002
 lately+0.002
 adventure+0.002
Neg logit contributions
z-0.004
balls-0.004
Mac-0.004
MY-0.004
bled-0.004
Token says
Token ID1139
Feature activation+1.49e-02

Pos logit contributions
balls+0.049
Mac+0.046
ula+0.045
 chip+0.045
bled+0.044
Neg logit contributions
adow-0.061
 zone-0.053
 lived-0.050
 night-0.050
arium-0.049
Token Tim
Token ID5045
Feature activation+3.09e-02

Pos logit contributions
balls+0.026
bled+0.026
MY+0.026
Mac+0.025
ula+0.025
Neg logit contributions
adow-0.022
 lived-0.021
 about-0.020
 night-0.020
 day-0.019
Token.
Token ID13
Feature activation+5.68e-03

Pos logit contributions
bled+0.077
balls+0.077
MY+0.077
Mac+0.076
z+0.074
Neg logit contributions
adow-0.023
 lived-0.020
 about-0.020
 night-0.019
 day-0.018
Token
Token ID198
Feature activation+2.80e-03

Pos logit contributions
bled+0.012
MY+0.012
z+0.012
aults+0.012
 eighteen+0.012
Neg logit contributions
 about-0.006
 lived-0.006
 of-0.006
 day-0.005
adow-0.005
Token
Token ID198
Feature activation+2.42e-03

Pos logit contributions
bled+0.006
MY+0.006
balls+0.006
 seventeen+0.006
 eighteen+0.006
Neg logit contributions
 lived-0.003
adow-0.003
 about-0.003
 of-0.003
 day-0.003
Token"
Token ID1
Feature activation+4.52e-02

Pos logit contributions
bled+0.004
MY+0.004
balls+0.004
 wrists+0.004
 eighteen+0.004
Neg logit contributions
 lived-0.004
adow-0.004
 of-0.004
 about-0.004
 day-0.004
TokenYeah
Token ID10995
Feature activation-1.77e-02

Pos logit contributions
MY+0.076
bled+0.073
bling+0.068
balls+0.067
 wrists+0.066
Neg logit contributions
 lived-0.067
 day-0.066
 of-0.062
 today-0.059
 night-0.058
Token,
Token ID11
Feature activation+3.85e-02

Pos logit contributions
 of+0.014
 about+0.013
 lived+0.013
 today+0.013
 night+0.012
Neg logit contributions
Mac-0.045
bled-0.044
balls-0.043
Marcus-0.043
 seventeen-0.043
Token let
Token ID1309
Feature activation+1.20e-02

Pos logit contributions
bled+0.074
MY+0.074
Mac+0.074
balls+0.073
z+0.072
Neg logit contributions
 lived-0.049
 about-0.048
adow-0.048
 night-0.045
 of-0.045
Token's
Token ID338
Feature activation-2.41e-02

Pos logit contributions
bled+0.027
balls+0.027
Mac+0.027
 seventeen+0.027
MY+0.026
Neg logit contributions
 night-0.012
 lived-0.012
 about-0.012
 day-0.012
adow-0.011
Token make
Token ID787
Feature activation+1.64e-02

Pos logit contributions
adow+0.029
 lived+0.029
 about+0.028
 night+0.028
 day+0.027
Neg logit contributions
balls-0.049
MY-0.048
bled-0.048
Mac-0.048
z-0.048
Token pur
Token ID1308
Feature activation-1.23e-03

Pos logit contributions
bled+0.007
MY+0.007
ula+0.007
Mac+0.007
balls+0.007
Neg logit contributions
 lived-0.005
adow-0.004
 about-0.004
 night-0.004
 day-0.004
Tokenred
Token ID445
Feature activation-5.40e-03

Pos logit contributions
adow+0.001
 lived+0.001
 about+0.001
 night+0.001
 day+0.001
Neg logit contributions
balls-0.002
MY-0.002
Mac-0.002
bled-0.002
Marcus-0.002
Token happily
Token ID18177
Feature activation-1.25e-02

Pos logit contributions
 about+0.006
 lived+0.006
 of+0.006
adow+0.006
 night+0.005
Neg logit contributions
Mac-0.012
Marcus-0.011
MY-0.011
bled-0.011
 extract-0.011
Token and
Token ID290
Feature activation-1.62e-02

Pos logit contributions
 lived+0.015
adow+0.014
 about+0.013
 night+0.013
arium+0.013
Neg logit contributions
balls-0.025
MY-0.024
z-0.024
bled-0.024
 eighteen-0.023
Token gave
Token ID2921
Feature activation-1.12e-02

Pos logit contributions
adow+0.024
 lived+0.023
 about+0.023
 night+0.022
 day+0.022
Neg logit contributions
balls-0.028
bled-0.028
MY-0.028
Mac-0.027
z-0.027
Token Bob
Token ID5811
Feature activation+6.11e-02

Pos logit contributions
adow+0.011
 lived+0.011
 about+0.011
 night+0.011
 day+0.010
Neg logit contributions
MY-0.025
balls-0.024
bled-0.024
Mac-0.024
ula-0.024
Token a
Token ID257
Feature activation+4.87e-02

Pos logit contributions
bled+0.107
MY+0.106
balls+0.105
Mac+0.103
 seventeen+0.102
Neg logit contributions
adow-0.092
 about-0.088
 lived-0.087
 night-0.086
 day-0.084
Token big
Token ID1263
Feature activation+3.66e-02

Pos logit contributions
bled+0.075
balls+0.072
MY+0.071
Mac+0.070
z+0.068
Neg logit contributions
adow-0.085
 lived-0.082
 night-0.081
 about-0.081
 day-0.080
Token kitten
Token ID42143
Feature activation+5.25e-03

Pos logit contributions
balls+0.064
bled+0.064
MY+0.063
Mac+0.062
z+0.060
Neg logit contributions
adow-0.054
 lived-0.052
 about-0.051
 night-0.050
 day-0.049
Token hug
Token ID16225
Feature activation-3.51e-03

Pos logit contributions
balls+0.010
MY+0.010
z+0.009
bled+0.009
Mac+0.009
Neg logit contributions
adow-0.007
 lived-0.007
 about-0.006
 night-0.006
 day-0.006
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
adow+0.004
 lived+0.003
arium+0.003
 night+0.003
 day+0.003
Neg logit contributions
balls-0.008
bled-0.008
MY-0.008
Mac-0.007
ula-0.007
Token Ben
Token ID3932
Feature activation+4.19e-02

Pos logit contributions
balls+0.036
Mac+0.035
MY+0.034
bled+0.034
Marcus+0.033
Neg logit contributions
adow-0.066
 lived-0.063
 about-0.061
 day-0.060
 night-0.060
Token shouts
Token ID34757
Feature activation+1.08e-02

Pos logit contributions
bled+0.078
MY+0.075
balls+0.074
z+0.073
Mac+0.073
Neg logit contributions
 about-0.059
adow-0.059
 lived-0.058
 of-0.054
 night-0.053
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
Mac+0.029
bled+0.029
MY+0.029
Marcus+0.028
balls+0.028
Neg logit contributions
 about-0.007
adow-0.006
 of-0.006
 lived-0.005
 night-0.005
Token
Token ID198
Feature activation+9.98e-03

Pos logit contributions
bled+0.033
MY+0.033
irling+0.032
z+0.032
aults+0.032
Neg logit contributions
 about-0.011
 lived-0.011
 of-0.010
 night-0.009
 day-0.009
Token
Token ID198
Feature activation+6.94e-03

Pos logit contributions
MY+0.022
bled+0.022
balls+0.022
 seventeen+0.021
 eighteen+0.021
Neg logit contributions
 lived-0.010
 about-0.010
adow-0.010
 of-0.010
 night-0.009
Token"
Token ID1
Feature activation+5.13e-02

Pos logit contributions
MY+0.011
bled+0.010
ula+0.010
 wrists+0.010
 extract+0.010
Neg logit contributions
 lived-0.012
 of-0.012
 about-0.011
adow-0.011
 night-0.011
TokenBen
Token ID11696
Feature activation+2.95e-02

Pos logit contributions
bled+0.087
MY+0.084
 seventeen+0.083
 extract+0.082
 wrists+0.081
Neg logit contributions
 lived-0.075
 day-0.071
 of-0.069
 night-0.068
igator-0.067
Token,
Token ID11
Feature activation+4.50e-02

Pos logit contributions
bled+0.071
balls+0.069
ula+0.068
 wrists+0.068
Mac+0.068
Neg logit contributions
 lived-0.026
adow-0.025
 about-0.025
 night-0.023
 day-0.023
Token Anna
Token ID11735
Feature activation+8.49e-04

Pos logit contributions
MY+0.082
bled+0.082
z+0.082
Mac+0.081
balls+0.079
Neg logit contributions
 lived-0.063
 about-0.061
adow-0.059
 night-0.059
 day-0.057
Token,
Token ID11
Feature activation+3.00e-02

Pos logit contributions
balls+0.002
MY+0.002
bled+0.002
Mac+0.002
z+0.002
Neg logit contributions
adow-0.001
 lived-0.001
 about-0.001
 night-0.001
 day-0.001
Token run
Token ID1057
Feature activation+2.44e-02

Pos logit contributions
bled+0.057
MY+0.056
balls+0.056
Mac+0.056
z+0.055
Neg logit contributions
adow-0.039
 lived-0.039
 about-0.038
 night-0.037
 day-0.036
Tokeny
Token ID88
Feature activation+1.73e-02

Pos logit contributions
MY+0.018
bled+0.018
balls+0.018
ula+0.017
z+0.017
Neg logit contributions
 lived-0.013
adow-0.013
 adventure-0.012
 about-0.012
 night-0.012
Token.
Token ID13
Feature activation+1.86e-03

Pos logit contributions
balls+0.033
MY+0.032
bled+0.031
z+0.031
 eighteen+0.031
Neg logit contributions
adow-0.022
 lived-0.021
 about-0.020
 night-0.019
arium-0.019
Token You
Token ID921
Feature activation-3.04e-03

Pos logit contributions
balls+0.004
bled+0.004
MY+0.004
Mac+0.004
z+0.003
Neg logit contributions
adow-0.002
 lived-0.002
 about-0.002
 night-0.002
 day-0.002
Token should
Token ID815
Feature activation-1.92e-02

Pos logit contributions
adow+0.004
 about+0.004
 lived+0.004
 day+0.004
 night+0.004
Neg logit contributions
Mac-0.005
balls-0.005
MY-0.005
bled-0.005
Er-0.005
Token take
Token ID1011
Feature activation+2.24e-02

Pos logit contributions
adow+0.028
 lived+0.027
 about+0.026
 night+0.026
 day+0.025
Neg logit contributions
balls-0.032
MY-0.032
bled-0.032
Mac-0.032
 eighteen-0.031
Token a
Token ID257
Feature activation+4.37e-02

Pos logit contributions
bled+0.042
balls+0.042
MY+0.041
Mac+0.041
z+0.040
Neg logit contributions
 about-0.031
 night-0.031
adow-0.030
 lived-0.030
 day-0.030
Token break
Token ID2270
Feature activation+1.95e-02

Pos logit contributions
balls+0.070
MY+0.070
bled+0.070
Mac+0.069
z+0.067
Neg logit contributions
adow-0.070
 lived-0.068
 about-0.066
 night-0.064
 day-0.063
Token.
Token ID13
Feature activation-7.08e-03

Pos logit contributions
balls+0.039
bled+0.039
MY+0.039
Mac+0.038
z+0.037
Neg logit contributions
adow-0.024
 lived-0.022
 about-0.022
 night-0.022
 day-0.021
Tokenâ
Token ID22940
Feature activation-7.17e-03

Pos logit contributions
adow+0.009
 lived+0.009
 about+0.009
 night+0.008
 day+0.008
Neg logit contributions
bled-0.014
balls-0.014
MY-0.013
Mac-0.013
z-0.013
Token
Token ID26391
Feature activation+3.88e-02

Pos logit contributions
adow+0.013
 lived+0.013
 about+0.013
 of+0.013
 night+0.013
Neg logit contributions
MY-0.009
bled-0.009
Mac-0.009
z-0.009
 seventeen-0.008
Token
Token ID198
Feature activation+3.67e-03

Pos logit contributions
bled+0.060
balls+0.058
MY+0.056
Mac+0.055
ula+0.054
Neg logit contributions
adow-0.070
 lived-0.066
 about-0.064
 night-0.062
 day-0.061
Token got
Token ID1392
Feature activation+4.98e-02

Pos logit contributions
 lived+0.005
 about+0.005
 night+0.005
adow+0.005
 day+0.005
Neg logit contributions
MY-0.006
balls-0.006
Mac-0.006
bled-0.006
z-0.006
Token hurt
Token ID5938
Feature activation-1.19e-02

Pos logit contributions
MY+0.090
Mac+0.087
balls+0.086
 seventeen+0.084
bled+0.084
Neg logit contributions
 night-0.071
 about-0.070
 lived-0.070
 of-0.069
 day-0.068
Token.
Token ID13
Feature activation+1.88e-03

Pos logit contributions
adow+0.010
 lived+0.010
 about+0.009
 night+0.009
 day+0.009
Neg logit contributions
bled-0.028
balls-0.028
MY-0.028
Mac-0.027
z-0.027
Token Her
Token ID2332
Feature activation-7.13e-03

Pos logit contributions
balls+0.004
bled+0.004
MY+0.004
Mac+0.004
ula+0.004
Neg logit contributions
adow-0.002
 lived-0.002
 about-0.002
 night-0.002
 day-0.002
Token mom
Token ID1995
Feature activation+5.71e-03

Pos logit contributions
 day+0.013
 night+0.012
 lived+0.012
 about+0.012
adow+0.012
Neg logit contributions
MY-0.011
Mac-0.010
 seventeen-0.010
z-0.010
bled-0.010
Token took
Token ID1718
Feature activation+2.59e-02

Pos logit contributions
balls+0.011
MY+0.011
bled+0.011
Mac+0.011
 eighteen+0.010
Neg logit contributions
 lived-0.007
adow-0.007
 about-0.007
 night-0.007
 of-0.007
Token her
Token ID607
Feature activation+1.34e-02

Pos logit contributions
balls+0.048
bled+0.047
MY+0.047
Mac+0.047
z+0.045
Neg logit contributions
adow-0.035
 lived-0.035
 about-0.034
 night-0.033
 day-0.032
Token to
Token ID284
Feature activation-1.55e-02

Pos logit contributions
balls+0.028
bled+0.028
MY+0.027
Mac+0.027
z+0.026
Neg logit contributions
adow-0.015
 lived-0.015
 about-0.014
 night-0.014
 day-0.013
Token the
Token ID262
Feature activation-2.83e-02

Pos logit contributions
adow+0.023
 lived+0.023
 about+0.022
 night+0.022
 day+0.021
Neg logit contributions
balls-0.026
bled-0.026
MY-0.026
Mac-0.026
z-0.025
Token hospital
Token ID4436
Feature activation-3.88e-02

Pos logit contributions
adow+0.040
 lived+0.038
 about+0.038
 night+0.037
 day+0.036
Neg logit contributions
balls-0.051
bled-0.051
MY-0.051
Mac-0.050
z-0.049
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
adow+0.053
 lived+0.053
 night+0.048
 day+0.046
 belong+0.046
Neg logit contributions
balls-0.070
MY-0.068
bled-0.068
z-0.067
ula-0.066
Token.
Token ID13
Feature activation-8.20e-03

Pos logit contributions
adow+0.022
 night+0.022
 lived+0.022
arium+0.021
bye+0.021
Neg logit contributions
ula-0.021
balls-0.021
MY-0.020
z-0.019
bled-0.018
Token She
Token ID1375
Feature activation-2.14e-03

Pos logit contributions
adow+0.009
 lived+0.009
 about+0.008
 night+0.008
 day+0.008
Neg logit contributions
balls-0.017
bled-0.017
MY-0.017
Mac-0.017
z-0.016
Token found
Token ID1043
Feature activation+8.18e-03

Pos logit contributions
adow+0.003
 lived+0.003
 about+0.003
 night+0.003
 day+0.003
Neg logit contributions
balls-0.004
bled-0.004
MY-0.004
Mac-0.004
z-0.004
Token some
Token ID617
Feature activation+4.52e-03

Pos logit contributions
MY+0.015
Mac+0.014
balls+0.014
 seventeen+0.014
z+0.014
Neg logit contributions
 about-0.011
 lived-0.011
 of-0.011
 night-0.011
adow-0.011
Token y
Token ID331
Feature activation-1.26e-02

Pos logit contributions
balls+0.007
bled+0.007
MY+0.006
Mac+0.006
z+0.006
Neg logit contributions
adow-0.008
 lived-0.008
 about-0.008
 night-0.007
 day-0.007
Tokenummy
Token ID13513
Feature activation+1.42e-02

Pos logit contributions
adow+0.017
 lived+0.017
 about+0.016
 night+0.016
 day+0.015
Neg logit contributions
balls-0.023
bled-0.023
MY-0.023
Mac-0.023
z-0.022
Token food
Token ID2057
Feature activation-3.15e-03

Pos logit contributions
bled+0.026
MY+0.025
Mac+0.025
balls+0.024
ula+0.024
Neg logit contributions
adow-0.021
 about-0.020
 lived-0.020
 of-0.020
 night-0.020
Token and
Token ID290
Feature activation-4.84e-03

Pos logit contributions
adow+0.004
 lived+0.004
 night+0.004
 about+0.004
 day+0.004
Neg logit contributions
balls-0.006
bled-0.006
MY-0.006
ula-0.005
Mac-0.005
Token put
Token ID1234
Feature activation+4.61e-02

Pos logit contributions
adow+0.007
 lived+0.007
 about+0.007
 night+0.007
 day+0.006
Neg logit contributions
balls-0.008
bled-0.008
MY-0.008
Mac-0.008
z-0.008
Token it
Token ID340
Feature activation+4.57e-02

Pos logit contributions
MY+0.088
Mac+0.088
irling+0.086
Marcus+0.084
z+0.084
Neg logit contributions
 night-0.061
 lived-0.059
 day-0.059
 about-0.057
 of-0.057
Token on
Token ID319
Feature activation-1.01e-04

Pos logit contributions
balls+0.079
MY+0.079
bled+0.079
Mac+0.078
z+0.075
Neg logit contributions
adow-0.067
 lived-0.065
 about-0.063
 night-0.062
 day-0.061
Token and
Token ID290
Feature activation-5.87e-03

Pos logit contributions
balls+0.011
bled+0.010
z+0.010
MY+0.010
ula+0.010
Neg logit contributions
adow-0.010
 lived-0.009
arium-0.008
 night-0.008
 belong-0.008
Token he
Token ID339
Feature activation+1.52e-02

Pos logit contributions
adow+0.008
arium+0.007
 zone+0.007
 sorts+0.007
 night+0.006
Neg logit contributions
bled-0.011
balls-0.011
Mac-0.010
 chip-0.010
Marcus-0.009
Token had
Token ID550
Feature activation+3.88e-03

Pos logit contributions
balls+0.028
bled+0.028
Mac+0.027
MY+0.026
z+0.026
Neg logit contributions
adow-0.021
arium-0.018
 about-0.018
 night-0.018
 zone-0.017
Token learned
Token ID4499
Feature activation-4.23e-03

Pos logit contributions
balls+0.007
Mac+0.007
bled+0.007
 eighteen+0.007
MY+0.007
Neg logit contributions
adow-0.005
 lived-0.005
arium-0.004
 night-0.004
 zone-0.004
Token an
Token ID281
Feature activation-8.45e-03

Pos logit contributions
adow+0.007
 lived+0.007
arium+0.006
 night+0.006
 day+0.006
Neg logit contributions
bled-0.006
balls-0.006
Mac-0.006
ula-0.006
MY-0.006
Token important
Token ID1593
Feature activation+5.85e-03

Pos logit contributions
 lived+0.012
arium+0.012
adow+0.011
 zone+0.010
 night+0.010
Neg logit contributions
MY-0.014
ula-0.014
bled-0.014
Mac-0.013
 chip-0.013
Token lesson
Token ID11483
Feature activation-4.01e-02

Pos logit contributions
balls+0.010
MY+0.009
Mac+0.009
bled+0.009
z+0.009
Neg logit contributions
adow-0.009
 lived-0.009
 about-0.009
 night-0.008
arium-0.008
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
adow+0.060
arium+0.056
 lived+0.053
igator+0.053
weet+0.052
Neg logit contributions
ula-0.069
balls-0.066
bled-0.063
Marcus-0.059
 chip-0.058
Token From
Token ID3574
Feature activation-5.49e-02

Pos logit contributions
adow+0.020
 lived+0.018
arium+0.018
igator+0.018
 belong+0.017
Neg logit contributions
Mac-0.026
Marcus-0.025
ula-0.025
Er-0.025
MY-0.025
Token then
Token ID788
Feature activation+3.32e-02

Pos logit contributions
adow+0.077
 lived+0.074
 about+0.071
 night+0.069
 day+0.067
Neg logit contributions
bled-0.100
balls-0.099
MY-0.098
Mac-0.097
z-0.094
Token on
Token ID319
Feature activation-2.14e-03

Pos logit contributions
bled+0.038
Mac+0.036
balls+0.036
z+0.036
ula+0.035
Neg logit contributions
adow-0.071
 lived-0.065
arium-0.064
 about-0.063
 adventure-0.062
Token
Token ID198
Feature activation+1.29e-02

Pos logit contributions
bled+0.029
MY+0.029
balls+0.029
Mac+0.028
 seventeen+0.027
Neg logit contributions
adow-0.018
 lived-0.018
 about-0.017
 night-0.017
 day-0.016
TokenL
Token ID43
Feature activation+2.01e-02

Pos logit contributions
bled+0.018
MY+0.018
balls+0.018
 wrists+0.016
 seventeen+0.016
Neg logit contributions
 lived-0.024
 of-0.023
adow-0.023
 day-0.022
 about-0.022
Tokenila
Token ID10102
Feature activation+1.77e-02

Pos logit contributions
bled+0.022
balls+0.022
MY+0.021
Mac+0.021
ula+0.020
Neg logit contributions
adow-0.042
 lived-0.042
 about-0.041
 night-0.040
 day-0.040
Token and
Token ID290
Feature activation-1.12e-02

Pos logit contributions
balls+0.035
MY+0.035
bled+0.035
Mac+0.034
ula+0.034
Neg logit contributions
adow-0.022
 lived-0.022
 about-0.021
 night-0.020
 day-0.020
Token Blink
Token ID41732
Feature activation-8.23e-03

Pos logit contributions
adow+0.020
 lived+0.019
 about+0.019
 night+0.019
 day+0.018
Neg logit contributions
balls-0.016
bled-0.016
Mac-0.016
MY-0.016
z-0.015
Token played
Token ID2826
Feature activation+3.73e-02

Pos logit contributions
adow+0.010
 about+0.010
 night+0.009
 sorts+0.009
 day+0.009
Neg logit contributions
balls-0.015
bled-0.015
Mac-0.015
z-0.015
 eighteen-0.015
Token for
Token ID329
Feature activation+4.51e-03

Pos logit contributions
MY+0.070
Mac+0.068
bled+0.068
balls+0.067
 seventeen+0.067
Neg logit contributions
 lived-0.051
 about-0.051
adow-0.050
 day-0.047
 night-0.047
Token a
Token ID257
Feature activation+2.08e-02

Pos logit contributions
bled+0.008
MY+0.008
balls+0.008
ula+0.008
z+0.008
Neg logit contributions
 lived-0.006
 about-0.006
 night-0.006
adow-0.006
 day-0.006
Token long
Token ID890
Feature activation+3.68e-02

Pos logit contributions
bled+0.032
balls+0.032
MY+0.032
Mac+0.032
z+0.030
Neg logit contributions
adow-0.034
 lived-0.033
 about-0.033
 night-0.032
 day-0.032
Token time
Token ID640
Feature activation+1.18e-02

Pos logit contributions
balls+0.076
z+0.076
MY+0.076
 eighteen+0.074
Mac+0.074
Neg logit contributions
adow-0.041
 lived-0.036
 about-0.036
 zone-0.033
 belong-0.032
Token.
Token ID13
Feature activation+4.01e-03

Pos logit contributions
balls+0.019
z+0.018
ula+0.017
irling+0.017
bles+0.017
Neg logit contributions
 lived-0.018
 belong-0.017
adow-0.017
igator-0.017
grand-0.017
Token said
Token ID531
Feature activation-1.27e-02

Pos logit contributions
adow+0.013
 night+0.012
 Yesterday+0.012
arium+0.011
 lived+0.011
Neg logit contributions
balls-0.017
Mac-0.017
z-0.017
MY-0.017
 wrists-0.017
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
adow+0.015
 lived+0.013
 night+0.012
arium+0.012
 sorts+0.012
Neg logit contributions
bled-0.026
balls-0.026
ula-0.025
MY-0.024
z-0.024
Token<|endoftext|>
Token ID50256
Feature activation+4.01e-03

Pos logit contributions
adow+0.017
 lived+0.017
 about+0.016
 night+0.016
 day+0.015
Neg logit contributions
balls-0.023
Mac-0.023
MY-0.023
bled-0.023
z-0.022
TokenOne
Token ID3198
Feature activation-2.89e-02

Pos logit contributions
balls+0.007
bled+0.007
MY+0.007
Mac+0.007
z+0.007
Neg logit contributions
adow-0.006
 lived-0.006
 about-0.006
 night-0.005
 day-0.005
Token day
Token ID1110
Feature activation+3.55e-02

Pos logit contributions
 zone+0.020
 privacy+0.018
arium+0.017
 lived+0.017
grand+0.016
Neg logit contributions
Mac-0.063
Danny-0.062
z-0.062
 chip-0.062
Re-0.060
Token,
Token ID11
Feature activation+1.91e-02

Pos logit contributions
balls+0.075
bled+0.074
MY+0.074
Mac+0.074
z+0.072
Neg logit contributions
adow-0.039
 lived-0.038
 about-0.036
 night-0.035
 day-0.034
Token two
Token ID734
Feature activation-2.92e-02

Pos logit contributions
balls+0.031
bled+0.031
MY+0.031
Mac+0.031
z+0.030
Neg logit contributions
adow-0.030
 lived-0.029
 about-0.028
 night-0.028
 day-0.027
Token friends
Token ID2460
Feature activation-2.27e-02

Pos logit contributions
adow+0.039
 lived+0.039
 about+0.038
 night+0.037
 day+0.036
Neg logit contributions
bled-0.055
balls-0.055
MY-0.055
Mac-0.054
z-0.052
Token Jack
Token ID3619
Feature activation-1.07e-02

Pos logit contributions
adow+0.032
 about+0.028
 night+0.028
 lived+0.027
arium+0.026
Neg logit contributions
bled-0.038
MY-0.038
balls-0.038
z-0.037
Mac-0.037
Token and
Token ID290
Feature activation-2.39e-02

Pos logit contributions
adow+0.017
 lately+0.016
 about+0.016
 belong+0.016
arium+0.016
Neg logit contributions
z-0.014
MY-0.014
balls-0.014
bled-0.013
Marcus-0.013
Token Jane
Token ID12091
Feature activation-1.87e-02

Pos logit contributions
adow+0.033
 lived+0.031
 about+0.031
 night+0.030
 day+0.029
Neg logit contributions
balls-0.044
bled-0.043
MY-0.043
Mac-0.043
z-0.041
Token secret
Token ID3200
Feature activation+1.14e-02

Pos logit contributions
bled+0.063
balls+0.063
MY+0.063
Mac+0.062
z+0.060
Neg logit contributions
adow-0.063
 lived-0.061
 about-0.060
 night-0.060
 day-0.059
Token!
Token ID0
Feature activation-1.29e-02

Pos logit contributions
balls+0.021
MY+0.021
z+0.020
bled+0.020
aults+0.020
Neg logit contributions
 lived-0.015
adow-0.014
 about-0.012
 night-0.012
arium-0.012
Token He
Token ID679
Feature activation+5.80e-03

Pos logit contributions
adow+0.017
 lived+0.016
 night+0.016
 about+0.015
 adventure+0.015
Neg logit contributions
Mac-0.024
MY-0.024
balls-0.024
Marcus-0.023
bled-0.023
Token told
Token ID1297
Feature activation-2.00e-02

Pos logit contributions
balls+0.010
bled+0.010
MY+0.010
Mac+0.010
z+0.010
Neg logit contributions
adow-0.008
 lived-0.008
 about-0.008
 night-0.007
 day-0.007
Token his
Token ID465
Feature activation-1.80e-02

Pos logit contributions
 about+0.025
adow+0.024
 lived+0.024
 night+0.023
 day+0.023
Neg logit contributions
balls-0.039
bled-0.039
MY-0.039
Mac-0.039
z-0.038
Token friends
Token ID2460
Feature activation-3.72e-03

Pos logit contributions
adow+0.032
 lived+0.031
 about+0.030
 night+0.030
 day+0.029
Neg logit contributions
balls-0.026
bled-0.026
MY-0.026
Mac-0.026
z-0.025
Token what
Token ID644
Feature activation+1.27e-02

Pos logit contributions
adow+0.004
 lived+0.004
 night+0.003
arium+0.003
 zone+0.003
Neg logit contributions
balls-0.008
bled-0.008
ula-0.007
bling-0.007
Marcus-0.007
Token the
Token ID262
Feature activation-3.02e-03

Pos logit contributions
balls+0.024
Mac+0.024
Marcus+0.023
 chip+0.023
bled+0.023
Neg logit contributions
adow-0.017
 zone-0.014
arium-0.013
 night-0.013
 lived-0.013
Token special
Token ID2041
Feature activation-1.01e-02

Pos logit contributions
adow+0.005
 lived+0.004
 about+0.004
 of+0.004
 night+0.004
Neg logit contributions
balls-0.005
MY-0.005
Mac-0.005
bled-0.005
 chip-0.005
Token words
Token ID2456
Feature activation-2.41e-02

Pos logit contributions
adow+0.014
 about+0.013
 lived+0.012
 Yesterday+0.012
weet+0.012
Neg logit contributions
balls-0.017
 chip-0.016
z-0.016
Mac-0.015
MY-0.015
Token meant
Token ID4001
Feature activation-9.60e-03

Pos logit contributions
adow+0.032
arium+0.029
 night+0.027
 zone+0.026
 Yesterday+0.026
Neg logit contributions
bled-0.042
balls-0.042
 swirl-0.040
z-0.039
Mac-0.039
Token,
Token ID11
Feature activation+4.15e-02

Pos logit contributions
bled+0.097
ula+0.095
balls+0.095
Mac+0.093
MY+0.092
Neg logit contributions
 lived-0.038
adow-0.034
 about-0.034
 night-0.033
 day-0.032
Token you
Token ID345
Feature activation-5.09e-03

Pos logit contributions
balls+0.077
bled+0.075
Mac+0.075
MY+0.075
 eighteen+0.072
Neg logit contributions
adow-0.057
 lived-0.053
 about-0.052
 night-0.051
 day-0.050
Token are
Token ID389
Feature activation-3.38e-03

Pos logit contributions
adow+0.007
 about+0.007
 night+0.007
 lived+0.006
 day+0.006
Neg logit contributions
Mac-0.009
balls-0.009
MY-0.009
bled-0.009
z-0.009
Token mean
Token ID1612
Feature activation-1.04e-02

Pos logit contributions
adow+0.005
 lived+0.005
 about+0.005
 night+0.005
 day+0.005
Neg logit contributions
bled-0.006
balls-0.006
MY-0.006
Mac-0.006
z-0.005
Token!
Token ID0
Feature activation-1.32e-02

Pos logit contributions
 lived+0.016
adow+0.016
arium+0.014
 night+0.014
 day+0.014
Neg logit contributions
balls-0.018
MY-0.018
z-0.017
Mac-0.016
ula-0.016
Token You
Token ID921
Feature activation-3.34e-03

Pos logit contributions
adow+0.015
 lived+0.015
 about+0.014
 night+0.013
 day+0.013
Neg logit contributions
bled-0.028
balls-0.027
MY-0.027
Mac-0.027
z-0.026
Token are
Token ID389
Feature activation+8.92e-04

Pos logit contributions
adow+0.005
arium+0.005
 day+0.005
 night+0.005
 about+0.005
Neg logit contributions
Mac-0.005
balls-0.005
MY-0.005
z-0.005
 eighteen-0.005
Token not
Token ID407
Feature activation+2.48e-03

Pos logit contributions
bled+0.001
MY+0.001
balls+0.001
Mac+0.001
z+0.001
Neg logit contributions
 about-0.001
adow-0.001
 lived-0.001
 night-0.001
 day-0.001
Token my
Token ID616
Feature activation+9.60e-03

Pos logit contributions
balls+0.004
MY+0.004
Mac+0.004
bled+0.004
 eighteen+0.004
Neg logit contributions
adow-0.004
 lived-0.004
 night-0.004
arium-0.004
 day-0.004
Token friend
Token ID1545
Feature activation+6.61e-03

Pos logit contributions
balls+0.017
MY+0.016
bled+0.016
Mac+0.016
z+0.016
Neg logit contributions
adow-0.014
 lived-0.014
 about-0.013
 night-0.013
 day-0.013
Token!
Token ID0
Feature activation-1.24e-02

Pos logit contributions
MY+0.012
balls+0.012
 chip+0.011
z+0.011
 eighteen+0.011
Neg logit contributions
adow-0.009
 lived-0.009
arium-0.008
 night-0.008
 sorts-0.008
Token
Token ID198
Feature activation+1.30e-02

Pos logit contributions
balls+0.013
Mac+0.013
MY+0.013
bled+0.013
Marcus+0.012
Neg logit contributions
adow-0.012
 lived-0.011
 about-0.011
 night-0.011
 day-0.010
Token
Token ID198
Feature activation+7.31e-03

Pos logit contributions
bled+0.030
balls+0.030
MY+0.029
 seventeen+0.029
 wrists+0.028
Neg logit contributions
 lived-0.012
 about-0.012
adow-0.012
 of-0.012
 day-0.012
TokenThe
Token ID464
Feature activation+4.96e-03

Pos logit contributions
bled+0.011
balls+0.010
MY+0.010
 extract+0.009
 wrists+0.009
Neg logit contributions
 lived-0.013
adow-0.013
 of-0.013
 day-0.013
 about-0.012
Token boy
Token ID2933
Feature activation+1.89e-02

Pos logit contributions
MY+0.009
bled+0.009
balls+0.009
Mac+0.009
z+0.009
Neg logit contributions
 day-0.007
 night-0.007
 lived-0.007
adow-0.007
 about-0.007
Token did
Token ID750
Feature activation+1.01e-02

Pos logit contributions
balls+0.032
bled+0.032
Mac+0.032
MY+0.031
z+0.031
Neg logit contributions
adow-0.027
 night-0.025
 lived-0.025
 about-0.025
 day-0.025
Token not
Token ID407
Feature activation-9.87e-03

Pos logit contributions
balls+0.011
bled+0.011
MY+0.011
Mac+0.010
 eighteen+0.010
Neg logit contributions
adow-0.021
 lived-0.020
 night-0.020
 zone-0.020
 day-0.019
Token understand
Token ID1833
Feature activation-2.96e-02

Pos logit contributions
adow+0.014
 lived+0.014
arium+0.013
 night+0.013
 about+0.013
Neg logit contributions
MY-0.017
balls-0.017
Mac-0.017
 eighteen-0.016
bled-0.016
Token,
Token ID11
Feature activation+3.34e-02

Pos logit contributions
adow+0.040
 lived+0.038
arium+0.035
 night+0.034
bye+0.033
Neg logit contributions
Mac-0.053
 chip-0.053
balls-0.053
MY-0.052
ula-0.052
Token so
Token ID523
Feature activation-2.48e-04

Pos logit contributions
balls+0.056
MY+0.053
Mac+0.053
bled+0.053
 eighteen+0.052
Neg logit contributions
adow-0.053
 lived-0.049
 night-0.046
arium-0.045
 day-0.044
Token he
Token ID339
Feature activation+9.42e-03

Pos logit contributions
adow+0.000
 lived+0.000
 about+0.000
 night+0.000
 day+0.000
Neg logit contributions
balls-0.001
bled-0.001
Mac-0.001
MY-0.001
 eighteen-0.001
Token asked
Token ID1965
Feature activation-1.38e-02

Pos logit contributions
balls+0.018
bled+0.018
MY+0.017
Mac+0.017
z+0.017
Neg logit contributions
adow-0.013
 lived-0.012
 about-0.012
 night-0.011
 day-0.011
Token saw
Token ID2497
Feature activation-7.46e-03

Pos logit contributions
balls+0.034
bled+0.034
Mac+0.034
MY+0.033
z+0.032
Neg logit contributions
adow-0.028
 lived-0.025
 about-0.025
 night-0.025
 day-0.025
Token him
Token ID683
Feature activation+1.02e-03

Pos logit contributions
adow+0.011
 lived+0.009
 night+0.009
 day+0.009
 zone+0.009
Neg logit contributions
bled-0.014
balls-0.013
Mac-0.013
MY-0.013
 eighteen-0.012
Token fall
Token ID2121
Feature activation+9.28e-03

Pos logit contributions
balls+0.002
MY+0.002
bled+0.002
Mac+0.002
z+0.002
Neg logit contributions
 lived-0.002
adow-0.002
 night-0.001
arium-0.001
 about-0.001
Token and
Token ID290
Feature activation+2.51e-03

Pos logit contributions
MY+0.015
balls+0.015
z+0.014
bled+0.014
ula+0.014
Neg logit contributions
adow-0.015
 lived-0.015
arium-0.014
 about-0.013
 sorts-0.013
Token came
Token ID1625
Feature activation+9.50e-03

Pos logit contributions
balls+0.004
bled+0.004
Mac+0.004
z+0.004
MY+0.004
Neg logit contributions
adow-0.005
 about-0.004
 zone-0.004
arium-0.004
 adventure-0.004
Token to
Token ID284
Feature activation-3.30e-03

Pos logit contributions
bled+0.018
MY+0.018
balls+0.018
Mac+0.018
 seventeen+0.017
Neg logit contributions
adow-0.012
 lived-0.012
 about-0.012
 night-0.011
 day-0.011
Token help
Token ID1037
Feature activation-5.43e-03

Pos logit contributions
adow+0.004
 lived+0.004
 about+0.004
 night+0.004
 day+0.004
Neg logit contributions
balls-0.006
bled-0.006
MY-0.006
Mac-0.006
z-0.006
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
adow+0.006
 lived+0.006
arium+0.005
 about+0.005
 night+0.005
Neg logit contributions
balls-0.012
bled-0.011
MY-0.011
Mac-0.011
ula-0.011
Token Sam
Token ID3409
Feature activation+2.07e-02

Pos logit contributions
adow+0.015
 night+0.013
 lived+0.013
 day+0.012
 zone+0.012
Neg logit contributions
balls-0.021
MY-0.019
Mac-0.019
bled-0.019
 chip-0.019
Token said
Token ID531
Feature activation+1.29e-03

Pos logit contributions
ula+0.046
bled+0.046
balls+0.045
MY+0.045
 seventeen+0.045
Neg logit contributions
 lived-0.023
 about-0.021
adow-0.020
 of-0.019
 night-0.019
Token,
Token ID11
Feature activation+2.70e-02

Pos logit contributions
balls+0.003
bled+0.003
MY+0.003
Mac+0.003
z+0.003
Neg logit contributions
adow-0.001
 lived-0.001
 about-0.001
 night-0.001
 day-0.001
Token little
Token ID1310
Feature activation-1.54e-02

Pos logit contributions
 day+0.003
 night+0.003
 lived+0.003
 of+0.003
adow+0.003
Neg logit contributions
bled-0.007
 seventeen-0.006
balls-0.006
 eighteen-0.006
z-0.006
Token girl
Token ID2576
Feature activation-5.89e-03

Pos logit contributions
adow+0.022
 night+0.022
 day+0.021
 lived+0.021
 of+0.020
Neg logit contributions
bled-0.029
balls-0.028
Mac-0.027
MY-0.027
 seventeen-0.027
Token who
Token ID508
Feature activation-8.76e-03

Pos logit contributions
adow+0.006
 about+0.006
 belong+0.005
 zone+0.005
arium+0.005
Neg logit contributions
z-0.012
 chip-0.011
MY-0.011
Mac-0.011
 brist-0.011
Token went
Token ID1816
Feature activation+7.71e-03

Pos logit contributions
adow+0.012
arium+0.012
 about+0.011
 adventure+0.011
 zone+0.011
Neg logit contributions
Mac-0.015
z-0.015
balls-0.014
St-0.014
MY-0.014
Token to
Token ID284
Feature activation-1.66e-02

Pos logit contributions
balls+0.014
z+0.013
ula+0.013
bled+0.013
MY+0.013
Neg logit contributions
adow-0.011
 lived-0.011
 zone-0.009
 sorts-0.009
arium-0.009
Token the
Token ID262
Feature activation-3.07e-02

Pos logit contributions
adow+0.028
 lived+0.026
 about+0.025
 zone+0.024
 of+0.024
Neg logit contributions
Mac-0.025
MY-0.024
balls-0.024
bled-0.023
 chip-0.023
Token park
Token ID3952
Feature activation-1.38e-02

Pos logit contributions
 lived+0.035
adow+0.035
 night+0.034
 day+0.033
 about+0.033
Neg logit contributions
bled-0.064
balls-0.063
MY-0.063
Mac-0.061
 seventeen-0.061
Token with
Token ID351
Feature activation-2.94e-02

Pos logit contributions
 lived+0.023
 privacy+0.022
adow+0.022
 belong+0.022
igator+0.022
Neg logit contributions
z-0.020
balls-0.018
 chip-0.018
ula-0.016
 wrists-0.016
Token her
Token ID607
Feature activation-2.60e-02

Pos logit contributions
adow+0.041
 lived+0.039
 about+0.038
 night+0.037
 day+0.036
Neg logit contributions
balls-0.054
bled-0.054
MY-0.054
Mac-0.053
z-0.052
Token dad
Token ID9955
Feature activation-1.41e-02

Pos logit contributions
 lived+0.048
adow+0.047
 day+0.047
 night+0.046
 about+0.046
Neg logit contributions
MY-0.036
 seventeen-0.036
bled-0.036
 eighteen-0.036
Mac-0.035
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
 lived+0.020
adow+0.018
 belong+0.018
 privacy+0.017
 ruled+0.017
Neg logit contributions
 chip-0.024
z-0.024
balls-0.023
ula-0.023
MY-0.022
Token a
Token ID257
Feature activation-1.17e-02

Pos logit contributions
adow+0.046
 lived+0.043
 about+0.042
 night+0.042
 day+0.041
Neg logit contributions
bled-0.038
balls-0.038
Mac-0.037
MY-0.037
ula-0.036
Token little
Token ID1310
Feature activation-2.05e-02

Pos logit contributions
 lived+0.018
 night+0.018
 day+0.018
adow+0.017
 about+0.017
Neg logit contributions
bled-0.021
balls-0.020
z-0.019
Mac-0.019
MY-0.018
Token man
Token ID582
Feature activation-8.69e-03

Pos logit contributions
adow+0.030
 lived+0.029
 night+0.029
 about+0.028
 day+0.028
Neg logit contributions
bled-0.037
balls-0.037
Mac-0.035
MY-0.035
z-0.035
Token standing
Token ID5055
Feature activation+2.19e-05

Pos logit contributions
 lived+0.013
adow+0.013
 night+0.013
 about+0.012
 day+0.012
Neg logit contributions
z-0.013
balls-0.013
bled-0.013
Mac-0.013
MY-0.013
Token in
Token ID287
Feature activation-9.81e-03

Pos logit contributions
balls+0.000
MY+0.000
 seventeen+0.000
Mac+0.000
 eighteen+0.000
Neg logit contributions
adow-0.000
 about-0.000
 lived-0.000
 night-0.000
 day-0.000
Token front
Token ID2166
Feature activation-5.36e-02

Pos logit contributions
adow+0.018
 lived+0.017
 about+0.016
 night+0.015
 day+0.015
Neg logit contributions
MY-0.014
Mac-0.014
balls-0.014
bled-0.014
Marcus-0.013
Token of
Token ID286
Feature activation-1.59e-02

Pos logit contributions
 lived+0.052
 belong+0.047
adow+0.044
arium+0.043
 night+0.036
Neg logit contributions
 swirl-0.106
 seventeen-0.104
 edge-0.102
Danny-0.102
 sprink-0.102
Token her
Token ID607
Feature activation-2.90e-02

Pos logit contributions
adow+0.022
 lived+0.021
 about+0.021
 night+0.020
 day+0.020
Neg logit contributions
balls-0.029
bled-0.029
MY-0.029
Mac-0.029
z-0.028
Token.
Token ID13
Feature activation-4.95e-03

Pos logit contributions
 lived+0.033
adow+0.031
 about+0.030
 sorts+0.029
arium+0.029
Neg logit contributions
balls-0.056
MY-0.054
 wrists-0.054
z-0.054
bled-0.053
Token The
Token ID383
Feature activation+1.94e-03

Pos logit contributions
adow+0.006
 lived+0.006
 about+0.005
 night+0.005
 day+0.005
Neg logit contributions
balls-0.010
MY-0.010
Mac-0.010
bled-0.010
z-0.010
Token man
Token ID582
Feature activation-2.19e-03

Pos logit contributions
balls+0.002
bled+0.002
MY+0.002
Mac+0.002
 eighteen+0.002
Neg logit contributions
adow-0.004
 lived-0.004
 about-0.004
 night-0.003
 day-0.003
Token in
Token ID287
Feature activation-2.38e-02

Pos logit contributions
adow+0.040
 lived+0.039
 about+0.038
 night+0.037
 day+0.036
Neg logit contributions
bled-0.049
balls-0.048
MY-0.048
Mac-0.047
z-0.046
Token the
Token ID262
Feature activation-5.78e-03

Pos logit contributions
adow+0.048
 lived+0.045
 about+0.043
 zone+0.040
 day+0.040
Neg logit contributions
Mac-0.029
MY-0.029
balls-0.027
 chip-0.027
z-0.027
Token grass
Token ID8701
Feature activation-3.66e-02

Pos logit contributions
adow+0.009
 lived+0.008
 about+0.008
 night+0.008
 of+0.008
Neg logit contributions
balls-0.010
MY-0.010
bled-0.010
Mac-0.010
 eighteen-0.009
Token near
Token ID1474
Feature activation-3.02e-02

Pos logit contributions
 lived+0.046
grand+0.043
 belong+0.043
adow+0.042
 privacy+0.041
Neg logit contributions
balls-0.069
z-0.065
bled-0.064
ula-0.064
MY-0.063
Token the
Token ID262
Feature activation-1.56e-02

Pos logit contributions
adow+0.053
 lived+0.051
 about+0.048
 night+0.047
 day+0.047
Neg logit contributions
Mac-0.042
bled-0.041
balls-0.041
MY-0.041
ula-0.040
Token flower
Token ID15061
Feature activation-4.71e-02

Pos logit contributions
 night+0.021
 day+0.020
 lived+0.020
adow+0.019
 about+0.018
Neg logit contributions
bled-0.031
z-0.030
balls-0.030
Mac-0.030
MY-0.029
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
 lived+0.060
grand+0.058
 hour+0.057
 lately+0.057
bye+0.056
Neg logit contributions
balls-0.078
z-0.072
 chip-0.071
 wrists-0.071
MY-0.071
Token The
Token ID383
Feature activation-7.11e-04

Pos logit contributions
adow+0.013
 lived+0.013
 about+0.012
 night+0.012
 day+0.012
Neg logit contributions
balls-0.019
MY-0.019
bled-0.019
Mac-0.019
z-0.018
Token little
Token ID1310
Feature activation-8.78e-03

Pos logit contributions
adow+0.001
 lived+0.001
 about+0.001
 night+0.001
 day+0.001
Neg logit contributions
bled-0.001
balls-0.001
MY-0.001
Mac-0.001
z-0.001
Token girl
Token ID2576
Feature activation+4.20e-03

Pos logit contributions
adow+0.013
 lived+0.012
 night+0.012
 day+0.012
 about+0.012
Neg logit contributions
bled-0.016
balls-0.016
MY-0.015
Mac-0.015
Marcus-0.015
Token felt
Token ID2936
Feature activation-1.02e-02

Pos logit contributions
balls+0.008
bled+0.008
MY+0.008
Mac+0.008
ula+0.008
Neg logit contributions
adow-0.005
 lived-0.005
 about-0.005
 night-0.005
 day-0.005
Token girl
Token ID2576
Feature activation-1.95e-02

Pos logit contributions
adow+0.060
 lived+0.058
 about+0.057
 night+0.053
 adventure+0.052
Neg logit contributions
balls-0.048
MY-0.047
Mac-0.046
bled-0.045
 chip-0.045
Token who
Token ID508
Feature activation-1.57e-02

Pos logit contributions
adow+0.022
arium+0.021
 about+0.020
 adventure+0.019
 lived+0.018
Neg logit contributions
z-0.037
 chip-0.036
balls-0.036
MY-0.035
ula-0.035
Token was
Token ID373
Feature activation-1.71e-02

Pos logit contributions
adow+0.020
arium+0.019
 about+0.018
 zone+0.017
 adventure+0.017
Neg logit contributions
Mac-0.028
MY-0.028
Er-0.027
balls-0.027
Marcus-0.027
Token three
Token ID1115
Feature activation-2.93e-02

Pos logit contributions
adow+0.024
 lived+0.023
 about+0.023
 night+0.023
 day+0.022
Neg logit contributions
balls-0.031
MY-0.031
bled-0.031
Mac-0.031
z-0.030
Token years
Token ID812
Feature activation-6.12e-02

Pos logit contributions
adow+0.035
 lived+0.034
 night+0.032
 about+0.031
arium+0.030
Neg logit contributions
MY-0.057
balls-0.056
z-0.055
bled-0.055
 chip-0.054
Token old
Token ID1468
Feature activation-5.56e-02

Pos logit contributions
adow+0.115
 lived+0.113
 zone+0.105
 belong+0.102
arium+0.098
Neg logit contributions
 chip-0.081
MY-0.079
ula-0.076
balls-0.075
bled-0.072
Token.
Token ID13
Feature activation-1.92e-02

Pos logit contributions
adow+0.056
 lived+0.052
 about+0.049
 night+0.046
 day+0.045
Neg logit contributions
balls-0.122
MY-0.122
bled-0.120
Mac-0.119
 chip-0.117
Token Her
Token ID2332
Feature activation-3.18e-02

Pos logit contributions
adow+0.028
 belong+0.024
 lived+0.024
 adventure+0.023
 about+0.023
Neg logit contributions
 chip-0.032
Mac-0.032
balls-0.032
MY-0.032
Er-0.032
Token name
Token ID1438
Feature activation-6.83e-03

Pos logit contributions
adow+0.054
 lived+0.052
 about+0.051
 night+0.050
 day+0.050
Neg logit contributions
balls-0.048
bled-0.048
MY-0.048
Mac-0.047
z-0.046
Token was
Token ID373
Feature activation-2.17e-02

Pos logit contributions
adow+0.009
 lived+0.009
 about+0.009
 night+0.008
 day+0.008
Neg logit contributions
balls-0.013
bled-0.013
MY-0.013
Mac-0.013
z-0.012
Token Tin
Token ID22894
Feature activation+1.45e-02

Pos logit contributions
 lived+0.031
 night+0.029
 about+0.029
adow+0.029
 day+0.028
Neg logit contributions
bled-0.041
balls-0.040
 seventeen-0.040
MY-0.039
z-0.039
Token wasn
Token ID2492
Feature activation+1.35e-03

Pos logit contributions
adow+0.027
 about+0.025
 night+0.025
 lived+0.024
arium+0.024
Neg logit contributions
balls-0.031
bled-0.030
z-0.030
MY-0.030
Mac-0.029
Token't
Token ID470
Feature activation-8.58e-03

Pos logit contributions
balls+0.002
bled+0.002
MY+0.002
Mac+0.002
z+0.002
Neg logit contributions
adow-0.002
 lived-0.002
 about-0.002
 night-0.002
 day-0.002
Token so
Token ID523
Feature activation+5.16e-03

Pos logit contributions
adow+0.013
 lived+0.013
 about+0.012
 night+0.012
arium+0.012
Neg logit contributions
MY-0.014
bled-0.014
balls-0.014
Mac-0.014
 eighteen-0.013
Token terrible
Token ID7818
Feature activation-1.12e-02

Pos logit contributions
MY+0.007
bled+0.007
balls+0.007
Mac+0.007
z+0.007
Neg logit contributions
adow-0.009
 lived-0.009
 about-0.008
 night-0.008
 day-0.008
Token after
Token ID706
Feature activation-3.13e-02

Pos logit contributions
adow+0.013
 lived+0.012
 night+0.011
 about+0.011
 day+0.010
Neg logit contributions
balls-0.023
MY-0.023
bled-0.023
ula-0.022
Mac-0.022
Token all
Token ID477
Feature activation-4.81e-02

Pos logit contributions
adow+0.047
 zone+0.042
 lived+0.041
arium+0.041
 sorts+0.040
Neg logit contributions
bled-0.055
balls-0.054
ula-0.052
MY-0.050
bling-0.048
Token!
Token ID0
Feature activation-2.35e-02

Pos logit contributions
adow+0.065
 lived+0.062
arium+0.059
 zone+0.055
 night+0.053
Neg logit contributions
MY-0.082
ula-0.080
balls-0.080
 chip-0.080
z-0.078
Tokenâ
Token ID22940
Feature activation-1.31e-02

Pos logit contributions
adow+0.033
 lived+0.033
 adventure+0.032
 night+0.031
 day+0.031
Neg logit contributions
Mac-0.041
MY-0.039
 eighteen-0.038
Marcus-0.038
balls-0.038
Token
Token ID26391
Feature activation+3.10e-02

Pos logit contributions
 about+0.022
 of+0.022
adow+0.022
 lived+0.022
 night+0.021
Neg logit contributions
MY-0.018
bled-0.017
 eighteen-0.017
Mac-0.017
 seventeen-0.017
Token<|endoftext|>
Token ID50256
Feature activation-7.89e-03

Pos logit contributions
balls+0.051
bled+0.051
MY+0.050
Mac+0.050
z+0.048
Neg logit contributions
adow-0.048
 lived-0.047
 about-0.046
 night-0.044
 day-0.044
TokenOnce
Token ID7454
Feature activation-1.27e-02

Pos logit contributions
adow+0.013
 about+0.012
 lived+0.012
 adventure+0.012
 night+0.012
Neg logit contributions
Mac-0.012
balls-0.012
MY-0.012
bled-0.012
z-0.011
Token "
Token ID366
Feature activation+3.18e-02

Pos logit contributions
MY+0.031
Mac+0.031
aults+0.030
z+0.030
Marcus+0.029
Neg logit contributions
 about-0.018
 lived-0.016
 because-0.015
 of-0.015
 day-0.015
TokenNo
Token ID2949
Feature activation-1.45e-02

Pos logit contributions
bled+0.046
MY+0.046
balls+0.046
Mac+0.044
 eighteen+0.042
Neg logit contributions
adow-0.056
 lived-0.054
 about-0.053
 night-0.052
 day-0.052
Token,
Token ID11
Feature activation+2.40e-02

Pos logit contributions
adow+0.024
 lived+0.023
 ruled+0.021
 zone+0.020
arium+0.020
Neg logit contributions
MY-0.024
balls-0.023
 chip-0.023
ula-0.023
 eighteen-0.022
Token sweet
Token ID6029
Feature activation-3.58e-02

Pos logit contributions
balls+0.040
MY+0.039
bled+0.039
Mac+0.039
 eighteen+0.037
Neg logit contributions
adow-0.039
 lived-0.036
 night-0.034
 about-0.034
 day-0.033
Tokenheart
Token ID11499
Feature activation-1.49e-02

Pos logit contributions
 lived+0.028
adow+0.027
 about+0.023
arium+0.023
 night+0.020
Neg logit contributions
MY-0.086
balls-0.083
 chip-0.082
Mac-0.081
ula-0.081
Token.
Token ID13
Feature activation-4.77e-02

Pos logit contributions
adow+0.017
 lived+0.016
 night+0.015
 about+0.015
arium+0.015
Neg logit contributions
balls-0.030
MY-0.030
z-0.029
bled-0.028
 eighteen-0.028
Token But
Token ID887
Feature activation-2.97e-02

Pos logit contributions
adow+0.072
 lived+0.066
 night+0.065
 about+0.065
 adventure+0.065
Neg logit contributions
balls-0.082
Mac-0.081
MY-0.079
bled-0.079
 seventeen-0.077
Token you
Token ID345
Feature activation-1.98e-02

Pos logit contributions
adow+0.044
 lived+0.041
 about+0.040
 night+0.039
 day+0.037
Neg logit contributions
bled-0.051
balls-0.051
Mac-0.049
MY-0.048
 eighteen-0.048
Token can
Token ID460
Feature activation+5.28e-03

Pos logit contributions
adow+0.029
 zone+0.027
 day+0.026
 lived+0.026
 about+0.025
Neg logit contributions
Mac-0.031
MY-0.030
balls-0.029
Marcus-0.029
 eighteen-0.029
Token play
Token ID711
Feature activation+3.06e-02

Pos logit contributions
bled+0.010
MY+0.010
balls+0.009
 seventeen+0.009
 eighteen+0.009
Neg logit contributions
 lived-0.007
adow-0.007
 about-0.007
 of-0.007
 night-0.007
Token with
Token ID351
Feature activation-2.35e-02

Pos logit contributions
bled+0.055
MY+0.055
Mac+0.054
 seventeen+0.054
Marcus+0.053
Neg logit contributions
 about-0.045
 lived-0.043
adow-0.042
 today-0.041
 night-0.041