TOP ACTIVATIONS
MAX = 10.004

Cars didn 't fly to volcan oes . <|endoftext|> L ily
The book has pictures of volcan oes . Vol can oes
big book with pictures of volcan oes . Vol can oes
was a grand door . Bes ide the door , there
and listening . <|endoftext|> M omm a and Billy were walking
big book with pictures of volcan oes . Vol can oes
little girl all about how volcan oes work . She taught
not understand . They like volcan oes . They think they
They want to write about volcan oes . They
but foolish . The cat tipped the glass and water spilled
. They had enough of volcan oes for one day .
. Lily and Ben think volcan oes are cool . They
. Suddenly , John heard nos y footsteps behind them .
Tom cried . The shelf tipped over . More toys fell
their faces . <|endoftext|> M omm a and Ron ny were
knew to be careful around volcan oes . <|endoftext|> Once upon
go any higher . She tipped her hat to the clouds
not understand . They like volcan oes . They think they
They learned a lot about volcan oes . They thanked the
They want to write about volcan oes . They

MIN ACTIVATIONS
MIN = -9.263

and she was the happiest girl in town . She used
" You are the best twins ever ! I love you
. You 're my best girl . I 'll talk to
You are both my beautiful girls . Now , let 's
" You are the best twins ever !" she said .
pain ters and the best twins in the world ! I
! You are the best twins ever . This is very
and she was the happiest girl around ! <|endoftext|> One day
" You are the best twins ever . You are so
" You are such good twins . You are such good
" We are the best friends ever !" They were not
. You 're my sweet girl ." They hug and thank
. It was the happiest day ever ! <|endoftext|> Once upon
. You are my precious twins ." <|endoftext|> L ily and
toes made him the happiest boy in the world . <|endoftext|>
. You are our best girl ." Anna smiled
thinking it was the happiest day of all . Her mom
Honest friends are the best friends !". <|endoftext|> A little boy
You 're such a good girl , Lily ." Lily smiled
" This is the best day ever . We love these

INTERVAL 5.187 - 10.004
CONTAINS 0.697%

scared . But he could not stop shrinking . Tim got
and people . He did not hear his mom calling him
the TV . He can 't hurt you . You are
the house . Lily didn 't want to stop playing with
ly , but it could not win . In the end

INTERVAL 0.371 - 5.187
CONTAINS 38.927%

and waited , but the pie didn 't seem to cool
, they saw a big box in the living room .
Oh no ," Ben said . " We broke the window
the watch . But then , something bad happened
udd les and watch the rain drops fall .

INTERVAL -4.446 - 0.371
CONTAINS 59.400%

bit better . The rabbit kept walking and
right places . It was a rare thing that had never
, round rock . She put it up to her mouth
The spider replied , " I 'm thirsty . I need
always took care of each other . <|endoftext|> Once upon a

INTERVAL -9.263 - -4.446
CONTAINS 0.976%

special message for a special girl ." Anna thanked
leader of the band kept waving his arms and the band
, " What are you doing up there ?" Suddenly the
They had fun with their friends . But then
did not know what to do . They wanted to help
Token Cars
Token ID25277
Feature activation+1.59e+00

Pos logit contributions
mun+0.011
rob+0.010
 continuing+0.009
 enjoying+0.009
 riding+0.009
Neg logit contributions
eware-0.032
angs-0.029
ricanes-0.028
 nearer-0.028
 Knife-0.028
Token didn
Token ID1422
Feature activation+2.68e+00

Pos logit contributions
eware+0.060
angs+0.057
 nearer+0.056
 closer+0.055
 knob+0.055
Neg logit contributions
mun-0.048
rob-0.045
 couple-0.044
 And-0.044
oc-0.043
Token't
Token ID470
Feature activation+5.59e+00

Pos logit contributions
eware+0.097
angs+0.089
 nearer+0.084
 knob+0.081
ricanes+0.080
Neg logit contributions
mun-0.094
 enjoying-0.088
 couple-0.087
 pengu-0.086
 celebrating-0.085
Token fly
Token ID6129
Feature activation-1.79e-01

Pos logit contributions
eware+0.201
angs+0.188
 nearer+0.171
 prick+0.167
 closer+0.165
Neg logit contributions
mun-0.201
 And-0.192
rob-0.191
 continuing-0.186
Have-0.184
Token to
Token ID284
Feature activation+1.05e+00

Pos logit contributions
mun+0.006
 And+0.006
 riding+0.006
rob+0.006
 enjoying+0.006
Neg logit contributions
eware-0.006
angs-0.006
 nearer-0.006
 upwards-0.005
ricanes-0.005
Token volcan
Token ID17516
Feature activation+1.00e+01

Pos logit contributions
eware+0.035
angs+0.034
 nearer+0.033
 closer+0.032
 knob+0.032
Neg logit contributions
mun-0.040
 And-0.038
rob-0.037
 Have-0.035
 celebrating-0.034
Tokenoes
Token ID3028
Feature activation+2.96e+00

Pos logit contributions
eware+0.125
angs+0.098
ricanes+0.073
 nearer+0.071
isable+0.065
Neg logit contributions
mun-0.582
 And-0.571
 playing-0.569
 enjoying-0.567
 riding-0.566
Token.
Token ID13
Feature activation-4.81e-01

Pos logit contributions
eware+0.099
angs+0.096
 nearer+0.093
 closer+0.092
 upwards+0.090
Neg logit contributions
mun-0.108
rob-0.102
Che-0.099
 couple-0.098
 And-0.095
Token<|endoftext|>
Token ID50256
Feature activation+1.16e+00

Pos logit contributions
mun+0.010
rob+0.010
 continuing+0.009
 enjoying+0.008
 riding+0.008
Neg logit contributions
eware-0.026
angs-0.024
ricanes-0.023
 Knife-0.022
 nearer-0.022
TokenL
Token ID43
Feature activation+3.59e+00

Pos logit contributions
eware+0.038
angs+0.036
 iv+0.034
 nearer+0.034
 powder+0.033
Neg logit contributions
 sidelines-0.044
 wedding-0.039
 couple-0.039
 continuing-0.038
 congratulate-0.038
Tokenily
Token ID813
Feature activation+2.75e+00

Pos logit contributions
eware+0.119
angs+0.113
 knob+0.100
out+0.100
 nearer+0.100
Neg logit contributions
mun-0.136
 continuing-0.130
 enjoying-0.130
 And-0.129
 riding-0.128
Token The
Token ID383
Feature activation-5.01e-02

Pos logit contributions
eware+0.053
angs+0.051
ricanes+0.048
 nearer+0.048
isable+0.048
Neg logit contributions
 And-0.011
 playing-0.010
 having-0.009
 enjoying-0.009
 town-0.009
Token book
Token ID1492
Feature activation+1.46e+00

Pos logit contributions
mun+0.002
 And+0.002
 playing+0.002
 riding+0.002
 enjoying+0.002
Neg logit contributions
eware-0.002
angs-0.002
ricanes-0.001
 nearer-0.001
isable-0.001
Token has
Token ID468
Feature activation-5.23e-01

Pos logit contributions
eware+0.073
angs+0.068
 nearer+0.064
ricanes+0.064
isable+0.063
Neg logit contributions
 And-0.032
 playing-0.031
mun-0.031
 having-0.030
 riding-0.030
Token pictures
Token ID5986
Feature activation+2.12e+00

Pos logit contributions
 having+0.011
 riding+0.011
 playing+0.011
 And+0.011
 rh+0.010
Neg logit contributions
eware-0.026
angs-0.024
ricanes-0.024
 nearer-0.024
isable-0.024
Token of
Token ID286
Feature activation-1.56e+00

Pos logit contributions
eware+0.096
angs+0.091
ricanes+0.084
 nearer+0.084
 knob+0.084
Neg logit contributions
mun-0.056
 And-0.051
 enjoying-0.050
 playing-0.049
 continuing-0.049
Token volcan
Token ID17516
Feature activation+9.86e+00

Pos logit contributions
mun+0.059
oun+0.057
rob+0.056
 continuing+0.056
Che+0.054
Neg logit contributions
angs-0.048
eware-0.048
 knob-0.047
 cigarettes-0.045
 powder-0.045
Tokenoes
Token ID3028
Feature activation+2.54e+00

Pos logit contributions
eware+0.136
angs+0.104
 nearer+0.094
ricanes+0.087
isable+0.086
Neg logit contributions
mun-0.551
 And-0.548
 playing-0.545
 having-0.542
 riding-0.541
Token.
Token ID13
Feature activation+6.66e-01

Pos logit contributions
eware+0.112
angs+0.107
 knob+0.099
 nearer+0.098
 upwards+0.097
Neg logit contributions
mun-0.070
Che-0.061
rob-0.061
 And-0.061
 continuing-0.061
Token Vol
Token ID4709
Feature activation+7.01e-01

Pos logit contributions
eware+0.034
angs+0.033
 nearer+0.031
ricanes+0.030
isable+0.030
Neg logit contributions
 And-0.015
 playing-0.013
 having-0.013
 town-0.012
 enjoying-0.012
Tokencan
Token ID5171
Feature activation+4.11e+00

Pos logit contributions
eware+0.022
angs+0.020
ricanes+0.018
 nearer+0.018
 knob+0.018
Neg logit contributions
mun-0.028
 And-0.027
 playing-0.027
 enjoying-0.027
 riding-0.027
Tokenoes
Token ID3028
Feature activation+2.75e+00

Pos logit contributions
eware+0.143
angs+0.133
isable+0.124
ricanes+0.122
 nearer+0.122
Neg logit contributions
 And-0.143
mun-0.143
 playing-0.143
 having-0.142
 riding-0.141
Token big
Token ID1263
Feature activation+1.01e+00

Pos logit contributions
eware+0.040
angs+0.039
ricanes+0.035
 nearer+0.035
isable+0.034
Neg logit contributions
 playing-0.027
mun-0.026
 rh-0.026
 enjoying-0.026
 riding-0.026
Token book
Token ID1492
Feature activation+1.52e+00

Pos logit contributions
eware+0.035
angs+0.033
ricanes+0.030
 nearer+0.029
 upwards+0.029
Neg logit contributions
 playing-0.037
mun-0.036
 riding-0.036
 rh-0.036
 enjoying-0.036
Token with
Token ID351
Feature activation-5.97e-01

Pos logit contributions
eware+0.073
angs+0.069
 nearer+0.065
ricanes+0.065
isable+0.064
Neg logit contributions
 playing-0.035
 And-0.035
 riding-0.035
 having-0.034
 enjoying-0.033
Token pictures
Token ID5986
Feature activation+1.68e+00

Pos logit contributions
mun+0.020
 continuing+0.018
 And+0.018
 enjoying+0.018
rob+0.018
Neg logit contributions
eware-0.023
angs-0.022
 knob-0.020
 nearer-0.020
ricanes-0.020
Token of
Token ID286
Feature activation-1.60e+00

Pos logit contributions
eware+0.077
angs+0.073
ricanes+0.068
 nearer+0.067
 knob+0.067
Neg logit contributions
mun-0.043
 And-0.040
 enjoying-0.039
 playing-0.039
 riding-0.039
Token volcan
Token ID17516
Feature activation+9.54e+00

Pos logit contributions
mun+0.066
oun+0.065
 continuing+0.063
rob+0.061
�+0.061
Neg logit contributions
angs-0.043
 knob-0.043
eware-0.041
 cigarettes-0.041
 powder-0.040
Tokenoes
Token ID3028
Feature activation+2.17e+00

Pos logit contributions
eware+0.141
angs+0.108
 nearer+0.101
isable+0.096
ricanes+0.093
Neg logit contributions
mun-0.523
 And-0.519
 playing-0.516
 having-0.515
 riding-0.514
Token.
Token ID13
Feature activation+9.27e-01

Pos logit contributions
eware+0.101
angs+0.096
 nearer+0.090
ricanes+0.089
 knob+0.089
Neg logit contributions
mun-0.053
 And-0.049
 enjoying-0.048
 playing-0.048
 riding-0.048
Token Vol
Token ID4709
Feature activation+9.59e-01

Pos logit contributions
eware+0.050
angs+0.047
ricanes+0.045
 nearer+0.045
 upwards+0.045
Neg logit contributions
mun-0.016
 enjoying-0.014
 continuing-0.014
rob-0.014
 riding-0.014
Tokencan
Token ID5171
Feature activation+3.98e+00

Pos logit contributions
eware+0.030
angs+0.027
ricanes+0.025
 nearer+0.024
 knob+0.024
Neg logit contributions
mun-0.038
 And-0.037
 enjoying-0.037
 playing-0.037
 riding-0.036
Tokenoes
Token ID3028
Feature activation+2.74e+00

Pos logit contributions
eware+0.148
angs+0.138
ricanes+0.127
 nearer+0.126
isable+0.126
Neg logit contributions
mun-0.132
 And-0.129
 playing-0.128
 riding-0.127
 having-0.127
Token was
Token ID373
Feature activation-2.42e-01

Pos logit contributions
eware+0.024
 knob+0.024
 nearer+0.022
out+0.022
angs+0.022
Neg logit contributions
rob-0.021
 Have-0.019
mun-0.019
 sidelines-0.019
 rh-0.018
Token a
Token ID257
Feature activation+2.13e-02

Pos logit contributions
 playing+0.007
 enjoying+0.007
 having+0.007
 were+0.006
 And+0.006
Neg logit contributions
eware-0.011
angs-0.011
ricanes-0.010
leys-0.010
 upwards-0.009
Token grand
Token ID4490
Feature activation+3.72e-01

Pos logit contributions
eware+0.001
 knob+0.001
angs+0.001
 nearer+0.001
ricanes+0.001
Neg logit contributions
mun-0.001
rob-0.001
 And-0.001
 riding-0.001
 having-0.001
Token door
Token ID3420
Feature activation+2.90e+00

Pos logit contributions
eware+0.013
angs+0.012
 knob+0.012
 nearer+0.011
ricanes+0.011
Neg logit contributions
mun-0.013
 And-0.012
Che-0.012
Have-0.012
 having-0.012
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
eware+0.119
angs+0.112
ricanes+0.103
 nearer+0.103
 knob+0.101
Neg logit contributions
mun-0.086
 And-0.083
 playing-0.082
 enjoying-0.082
 riding-0.081
Token Bes
Token ID30837
Feature activation+9.34e+00

Pos logit contributions
eware+0.010
angs+0.010
ricanes+0.009
 knob+0.009
 nearer+0.009
Neg logit contributions
mun-0.006
rob-0.006
 riding-0.006
 playing-0.006
 enjoying-0.006
Tokenide
Token ID485
Feature activation+3.98e-01

Pos logit contributions
eware+0.379
angs+0.354
ricanes+0.329
 nearer+0.325
 knob+0.320
Neg logit contributions
mun-0.282
 And-0.273
 enjoying-0.269
 playing-0.268
 riding-0.268
Token the
Token ID262
Feature activation-4.01e-01

Pos logit contributions
eware+0.015
angs+0.014
ricanes+0.013
 nearer+0.013
 knob+0.013
Neg logit contributions
mun-0.013
 And-0.013
 playing-0.012
 enjoying-0.012
 riding-0.012
Token door
Token ID3420
Feature activation+3.44e+00

Pos logit contributions
 town+0.015
 playing+0.014
 couple+0.014
 having+0.014
 enjoying+0.014
Neg logit contributions
angs-0.014
eware-0.013
ricanes-0.012
 Knife-0.012
isable-0.012
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
eware+0.159
angs+0.152
ricanes+0.141
 nearer+0.139
isable+0.138
Neg logit contributions
mun-0.083
 And-0.081
 playing-0.080
 enjoying-0.079
 riding-0.079
Token there
Token ID612
Feature activation+4.80e-01

Pos logit contributions
eware+0.038
angs+0.034
 knob+0.034
 nearer+0.034
ricanes+0.033
Neg logit contributions
mun-0.034
rob-0.033
 And-0.032
Che-0.032
 riding-0.031
Token and
Token ID290
Feature activation+2.02e+00

Pos logit contributions
eware+0.087
angs+0.080
 knob+0.080
 nearer+0.078
 closer+0.077
Neg logit contributions
rob-0.071
mun-0.071
oc-0.063
Che-0.063
 And-0.063
Token listening
Token ID8680
Feature activation+8.13e-01

Pos logit contributions
eware+0.082
angs+0.076
 nearer+0.073
ricanes+0.072
 knob+0.071
Neg logit contributions
mun-0.058
 And-0.055
rob-0.055
Che-0.054
 continuing-0.053
Token.
Token ID13
Feature activation+7.67e-01

Pos logit contributions
eware+0.032
angs+0.030
ricanes+0.028
 nearer+0.028
isable+0.027
Neg logit contributions
mun-0.025
 And-0.025
 playing-0.024
 enjoying-0.024
 riding-0.024
Token<|endoftext|>
Token ID50256
Feature activation+1.82e+00

Pos logit contributions
eware+0.035
angs+0.032
ricanes+0.031
 Knife+0.031
 upwards+0.030
Neg logit contributions
mun-0.019
rob-0.019
 enjoying-0.017
 continuing-0.016
 riding-0.016
TokenM
Token ID44
Feature activation+7.17e+00

Pos logit contributions
eware+0.076
angs+0.071
nob+0.069
 nearer+0.068
piece+0.065
Neg logit contributions
 sidelines-0.052
mun-0.050
 wedding-0.048
 couple-0.048
Che-0.048
Tokenomm
Token ID2002
Feature activation+9.34e+00

Pos logit contributions
eware+0.180
angs+0.165
 knob+0.157
right+0.147
outed+0.146
Neg logit contributions
mun-0.322
rob-0.310
 having-0.305
 enjoying-0.300
Have-0.300
Tokena
Token ID64
Feature activation+2.54e+00

Pos logit contributions
eware+0.250
angs+0.243
out+0.220
ups+0.206
outed+0.205
Neg logit contributions
 Have-0.402
 continuing-0.395
 riding-0.393
Have-0.392
 And-0.391
Token and
Token ID290
Feature activation+2.25e+00

Pos logit contributions
eware+0.088
angs+0.080
out+0.080
 knob+0.076
pot+0.075
Neg logit contributions
mun-0.082
Che-0.079
Have-0.079
rob-0.079
 continuing-0.078
Token Billy
Token ID15890
Feature activation+2.72e+00

Pos logit contributions
eware+0.076
angs+0.069
 nearer+0.069
 closer+0.067
ricanes+0.066
Neg logit contributions
mun-0.078
rob-0.077
oc-0.076
 And-0.075
Che-0.074
Token were
Token ID547
Feature activation-6.24e-01

Pos logit contributions
 locked+0.080
eware+0.075
angs+0.074
 closer+0.071
 shook+0.070
Neg logit contributions
 sidelines-0.098
rob-0.096
 couple-0.095
 Have-0.094
 importantly-0.094
Token walking
Token ID6155
Feature activation-8.16e-01

Pos logit contributions
rob+0.014
oc+0.014
Che+0.014
Have+0.013
mun+0.013
Neg logit contributions
angs-0.028
out-0.028
 ok-0.028
outed-0.027
eware-0.027
Token big
Token ID1263
Feature activation+6.80e-01

Pos logit contributions
eware+0.027
angs+0.026
ricanes+0.024
 nearer+0.023
isable+0.023
Neg logit contributions
 playing-0.018
 rh-0.017
mun-0.017
 enjoying-0.017
 pengu-0.017
Token book
Token ID1492
Feature activation+1.26e+00

Pos logit contributions
eware+0.024
angs+0.022
ricanes+0.020
 nearer+0.020
 upwards+0.019
Neg logit contributions
 playing-0.025
mun-0.024
 riding-0.024
 rh-0.024
 enjoying-0.024
Token with
Token ID351
Feature activation-9.34e-01

Pos logit contributions
eware+0.060
angs+0.058
 nearer+0.054
ricanes+0.054
isable+0.053
Neg logit contributions
 playing-0.029
 And-0.029
 riding-0.029
 having-0.029
 enjoying-0.027
Token pictures
Token ID5986
Feature activation+1.39e+00

Pos logit contributions
mun+0.030
 And+0.027
 continuing+0.027
 enjoying+0.027
rob+0.027
Neg logit contributions
eware-0.037
angs-0.036
 knob-0.032
 nearer-0.032
ricanes-0.032
Token of
Token ID286
Feature activation-1.93e+00

Pos logit contributions
eware+0.064
angs+0.060
ricanes+0.056
 nearer+0.056
 knob+0.055
Neg logit contributions
mun-0.035
 And-0.033
 enjoying-0.032
 playing-0.032
 riding-0.032
Token volcan
Token ID17516
Feature activation+9.21e+00

Pos logit contributions
mun+0.079
oun+0.078
 continuing+0.076
rob+0.074
�+0.073
Neg logit contributions
angs-0.053
 knob-0.052
eware-0.051
 cigarettes-0.050
 powder-0.050
Tokenoes
Token ID3028
Feature activation+1.89e+00

Pos logit contributions
eware+0.131
angs+0.100
 nearer+0.091
isable+0.086
ricanes+0.085
Neg logit contributions
mun-0.511
 And-0.507
 playing-0.503
 having-0.502
 riding-0.501
Token.
Token ID13
Feature activation+5.89e-01

Pos logit contributions
eware+0.086
angs+0.082
 nearer+0.076
ricanes+0.076
 knob+0.076
Neg logit contributions
mun-0.048
 And-0.044
 enjoying-0.043
 playing-0.042
 riding-0.042
Token Vol
Token ID4709
Feature activation+7.34e-01

Pos logit contributions
eware+0.031
angs+0.030
ricanes+0.028
 nearer+0.028
 upwards+0.028
Neg logit contributions
mun-0.011
 enjoying-0.009
 continuing-0.009
rob-0.009
 playing-0.009
Tokencan
Token ID5171
Feature activation+3.88e+00

Pos logit contributions
eware+0.023
angs+0.021
ricanes+0.019
 nearer+0.019
 knob+0.018
Neg logit contributions
mun-0.029
 And-0.028
 enjoying-0.028
 playing-0.028
 riding-0.028
Tokenoes
Token ID3028
Feature activation+2.72e+00

Pos logit contributions
eware+0.150
angs+0.141
ricanes+0.130
isable+0.129
 nearer+0.129
Neg logit contributions
mun-0.123
 And-0.120
 playing-0.119
 having-0.118
 riding-0.118
Token little
Token ID1310
Feature activation-1.74e+00

Pos logit contributions
mun+0.002
 And+0.002
 playing+0.002
 enjoying+0.002
 riding+0.002
Neg logit contributions
eware-0.004
angs-0.003
ricanes-0.003
 nearer-0.003
isable-0.003
Token girl
Token ID2576
Feature activation-3.87e+00

Pos logit contributions
 pengu+0.022
 town+0.019
 And+0.018
 couple+0.018
 playing+0.017
Neg logit contributions
eware-0.104
angs-0.103
ricanes-0.097
leys-0.095
iqu-0.094
Token all
Token ID477
Feature activation+2.10e+00

Pos logit contributions
 playing+0.130
 And+0.127
 having+0.126
 enjoying+0.123
 riding+0.122
Neg logit contributions
eware-0.152
angs-0.140
isable-0.131
ricanes-0.131
 nearer-0.127
Token about
Token ID546
Feature activation-5.18e-01

Pos logit contributions
eware+0.094
angs+0.089
ricanes+0.082
 nearer+0.082
isable+0.081
Neg logit contributions
mun-0.056
 And-0.054
 playing-0.053
 enjoying-0.053
 having-0.052
Token how
Token ID703
Feature activation-4.98e-01

Pos logit contributions
mun+0.015
 And+0.014
 enjoying+0.013
 riding+0.013
 playing+0.013
Neg logit contributions
eware-0.022
angs-0.021
 nearer-0.020
ricanes-0.020
 knob-0.019
Token volcan
Token ID17516
Feature activation+9.03e+00

Pos logit contributions
mun+0.014
 playing+0.014
 And+0.014
 enjoying+0.014
 having+0.013
Neg logit contributions
eware-0.021
angs-0.020
ricanes-0.018
isable-0.018
 nearer-0.018
Tokenoes
Token ID3028
Feature activation+1.68e+00

Pos logit contributions
eware+0.144
angs+0.122
ricanes+0.096
 nearer+0.094
 knob+0.089
Neg logit contributions
mun-0.496
 And-0.484
 playing-0.481
 enjoying-0.481
 riding-0.479
Token work
Token ID670
Feature activation-1.39e+00

Pos logit contributions
eware+0.063
angs+0.060
 nearer+0.057
 knob+0.056
 upwards+0.054
Neg logit contributions
mun-0.054
rob-0.053
 And-0.051
Che-0.050
 couple-0.050
Token.
Token ID13
Feature activation+8.85e-01

Pos logit contributions
mun+0.036
 And+0.033
 enjoying+0.033
 riding+0.033
 playing+0.033
Neg logit contributions
eware-0.062
angs-0.059
 nearer-0.055
ricanes-0.055
 knob-0.054
Token She
Token ID1375
Feature activation-2.42e-01

Pos logit contributions
eware+0.041
angs+0.037
ricanes+0.037
 upwards+0.036
 knob+0.036
Neg logit contributions
rob-0.023
mun-0.023
 riding-0.021
 enjoying-0.020
 continuing-0.020
Token taught
Token ID7817
Feature activation+4.11e-01

Pos logit contributions
mun+0.007
 And+0.007
 playing+0.007
 enjoying+0.007
 having+0.006
Neg logit contributions
eware-0.011
angs-0.010
ricanes-0.009
 upwards-0.009
isable-0.009
Token not
Token ID407
Feature activation+5.72e+00

Pos logit contributions
mun+0.170
rob+0.169
 rh+0.168
 pengu+0.166
oc+0.162
Neg logit contributions
eware-0.056
angs-0.047
 nearer-0.045
ricanes-0.043
out-0.043
Token understand
Token ID1833
Feature activation-1.17e+00

Pos logit contributions
eware+0.266
angs+0.252
ricanes+0.239
iqu+0.237
isable+0.237
Neg logit contributions
 And-0.135
 having-0.130
 playing-0.129
mun-0.129
 enjoying-0.126
Token.
Token ID13
Feature activation-4.23e-01

Pos logit contributions
 playing+0.020
 And+0.019
 having+0.018
mun+0.018
 enjoying+0.017
Neg logit contributions
eware-0.067
angs-0.062
ricanes-0.059
 nearer-0.058
isable-0.058
Token They
Token ID1119
Feature activation-2.45e+00

Pos logit contributions
mun+0.005
rob+0.004
 riding+0.004
 enjoying+0.004
 playing+0.004
Neg logit contributions
eware-0.026
angs-0.024
ricanes-0.023
 knob-0.023
 nearer-0.023
Token like
Token ID588
Feature activation-2.81e+00

Pos logit contributions
mun+0.062
 And+0.059
 playing+0.057
 enjoying+0.057
 riding+0.057
Neg logit contributions
eware-0.113
angs-0.107
ricanes-0.099
 nearer-0.099
 knob-0.097
Token volcan
Token ID17516
Feature activation+9.00e+00

Pos logit contributions
mun+0.080
 And+0.075
 enjoying+0.074
 riding+0.074
 playing+0.073
Neg logit contributions
eware-0.121
angs-0.114
ricanes-0.106
 nearer-0.105
 knob-0.104
Tokenoes
Token ID3028
Feature activation+2.00e+00

Pos logit contributions
eware+0.166
 nearer+0.131
angs+0.126
isable+0.124
ricanes+0.120
Neg logit contributions
mun-0.464
 And-0.458
 playing-0.455
 having-0.453
 enjoying-0.448
Token.
Token ID13
Feature activation-4.85e-01

Pos logit contributions
eware+0.074
angs+0.072
 knob+0.067
out+0.065
 upwards+0.064
Neg logit contributions
mun-0.063
rob-0.063
Che-0.062
 couple-0.060
 Evan-0.059
Token They
Token ID1119
Feature activation-2.62e+00

Pos logit contributions
mun+0.005
 riding+0.004
 enjoying+0.004
rob+0.004
 playing+0.004
Neg logit contributions
eware-0.030
angs-0.028
ricanes-0.027
 nearer-0.027
 knob-0.027
Token think
Token ID892
Feature activation+2.09e+00

Pos logit contributions
mun+0.070
 And+0.067
 playing+0.066
 enjoying+0.066
 having+0.065
Neg logit contributions
eware-0.116
angs-0.109
ricanes-0.101
 nearer-0.101
 upwards-0.099
Token they
Token ID484
Feature activation-1.99e+00

Pos logit contributions
eware+0.104
angs+0.097
isable+0.093
ricanes+0.091
 upwards+0.090
Neg logit contributions
 playing-0.046
 And-0.046
 having-0.045
 enjoying-0.044
mun-0.043
Token They
Token ID1119
Feature activation-2.32e+00

Pos logit contributions
eware+0.012
angs+0.011
ricanes+0.011
 nearer+0.011
 upwards+0.011
Neg logit contributions
mun-0.003
 riding-0.002
rob-0.002
 enjoying-0.002
 continuing-0.002
Token want
Token ID765
Feature activation+3.27e-01

Pos logit contributions
mun+0.071
 And+0.068
 riding+0.067
 enjoying+0.066
 playing+0.066
Neg logit contributions
eware-0.092
angs-0.087
ricanes-0.081
 nearer-0.081
 knob-0.081
Token to
Token ID284
Feature activation+1.47e+00

Pos logit contributions
eware+0.014
angs+0.013
isable+0.013
ricanes+0.012
rated+0.012
Neg logit contributions
 playing-0.010
 town-0.010
 having-0.010
 pengu-0.010
 enjoying-0.010
Token write
Token ID3551
Feature activation-1.28e+00

Pos logit contributions
eware+0.070
angs+0.066
 nearer+0.062
ricanes+0.062
 knob+0.061
Neg logit contributions
mun-0.035
 And-0.032
 enjoying-0.032
 playing-0.032
 riding-0.032
Token about
Token ID546
Feature activation-1.21e+00

Pos logit contributions
 playing+0.031
 And+0.031
 having+0.030
 enjoying+0.029
 riding+0.028
Neg logit contributions
eware-0.063
angs-0.059
ricanes-0.056
isable-0.055
iqu-0.055
Token volcan
Token ID17516
Feature activation+8.89e+00

Pos logit contributions
mun+0.037
rob+0.034
 And+0.034
Che+0.033
 enjoying+0.033
Neg logit contributions
eware-0.048
angs-0.046
 nearer-0.044
 knob-0.044
ricanes-0.043
Tokenoes
Token ID3028
Feature activation+1.94e+00

Pos logit contributions
eware+0.123
angs+0.096
 nearer+0.082
ricanes+0.080
isable+0.079
Neg logit contributions
mun-0.499
 And-0.494
 playing-0.491
 having-0.489
 riding-0.488
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
eware+0.083
angs+0.080
 nearer+0.075
 knob+0.074
 upwards+0.073
Neg logit contributions
mun-0.054
 And-0.048
Che-0.048
rob-0.048
 riding-0.048
Token
Token ID198
Feature activation-4.90e-01

Pos logit contributions
eware+0.012
angs+0.011
ricanes+0.011
 nearer+0.011
 upwards+0.011
Neg logit contributions
mun-0.002
 riding-0.001
 enjoying-0.001
 playing-0.001
 continuing-0.001
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
mun+0.011
 rh+0.011
rob+0.011
 celebrating+0.010
 wedding+0.010
Neg logit contributions
eware-0.023
 nearer-0.021
 closer-0.021
angs-0.020
out-0.020
TokenThey
Token ID2990
Feature activation-2.01e+00

Pos logit contributions
mun+0.008
 And+0.008
Che+0.008
 playing+0.008
Have+0.008
Neg logit contributions
eware-0.016
angs-0.016
 nearer-0.014
ricanes-0.014
 upwards-0.014
Token but
Token ID475
Feature activation+2.18e+00

Pos logit contributions
eware+0.027
 nearer+0.025
angs+0.025
 knob+0.024
 closer+0.024
Neg logit contributions
mun-0.028
rob-0.027
Che-0.025
oun-0.025
 And-0.025
Token foolish
Token ID19538
Feature activation+2.33e+00

Pos logit contributions
eware+0.113
angs+0.108
ricanes+0.101
 nearer+0.099
isable+0.098
Neg logit contributions
mun-0.043
 playing-0.041
 enjoying-0.041
 And-0.041
 having-0.041
Token.
Token ID13
Feature activation+4.07e-01

Pos logit contributions
eware+0.095
angs+0.089
 knob+0.081
 nearer+0.078
out+0.077
Neg logit contributions
mun-0.077
Che-0.072
rob-0.072
Have-0.069
 continuing-0.068
Token The
Token ID383
Feature activation-1.54e-01

Pos logit contributions
eware+0.020
angs+0.018
 Knife+0.018
ricanes+0.017
right+0.017
Neg logit contributions
mun-0.010
rob-0.010
 enjoying-0.009
 continuing-0.009
 celebrating-0.009
Token cat
Token ID3797
Feature activation-1.33e-01

Pos logit contributions
mun+0.005
rob+0.005
 And+0.005
 enjoying+0.005
 riding+0.005
Neg logit contributions
eware-0.006
angs-0.005
 knob-0.005
ricanes-0.005
 nearer-0.005
Token tipped
Token ID28395
Feature activation+8.88e+00

Pos logit contributions
mun+0.003
 playing+0.003
 enjoying+0.003
 And+0.003
 having+0.003
Neg logit contributions
eware-0.006
angs-0.006
ricanes-0.006
 nearer-0.006
 upwards-0.005
Token the
Token ID262
Feature activation+6.18e-01

Pos logit contributions
eware+0.431
angs+0.390
ricanes+0.388
iqu+0.373
iders+0.370
Neg logit contributions
 playing-0.261
 having-0.255
 riding-0.244
 enjoying-0.238
-0.234
Token glass
Token ID5405
Feature activation+3.24e+00

Pos logit contributions
eware+0.019
angs+0.017
ricanes+0.016
 nearer+0.015
isable+0.015
Neg logit contributions
mun-0.025
 And-0.025
 playing-0.024
 enjoying-0.024
 having-0.024
Token and
Token ID290
Feature activation+1.44e+00

Pos logit contributions
eware+0.166
ricanes+0.156
iqu+0.152
angs+0.152
ffic+0.150
Neg logit contributions
 were-0.067
 playing-0.066
 happily-0.065
 enjoying-0.064
 And-0.064
Token water
Token ID1660
Feature activation+2.78e+00

Pos logit contributions
eware+0.063
angs+0.060
ricanes+0.055
iddle+0.054
 upwards+0.053
Neg logit contributions
 playing-0.043
 enjoying-0.043
 having-0.042
 continuing-0.041
mun-0.040
Token spilled
Token ID31896
Feature activation+2.51e+00

Pos logit contributions
eware+0.113
angs+0.105
ricanes+0.099
 nearer+0.096
isable+0.096
Neg logit contributions
mun-0.084
 playing-0.083
 enjoying-0.082
 having-0.081
 And-0.081
Token.
Token ID13
Feature activation-4.77e-01

Pos logit contributions
eware+0.009
angs+0.009
ricanes+0.008
 nearer+0.008
isable+0.008
Neg logit contributions
mun-0.005
 And-0.005
 playing-0.005
 enjoying-0.005
 riding-0.005
Token They
Token ID1119
Feature activation-2.65e+00

Pos logit contributions
mun+0.012
rob+0.011
 continuing+0.010
 enjoying+0.010
 riding+0.010
Neg logit contributions
eware-0.023
angs-0.022
 Knife-0.021
ricanes-0.020
right-0.020
Token had
Token ID550
Feature activation-9.39e-01

Pos logit contributions
mun+0.081
 And+0.078
 playing+0.077
 enjoying+0.077
 riding+0.077
Neg logit contributions
eware-0.107
angs-0.101
ricanes-0.093
 nearer-0.093
 knob-0.091
Token enough
Token ID1576
Feature activation-1.21e+00

Pos logit contributions
 playing+0.034
 having+0.033
 enjoying+0.033
 riding+0.032
mun+0.032
Neg logit contributions
eware-0.034
angs-0.032
ricanes-0.030
 nearer-0.029
 knob-0.029
Token of
Token ID286
Feature activation-2.01e+00

Pos logit contributions
mun+0.041
 And+0.038
Che+0.038
 continuing+0.038
 enjoying+0.037
Neg logit contributions
eware-0.045
angs-0.043
 nearer-0.039
 knob-0.039
ricanes-0.039
Token volcan
Token ID17516
Feature activation+8.87e+00

Pos logit contributions
mun+0.067
oun+0.061
 And+0.061
rob+0.061
oc+0.061
Neg logit contributions
 nearer-0.071
angs-0.071
eware-0.071
 closer-0.069
 knob-0.068
Tokenoes
Token ID3028
Feature activation+2.24e+00

Pos logit contributions
eware+0.119
angs+0.093
 nearer+0.078
ricanes+0.075
isable+0.075
Neg logit contributions
mun-0.501
 And-0.493
 playing-0.491
 enjoying-0.490
 having-0.489
Token for
Token ID329
Feature activation-2.12e+00

Pos logit contributions
eware+0.089
angs+0.084
 nearer+0.078
 upwards+0.076
out+0.076
Neg logit contributions
mun-0.070
rob-0.065
Che-0.065
 And-0.064
 continuing-0.063
Token one
Token ID530
Feature activation+2.98e+00

Pos logit contributions
mun+0.080
rob+0.076
oun+0.071
oc+0.069
 And+0.068
Neg logit contributions
eware-0.073
angs-0.069
 nearer-0.068
 knob-0.068
 closer-0.065
Token day
Token ID1110
Feature activation-5.76e+00

Pos logit contributions
eware+0.129
angs+0.122
 nearer+0.113
ricanes+0.113
 knob+0.112
Neg logit contributions
mun-0.083
 And-0.078
 enjoying-0.077
 playing-0.077
 riding-0.077
Token.
Token ID13
Feature activation-5.96e-01

Pos logit contributions
mun+0.180
rob+0.169
Che+0.158
Have+0.155
 rh+0.154
Neg logit contributions
eware-0.237
angs-0.223
out-0.208
 knob-0.206
 nearer-0.205
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
eware+0.142
angs+0.140
 knob+0.127
 nearer+0.124
 upwards+0.124
Neg logit contributions
mun-0.107
rob-0.098
Che-0.097
 continuing-0.094
 And-0.093
Token Lily
Token ID20037
Feature activation-1.55e-01

Pos logit contributions
eware+0.009
angs+0.008
ricanes+0.008
 nearer+0.008
 knob+0.008
Neg logit contributions
mun-0.005
 enjoying-0.005
 riding-0.005
 playing-0.005
 continuing-0.005
Token and
Token ID290
Feature activation+8.63e-02

Pos logit contributions
 And+0.003
mun+0.003
 playing+0.003
 enjoying+0.003
 having+0.003
Neg logit contributions
eware-0.008
angs-0.008
 nearer-0.007
ricanes-0.007
isable-0.007
Token Ben
Token ID3932
Feature activation-9.03e-01

Pos logit contributions
eware+0.004
angs+0.004
 nearer+0.004
ricanes+0.004
isable+0.004
Neg logit contributions
 playing-0.002
mun-0.002
 enjoying-0.002
 And-0.002
 having-0.002
Token think
Token ID892
Feature activation+1.99e+00

Pos logit contributions
mun+0.031
rob+0.030
 riding+0.029
 continuing+0.028
 And+0.028
Neg logit contributions
eware-0.032
angs-0.031
 knob-0.030
 nearer-0.029
ricanes-0.029
Token volcan
Token ID17516
Feature activation+8.76e+00

Pos logit contributions
eware+0.080
angs+0.076
 knob+0.072
 nearer+0.070
ricanes+0.070
Neg logit contributions
mun-0.063
rob-0.057
Che-0.057
 continuing-0.056
 And-0.055
Tokenoes
Token ID3028
Feature activation+2.07e+00

Pos logit contributions
eware+0.184
isable+0.158
 nearer+0.156
angs+0.144
ricanes+0.140
Neg logit contributions
 And-0.419
 having-0.410
mun-0.408
 playing-0.407
 were-0.403
Token are
Token ID389
Feature activation-2.74e+00

Pos logit contributions
eware+0.089
angs+0.087
 knob+0.081
 nearer+0.080
 upwards+0.079
Neg logit contributions
mun-0.056
rob-0.054
 couple-0.052
Che-0.051
 continuing-0.050
Token cool
Token ID3608
Feature activation-2.16e-01

Pos logit contributions
mun+0.089
 And+0.085
 playing+0.084
 enjoying+0.084
 riding+0.084
Neg logit contributions
eware-0.106
angs-0.099
ricanes-0.091
 nearer-0.091
 knob-0.089
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
mun+0.006
Che+0.005
rob+0.005
 And+0.005
 continuing+0.005
Neg logit contributions
eware-0.010
angs-0.009
 nearer-0.008
 knob-0.008
 upwards-0.008
Token They
Token ID1119
Feature activation-2.32e+00

Pos logit contributions
eware+0.012
angs+0.011
ricanes+0.011
 nearer+0.011
 upwards+0.011
Neg logit contributions
mun-0.003
 riding-0.002
rob-0.002
 enjoying-0.002
 continuing-0.002
Token.
Token ID13
Feature activation+5.35e-01

Pos logit contributions
rob+0.221
mun+0.211
Che+0.192
 rh+0.191
Have+0.191
Neg logit contributions
eware-0.212
angs-0.209
 closer-0.202
out-0.200
 upwards-0.200
Token Suddenly
Token ID24975
Feature activation+3.32e-01

Pos logit contributions
eware+0.027
angs+0.025
ricanes+0.024
 nearer+0.024
 knob+0.023
Neg logit contributions
mun-0.011
 And-0.010
 enjoying-0.010
 playing-0.010
 riding-0.010
Token,
Token ID11
Feature activation+1.04e+00

Pos logit contributions
angs+0.019
eware+0.018
isable+0.017
ricanes+0.017
iddle+0.017
Neg logit contributions
 playing-0.005
 riding-0.005
 town-0.005
 were-0.005
 And-0.005
Token John
Token ID1757
Feature activation+1.59e-01

Pos logit contributions
eware+0.054
angs+0.053
ricanes+0.048
isable+0.048
 Knife+0.047
Neg logit contributions
 playing-0.021
 having-0.020
 enjoying-0.020
mun-0.020
 riding-0.020
Token heard
Token ID2982
Feature activation+3.65e+00

Pos logit contributions
eware+0.006
angs+0.005
 nearer+0.005
 knob+0.005
ricanes+0.005
Neg logit contributions
mun-0.006
 And-0.005
rob-0.005
 riding-0.005
 enjoying-0.005
Token nos
Token ID43630
Feature activation+8.75e+00

Pos logit contributions
eware+0.147
angs+0.137
ricanes+0.128
isable+0.125
 nearer+0.125
Neg logit contributions
mun-0.110
 playing-0.110
 And-0.109
 riding-0.108
 having-0.107
Tokeny
Token ID88
Feature activation-1.74e-01

Pos logit contributions
eware+0.261
angs+0.241
ricanes+0.213
 nearer+0.213
 knob+0.207
Neg logit contributions
mun-0.360
 And-0.349
 enjoying-0.345
 playing-0.344
 riding-0.343
Token footsteps
Token ID27146
Feature activation+4.12e-01

Pos logit contributions
rob+0.007
mun+0.006
 Have+0.006
Che+0.006
oun+0.006
Neg logit contributions
eware-0.006
angs-0.006
 nearer-0.006
 closer-0.005
 knob-0.005
Token behind
Token ID2157
Feature activation+9.21e-01

Pos logit contributions
eware+0.014
angs+0.014
 nearer+0.014
 knob+0.013
 closer+0.013
Neg logit contributions
mun-0.014
 And-0.014
rob-0.014
 Have-0.014
Che-0.013
Token them
Token ID606
Feature activation+1.79e+00

Pos logit contributions
angs+0.037
 nearer+0.036
 knob+0.036
eware+0.035
 upwards+0.034
Neg logit contributions
mun-0.028
rob-0.026
Che-0.026
 And-0.025
oun-0.025
Token.
Token ID13
Feature activation+7.40e-01

Pos logit contributions
angs+0.058
eware+0.058
 closer+0.055
 knob+0.054
 nearer+0.054
Neg logit contributions
rob-0.072
mun-0.070
Che-0.064
 Have-0.060
 couple-0.059
Token Tom
Token ID4186
Feature activation+5.09e-01

Pos logit contributions
eware+0.062
angs+0.058
ricanes+0.056
 Knife+0.056
 nearer+0.055
Neg logit contributions
mun-0.032
rob-0.030
 enjoying-0.028
 celebrating-0.026
 continuing-0.026
Token cried
Token ID16896
Feature activation+2.70e+00

Pos logit contributions
eware+0.018
angs+0.018
isable+0.016
 nearer+0.016
ricanes+0.016
Neg logit contributions
mun-0.016
rob-0.015
 continuing-0.015
 celebrating-0.015
Che-0.015
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
eware+0.108
angs+0.102
 nearer+0.094
ricanes+0.094
 knob+0.092
Neg logit contributions
mun-0.084
 And-0.080
 enjoying-0.079
 playing-0.079
 riding-0.079
Token The
Token ID383
Feature activation+4.42e-01

Pos logit contributions
eware+0.054
angs+0.051
ricanes+0.048
 nearer+0.048
 Knife+0.048
Neg logit contributions
mun-0.022
 enjoying-0.019
rob-0.019
 celebrating-0.018
 continuing-0.018
Token shelf
Token ID18316
Feature activation+6.58e-01

Pos logit contributions
eware+0.018
angs+0.016
ricanes+0.015
 nearer+0.015
isable+0.015
Neg logit contributions
mun-0.014
 And-0.013
 playing-0.013
 enjoying-0.013
 riding-0.013
Token tipped
Token ID28395
Feature activation+8.74e+00

Pos logit contributions
eware+0.033
angs+0.032
ricanes+0.030
 nearer+0.030
 upwards+0.030
Neg logit contributions
mun-0.014
 were-0.013
 playing-0.013
 And-0.013
 riding-0.012
Token over
Token ID625
Feature activation+2.57e+00

Pos logit contributions
eware+0.273
angs+0.241
ricanes+0.233
iqu+0.226
isable+0.216
Neg logit contributions
 playing-0.360
 having-0.360
 riding-0.353
 town-0.345
 And-0.343
Token.
Token ID13
Feature activation+3.50e-01

Pos logit contributions
eware+0.117
angs+0.112
 nearer+0.105
 knob+0.105
ricanes+0.102
Neg logit contributions
mun-0.067
 And-0.061
 enjoying-0.059
rob-0.059
 riding-0.058
Token More
Token ID3125
Feature activation+1.44e+00

Pos logit contributions
eware+0.017
angs+0.016
ricanes+0.015
 nearer+0.015
 knob+0.015
Neg logit contributions
mun-0.008
 enjoying-0.007
 playing-0.007
 continuing-0.007
 riding-0.007
Token toys
Token ID14958
Feature activation-1.45e+00

Pos logit contributions
eware+0.048
angs+0.047
 knob+0.046
 cigarettes+0.042
out+0.042
Neg logit contributions
mun-0.055
rob-0.053
Che-0.051
 continuing-0.050
Have-0.049
Token fell
Token ID3214
Feature activation+3.48e+00

Pos logit contributions
mun+0.055
rob+0.052
oc+0.050
Che+0.050
 And+0.048
Neg logit contributions
eware-0.049
angs-0.046
 locked-0.045
 knob-0.044
out-0.043
Token their
Token ID511
Feature activation-3.45e-01

Pos logit contributions
mun+0.072
rob+0.069
Have+0.059
Che+0.057
 rh+0.057
Neg logit contributions
eware-0.075
out-0.074
 firmly-0.073
 knob-0.073
 upwards-0.072
Token faces
Token ID6698
Feature activation-1.45e+00

Pos logit contributions
mun+0.013
rob+0.012
Che+0.012
 And+0.011
 Evan+0.011
Neg logit contributions
eware-0.012
 knob-0.011
angs-0.011
 upwards-0.010
 nearer-0.010
Token.
Token ID13
Feature activation-6.96e-01

Pos logit contributions
mun+0.048
rob+0.045
 rh+0.042
Che+0.041
oc+0.041
Neg logit contributions
eware-0.055
angs-0.053
 upwards-0.051
 nearer-0.050
 knob-0.050
Token<|endoftext|>
Token ID50256
Feature activation+1.01e+00

Pos logit contributions
mun+0.018
 pengu+0.016
 wedding+0.016
rob+0.016
 gor+0.015
Neg logit contributions
eware-0.031
ricanes-0.030
 upwards-0.028
angs-0.028
 ok-0.028
TokenM
Token ID44
Feature activation+6.22e+00

Pos logit contributions
eware+0.035
 nearer+0.032
nob+0.031
angs+0.031
 upwards+0.030
Neg logit contributions
 sidelines-0.035
 wedding-0.034
mun-0.032
Che-0.032
 rh-0.031
Tokenomm
Token ID2002
Feature activation+8.72e+00

Pos logit contributions
eware+0.155
angs+0.138
outed+0.131
 knob+0.129
ricanes+0.127
Neg logit contributions
mun-0.285
rob-0.271
 enjoying-0.267
 having-0.267
 continuing-0.263
Tokena
Token ID64
Feature activation+1.14e+00

Pos logit contributions
eware+0.286
angs+0.267
ricanes+0.239
 nearer+0.238
 knob+0.234
Neg logit contributions
mun-0.330
 And-0.321
 riding-0.318
 enjoying-0.317
 playing-0.317
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
eware+0.045
angs+0.041
 knob+0.040
out+0.039
ricanes+0.039
Neg logit contributions
mun-0.034
rob-0.031
Che-0.031
Have-0.031
 having-0.031
Token Ron
Token ID6575
Feature activation+2.98e+00

Pos logit contributions
eware+0.073
angs+0.068
 knob+0.065
ricanes+0.064
 nearer+0.063
Neg logit contributions
mun-0.069
rob-0.067
 continuing-0.064
Che-0.064
Have-0.063
Tokenny
Token ID3281
Feature activation-7.92e-01

Pos logit contributions
eware+0.109
piece+0.108
 knob+0.106
ered+0.106
 locked+0.106
Neg logit contributions
rob-0.087
mun-0.086
 riding-0.084
 celebrating-0.084
 importantly-0.083
Token were
Token ID547
Feature activation-9.47e-01

Pos logit contributions
rob+0.024
 sidelines+0.023
mun+0.023
Che+0.022
 continuing+0.022
Neg logit contributions
eware-0.029
 locked-0.027
 knob-0.026
angs-0.026
out-0.025
Token knew
Token ID2993
Feature activation+1.30e+00

Pos logit contributions
eware+0.011
angs+0.011
 locked+0.011
out+0.010
 knob+0.010
Neg logit contributions
 sidelines-0.009
rob-0.009
mun-0.008
Have-0.008
 Whe-0.008
Token to
Token ID284
Feature activation+8.30e-01

Pos logit contributions
eware+0.057
angs+0.053
 nearer+0.051
ricanes+0.050
 knob+0.050
Neg logit contributions
mun-0.036
 And-0.033
rob-0.032
Che-0.032
 enjoying-0.032
Token be
Token ID307
Feature activation-1.13e+00

Pos logit contributions
eware+0.035
angs+0.033
ricanes+0.031
 nearer+0.031
 knob+0.030
Neg logit contributions
mun-0.024
 And-0.022
 playing-0.022
 enjoying-0.022
 riding-0.022
Token careful
Token ID8161
Feature activation+1.33e+00

Pos logit contributions
 playing+0.039
mun+0.038
 enjoying+0.038
 having+0.038
 riding+0.038
Neg logit contributions
eware-0.043
angs-0.040
ricanes-0.036
 knob-0.035
isable-0.035
Token around
Token ID1088
Feature activation-1.68e+00

Pos logit contributions
eware+0.056
angs+0.053
ricanes+0.049
 nearer+0.049
 knob+0.048
Neg logit contributions
mun-0.038
 And-0.036
 enjoying-0.036
 playing-0.036
 riding-0.035
Token volcan
Token ID17516
Feature activation+8.71e+00

Pos logit contributions
mun+0.053
rob+0.050
Che+0.050
oun+0.050
 And+0.048
Neg logit contributions
eware-0.064
 knob-0.062
angs-0.062
 nearer-0.062
adoes-0.059
Tokenoes
Token ID3028
Feature activation+1.85e+00

Pos logit contributions
eware+0.109
angs+0.087
ricanes+0.063
 nearer+0.062
 knob+0.057
Neg logit contributions
mun-0.508
 And-0.496
 playing-0.494
 enjoying-0.493
 riding-0.492
Token.
Token ID13
Feature activation-8.19e-01

Pos logit contributions
eware+0.071
angs+0.067
 nearer+0.066
 upwards+0.064
 knob+0.064
Neg logit contributions
mun-0.058
Che-0.055
rob-0.055
 couple-0.052
 Evan-0.051
Token<|endoftext|>
Token ID50256
Feature activation+4.40e-01

Pos logit contributions
mun+0.025
rob+0.024
 wedding+0.023
 couple+0.022
 sidelines+0.021
Neg logit contributions
eware-0.033
ocular-0.030
ricanes-0.030
piece-0.029
 Knife-0.029
TokenOnce
Token ID7454
Feature activation+1.45e+00

Pos logit contributions
eware+0.017
nob+0.017
 nearer+0.016
angs+0.016
piece+0.015
Neg logit contributions
 sidelines-0.014
 wedding-0.013
mun-0.013
Che-0.012
 couple-0.012
Token upon
Token ID2402
Feature activation+2.39e+00

Pos logit contributions
eware+0.044
angs+0.041
 knob+0.038
 nearer+0.038
 upwards+0.037
Neg logit contributions
mun-0.057
rob-0.056
Che-0.055
 rh-0.054
 continuing-0.054
Token go
Token ID467
Feature activation-8.81e-01

Pos logit contributions
eware+0.286
 nearer+0.261
angs+0.260
 knob+0.257
nob+0.251
Neg logit contributions
mun-0.290
rob-0.280
 And-0.255
 celebrating-0.250
Che-0.245
Token any
Token ID597
Feature activation+2.67e+00

Pos logit contributions
mun+0.033
 And+0.032
Che+0.032
oc+0.031
 rh+0.031
Neg logit contributions
eware-0.029
angs-0.027
 nearer-0.027
 closer-0.025
ricanes-0.025
Token higher
Token ID2440
Feature activation+1.64e+00

Pos logit contributions
eware+0.101
angs+0.094
 nearer+0.087
ricanes+0.086
isable+0.085
Neg logit contributions
mun-0.088
 And-0.085
 enjoying-0.083
 playing-0.083
 riding-0.083
Token.
Token ID13
Feature activation+6.17e-01

Pos logit contributions
eware+0.065
angs+0.062
 nearer+0.059
 upwards+0.057
ricanes+0.057
Neg logit contributions
mun-0.049
 And-0.048
Che-0.046
 playing-0.046
 riding-0.046
Token She
Token ID1375
Feature activation-1.66e-01

Pos logit contributions
eware+0.027
angs+0.025
ricanes+0.024
 upwards+0.024
 Knife+0.023
Neg logit contributions
rob-0.017
mun-0.017
 enjoying-0.015
 pengu-0.014
 sailing-0.014
Token tipped
Token ID28395
Feature activation+8.69e+00

Pos logit contributions
mun+0.005
 And+0.005
 riding+0.005
 playing+0.005
 enjoying+0.005
Neg logit contributions
eware-0.007
angs-0.006
 nearer-0.006
ricanes-0.006
 knob-0.006
Token her
Token ID607
Feature activation+2.81e+00

Pos logit contributions
eware+0.374
angs+0.340
ricanes+0.325
isable+0.309
iqu+0.309
Neg logit contributions
 having-0.278
 playing-0.276
 riding-0.272
 enjoying-0.265
 town-0.250
Token hat
Token ID6877
Feature activation+1.89e+00

Pos logit contributions
eware+0.094
angs+0.087
ricanes+0.079
 nearer+0.078
isable+0.077
Neg logit contributions
mun-0.105
 And-0.102
 playing-0.102
 enjoying-0.101
 riding-0.101
Token to
Token ID284
Feature activation+2.82e+00

Pos logit contributions
eware+0.093
angs+0.087
ricanes+0.085
isable+0.082
 nearer+0.081
Neg logit contributions
 playing-0.042
 riding-0.041
 having-0.041
 enjoying-0.040
 And-0.040
Token the
Token ID262
Feature activation+7.47e-01

Pos logit contributions
eware+0.101
 knob+0.097
 nearer+0.095
angs+0.095
 closer+0.091
Neg logit contributions
mun-0.094
 And-0.089
rob-0.087
oc-0.084
 celebrating-0.082
Token clouds
Token ID15114
Feature activation+2.11e+00

Pos logit contributions
eware+0.025
angs+0.023
 knob+0.022
 nearer+0.021
ricanes+0.021
Neg logit contributions
mun-0.028
 And-0.027
 enjoying-0.026
 riding-0.026
 playing-0.026
Token not
Token ID407
Feature activation+5.43e+00

Pos logit contributions
rob+0.187
mun+0.186
 rh+0.185
 pengu+0.183
oc+0.179
Neg logit contributions
eware-0.058
angs-0.048
 nearer-0.047
out-0.045
 closer-0.044
Token understand
Token ID1833
Feature activation-1.50e+00

Pos logit contributions
eware+0.251
angs+0.238
ricanes+0.226
iqu+0.223
isable+0.223
Neg logit contributions
 And-0.129
 having-0.124
mun-0.124
 playing-0.123
 enjoying-0.121
Token.
Token ID13
Feature activation-6.31e-01

Pos logit contributions
 playing+0.026
 And+0.025
 having+0.024
mun+0.024
 enjoying+0.023
Neg logit contributions
eware-0.084
angs-0.079
ricanes-0.074
 nearer-0.073
isable-0.073
Token They
Token ID1119
Feature activation-2.81e+00

Pos logit contributions
mun+0.008
rob+0.006
 riding+0.006
 enjoying+0.006
 playing+0.006
Neg logit contributions
eware-0.038
angs-0.036
ricanes-0.035
 knob-0.034
 nearer-0.034
Token like
Token ID588
Feature activation-3.14e+00

Pos logit contributions
mun+0.070
 And+0.067
 playing+0.065
 enjoying+0.065
 having+0.064
Neg logit contributions
eware-0.131
angs-0.123
ricanes-0.115
 nearer-0.114
 upwards-0.112
Token volcan
Token ID17516
Feature activation+8.63e+00

Pos logit contributions
mun+0.089
 And+0.085
 playing+0.083
 enjoying+0.083
 riding+0.083
Neg logit contributions
eware-0.135
angs-0.127
ricanes-0.118
 nearer-0.117
 knob-0.116
Tokenoes
Token ID3028
Feature activation+1.71e+00

Pos logit contributions
eware+0.156
 nearer+0.121
angs+0.117
isable+0.116
ricanes+0.112
Neg logit contributions
mun-0.450
 And-0.443
 playing-0.440
 having-0.438
 enjoying-0.434
Token.
Token ID13
Feature activation-7.36e-01

Pos logit contributions
eware+0.063
angs+0.062
 knob+0.058
out+0.056
 nearer+0.056
Neg logit contributions
mun-0.054
rob-0.054
Che-0.053
 couple-0.051
 Evan-0.051
Token They
Token ID1119
Feature activation-2.98e+00

Pos logit contributions
mun+0.009
 riding+0.007
rob+0.007
 enjoying+0.007
 playing+0.007
Neg logit contributions
eware-0.044
angs-0.042
ricanes-0.040
 nearer-0.040
 knob-0.040
Token think
Token ID892
Feature activation+1.74e+00

Pos logit contributions
mun+0.079
 And+0.076
 playing+0.075
 enjoying+0.074
 having+0.073
Neg logit contributions
eware-0.133
angs-0.125
ricanes-0.116
 nearer-0.116
 upwards-0.114
Token they
Token ID484
Feature activation-2.33e+00

Pos logit contributions
eware+0.088
angs+0.083
isable+0.080
ricanes+0.078
 upwards+0.077
Neg logit contributions
 playing-0.036
 And-0.036
 having-0.036
 enjoying-0.035
mun-0.034
Token They
Token ID1119
Feature activation-2.63e+00

Pos logit contributions
mun+0.003
rob+0.002
 enjoying+0.002
 continuing+0.002
 riding+0.002
Neg logit contributions
eware-0.009
angs-0.009
ricanes-0.009
 upwards-0.008
 knob-0.008
Token learned
Token ID4499
Feature activation+1.07e-01

Pos logit contributions
mun+0.088
rob+0.084
 And+0.084
 riding+0.083
 playing+0.081
Neg logit contributions
eware-0.095
angs-0.091
 knob-0.084
ricanes-0.083
 nearer-0.082
Token a
Token ID257
Feature activation+2.74e-01

Pos logit contributions
eware+0.006
angs+0.005
rated+0.005
isable+0.005
 upwards+0.005
Neg logit contributions
 And-0.002
 playing-0.002
 having-0.002
 riding-0.002
 enjoying-0.002
Token lot
Token ID1256
Feature activation+2.11e+00

Pos logit contributions
eware+0.014
angs+0.014
ricanes+0.013
isable+0.013
 nearer+0.013
Neg logit contributions
mun-0.005
 And-0.005
 playing-0.005
 enjoying-0.005
 having-0.005
Token about
Token ID546
Feature activation-1.45e+00

Pos logit contributions
eware+0.111
angs+0.106
isable+0.103
ricanes+0.100
 upwards+0.099
Neg logit contributions
 And-0.042
 having-0.035
 playing-0.034
mun-0.033
 riding-0.033
Token volcan
Token ID17516
Feature activation+8.61e+00

Pos logit contributions
mun+0.048
rob+0.045
 And+0.045
Che+0.044
 Have+0.044
Neg logit contributions
eware-0.053
angs-0.050
 nearer-0.048
 knob-0.048
ricanes-0.046
Tokenoes
Token ID3028
Feature activation+1.81e+00

Pos logit contributions
eware+0.114
angs+0.092
ricanes+0.069
 nearer+0.068
isable+0.064
Neg logit contributions
mun-0.495
 And-0.485
 playing-0.482
 enjoying-0.481
 riding-0.479
Token.
Token ID13
Feature activation-5.90e-01

Pos logit contributions
eware+0.075
angs+0.072
 knob+0.067
 nearer+0.066
 upwards+0.065
Neg logit contributions
mun-0.052
Che-0.048
rob-0.048
 And-0.046
 Evan-0.046
Token They
Token ID1119
Feature activation-3.00e+00

Pos logit contributions
mun+0.010
rob+0.008
 enjoying+0.007
 playing+0.007
 continuing+0.007
Neg logit contributions
eware-0.034
angs-0.032
ricanes-0.031
 upwards-0.030
 nearer-0.030
Token thanked
Token ID26280
Feature activation-4.61e+00

Pos logit contributions
mun+0.091
 And+0.087
 riding+0.087
 playing+0.086
 enjoying+0.085
Neg logit contributions
eware-0.119
angs-0.113
ricanes-0.105
 nearer-0.104
 knob-0.104
Token the
Token ID262
Feature activation-1.86e+00

Pos logit contributions
mun+0.175
rob+0.169
oc+0.156
oun+0.154
 Have+0.151
Neg logit contributions
 knob-0.148
 nearer-0.144
eware-0.144
 closer-0.142
ricanes-0.135
Token They
Token ID1119
Feature activation-2.96e+00

Pos logit contributions
mun+0.014
rob+0.012
 riding+0.012
 enjoying+0.012
 continuing+0.011
Neg logit contributions
eware-0.061
angs-0.057
ricanes-0.055
 nearer-0.054
 upwards-0.054
Token want
Token ID765
Feature activation+1.62e-03

Pos logit contributions
mun+0.086
 And+0.081
 riding+0.081
 playing+0.080
 enjoying+0.080
Neg logit contributions
eware-0.123
angs-0.117
ricanes-0.109
 nearer-0.108
 knob-0.108
Token to
Token ID284
Feature activation+1.22e+00

Pos logit contributions
eware+0.000
angs+0.000
isable+0.000
rated+0.000
ricanes+0.000
Neg logit contributions
 playing-0.000
 pengu-0.000
 town-0.000
 having-0.000
 enjoying-0.000
Token write
Token ID3551
Feature activation-1.61e+00

Pos logit contributions
eware+0.046
angs+0.044
 knob+0.043
 nearer+0.042
ricanes+0.040
Neg logit contributions
mun-0.040
rob-0.038
 And-0.035
 continuing-0.035
 enjoying-0.034
Token about
Token ID546
Feature activation-1.63e+00

Pos logit contributions
 And+0.036
 playing+0.036
 having+0.034
 enjoying+0.033
 riding+0.033
Neg logit contributions
eware-0.082
angs-0.075
isable-0.072
ricanes-0.071
right-0.071
Token volcan
Token ID17516
Feature activation+8.58e+00

Pos logit contributions
mun+0.046
rob+0.043
 And+0.042
Che+0.042
 riding+0.042
Neg logit contributions
eware-0.068
angs-0.065
 nearer-0.062
 knob-0.061
ricanes-0.060
Tokenoes
Token ID3028
Feature activation+1.53e+00

Pos logit contributions
eware+0.135
angs+0.104
 nearer+0.095
isable+0.095
ricanes+0.093
Neg logit contributions
mun-0.467
 And-0.461
 playing-0.458
 having-0.458
 enjoying-0.456
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
eware+0.066
angs+0.063
 nearer+0.059
 knob+0.058
ricanes+0.058
Neg logit contributions
mun-0.042
 And-0.038
Che-0.038
rob-0.038
 riding-0.038
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
mun+0.013
 enjoying+0.011
 riding+0.011
rob+0.011
 playing+0.010
Neg logit contributions
eware-0.059
angs-0.056
ricanes-0.054
 nearer-0.053
 upwards-0.053
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
mun+0.026
rob+0.023
 enjoying+0.022
 continuing+0.021
 celebrating+0.020
Neg logit contributions
eware-0.077
angs-0.072
 nearer-0.070
ricanes-0.069
out-0.068
TokenThey
Token ID2990
Feature activation-2.68e+00

Pos logit contributions
mun+0.040
 And+0.039
 playing+0.038
 riding+0.038
 enjoying+0.038
Neg logit contributions
eware-0.048
angs-0.046
 nearer-0.041
ricanes-0.041
 upwards-0.040
Token and
Token ID290
Feature activation-9.95e-01

Pos logit contributions
eware+0.015
angs+0.014
ricanes+0.013
 nearer+0.013
isable+0.012
Neg logit contributions
mun-0.011
 And-0.011
 enjoying-0.011
 playing-0.011
 riding-0.011
Token she
Token ID673
Feature activation-2.56e+00

Pos logit contributions
mun+0.031
rob+0.030
 And+0.029
 riding+0.029
 continuing+0.028
Neg logit contributions
eware-0.039
angs-0.035
 nearer-0.034
ricanes-0.033
 knob-0.033
Token was
Token ID373
Feature activation-2.33e+00

Pos logit contributions
mun+0.076
 riding+0.072
 And+0.072
 playing+0.071
rob+0.071
Neg logit contributions
eware-0.102
angs-0.096
 nearer-0.089
 knob-0.088
ricanes-0.088
Token the
Token ID262
Feature activation-3.76e+00

Pos logit contributions
mun+0.065
 And+0.062
 playing+0.061
 enjoying+0.060
 riding+0.060
Neg logit contributions
eware-0.100
angs-0.095
 nearer-0.088
ricanes-0.088
 knob-0.086
Token happiest
Token ID49414
Feature activation-6.23e+00

Pos logit contributions
mun+0.120
 And+0.115
 playing+0.113
 enjoying+0.113
 riding+0.113
Neg logit contributions
eware-0.148
angs-0.139
ricanes-0.128
 nearer-0.127
 knob-0.125
Token girl
Token ID2576
Feature activation-9.26e+00

Pos logit contributions
mun+0.200
rob+0.189
 And+0.188
Che+0.184
 enjoying+0.182
Neg logit contributions
eware-0.240
angs-0.220
 knob-0.214
 nearer-0.209
 upwards-0.205
Token in
Token ID287
Feature activation-4.40e+00

Pos logit contributions
mun+0.307
rob+0.294
Che+0.284
 sidelines+0.278
 rh+0.271
Neg logit contributions
eware-0.347
angs-0.319
 knob-0.306
 nearer-0.303
pot-0.302
Token town
Token ID3240
Feature activation-4.10e+00

Pos logit contributions
rob+0.176
mun+0.172
oun+0.168
oc+0.162
Che+0.157
Neg logit contributions
 nearer-0.127
eware-0.123
 locked-0.122
 knob-0.122
 closer-0.122
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
rob+0.152
mun+0.142
oun+0.140
Che+0.137
 rh+0.136
Neg logit contributions
eware-0.127
out-0.122
ups-0.121
pot-0.115
angs-0.115
Token She
Token ID1375
Feature activation-1.96e+00

Pos logit contributions
mun+0.028
rob+0.027
 sidelines+0.026
 pengu+0.025
 sailing+0.025
Neg logit contributions
eware-0.048
 Judy-0.043
 upwards-0.043
angs-0.043
ricanes-0.042
Token used
Token ID973
Feature activation-3.91e-01

Pos logit contributions
mun+0.067
rob+0.065
 sidelines+0.063
Che+0.061
 rh+0.060
Neg logit contributions
eware-0.063
 knob-0.059
 locked-0.058
pot-0.057
angs-0.057
Token "
Token ID366
Feature activation+2.88e-01

Pos logit contributions
eware+0.007
 knob+0.006
ricanes+0.006
ker+0.006
 Knife+0.006
Neg logit contributions
mun-0.007
rob-0.007
 pengu-0.006
 town-0.006
 carn-0.006
TokenYou
Token ID1639
Feature activation-5.77e-01

Pos logit contributions
eware+0.010
ricanes+0.009
right+0.009
up+0.009
ups+0.009
Neg logit contributions
 playing-0.010
 sailing-0.009
 enjoying-0.009
mun-0.009
 pengu-0.009
Token are
Token ID389
Feature activation-3.47e+00

Pos logit contributions
mun+0.013
 And+0.012
 enjoying+0.012
 playing+0.012
 riding+0.012
Neg logit contributions
eware-0.028
angs-0.027
ricanes-0.025
 nearer-0.025
 knob-0.025
Token the
Token ID262
Feature activation-3.71e+00

Pos logit contributions
mun+0.126
oc+0.116
rob+0.113
Che+0.109
 continuing+0.107
Neg logit contributions
eware-0.115
angs-0.110
 ok-0.108
 knob-0.107
 nearer-0.107
Token best
Token ID1266
Feature activation-4.96e+00

Pos logit contributions
mun+0.123
 enjoying+0.117
 continuing+0.116
 And+0.116
 playing+0.114
Neg logit contributions
eware-0.137
angs-0.128
 knob-0.122
ricanes-0.120
 nearer-0.120
Token twins
Token ID20345
Feature activation-8.97e+00

Pos logit contributions
mun+0.178
Have+0.164
Che+0.161
 continuing+0.159
 enjoying+0.157
Neg logit contributions
eware-0.185
 knob-0.170
angs-0.164
 outage-0.152
ricanes-0.152
Token ever
Token ID1683
Feature activation-1.22e+00

Pos logit contributions
mun+0.305
Che+0.302
rob+0.287
 continuing+0.284
 sidelines+0.280
Neg logit contributions
eware-0.322
angs-0.301
out-0.284
 knob-0.277
 closer-0.270
Token!
Token ID0
Feature activation-8.16e-01

Pos logit contributions
mun+0.052
Che+0.052
 continuing+0.050
 sidelines+0.049
 Evan+0.048
Neg logit contributions
eware-0.036
angs-0.031
out-0.027
row-0.026
ups-0.026
Token I
Token ID314
Feature activation-1.09e-01

Pos logit contributions
mun+0.026
 sidelines+0.025
 continuing+0.025
 couple+0.024
 enjoying+0.024
Neg logit contributions
eware-0.032
angs-0.028
 Knife-0.027
 ok-0.027
ker-0.026
Token love
Token ID1842
Feature activation-1.12e+00

Pos logit contributions
 sidelines+0.004
mun+0.003
 continuing+0.003
 riding+0.003
rob+0.003
Neg logit contributions
eware-0.004
angs-0.004
 locked-0.004
 ok-0.004
up-0.003
Token you
Token ID345
Feature activation-5.13e-01

Pos logit contributions
mun+0.050
oc+0.046
he+0.045
Che+0.044
rob+0.043
Neg logit contributions
eware-0.029
ups-0.026
ricanes-0.026
 cigarettes-0.026
 knob-0.026
Token.
Token ID13
Feature activation-1.65e+00

Pos logit contributions
mun+0.095
Che+0.091
 continuing+0.087
 riding+0.087
rob+0.087
Neg logit contributions
eware-0.129
angs-0.124
 knob-0.115
out-0.114
ricanes-0.113
Token You
Token ID921
Feature activation+1.61e-01

Pos logit contributions
mun+0.040
 enjoying+0.036
 playing+0.035
 continuing+0.035
 riding+0.035
Neg logit contributions
eware-0.079
angs-0.074
ricanes-0.071
 nearer-0.069
 knob-0.069
Token're
Token ID821
Feature activation-1.88e+00

Pos logit contributions
eware+0.008
angs+0.007
 nearer+0.007
ricanes+0.007
 knob+0.007
Neg logit contributions
mun-0.004
 And-0.003
 riding-0.003
 playing-0.003
 enjoying-0.003
Token my
Token ID616
Feature activation-9.02e-01

Pos logit contributions
mun+0.065
 And+0.061
 enjoying+0.059
 riding+0.059
rob+0.059
Neg logit contributions
eware-0.069
angs-0.065
 nearer-0.060
ricanes-0.059
 knob-0.059
Token best
Token ID1266
Feature activation-5.27e+00

Pos logit contributions
mun+0.032
rob+0.031
 riding+0.030
 continuing+0.030
Che+0.029
Neg logit contributions
eware-0.032
angs-0.030
 knob-0.029
 nearer-0.027
isable-0.027
Token girl
Token ID2576
Feature activation-8.79e+00

Pos logit contributions
mun+0.193
 And+0.190
 playing+0.188
 enjoying+0.186
 riding+0.186
Neg logit contributions
eware-0.181
angs-0.168
ricanes-0.154
 nearer-0.152
isable-0.149
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
mun+0.264
Che+0.254
 continuing+0.247
rob+0.240
 sidelines+0.238
Neg logit contributions
eware-0.358
angs-0.336
 knob-0.307
out-0.305
 nearer-0.303
Token I
Token ID314
Feature activation-4.38e-01

Pos logit contributions
mun+0.038
 enjoying+0.034
 playing+0.034
 riding+0.034
 continuing+0.034
Neg logit contributions
eware-0.084
angs-0.079
ricanes-0.075
 nearer-0.074
 knob-0.073
Token'll
Token ID1183
Feature activation-4.34e-01

Pos logit contributions
mun+0.012
 sidelines+0.012
rob+0.012
 riding+0.012
 continuing+0.012
Neg logit contributions
eware-0.018
angs-0.016
 nearer-0.016
 closer-0.016
 ok-0.015
Token talk
Token ID1561
Feature activation+6.82e-01

Pos logit contributions
mun+0.017
rob+0.016
oc+0.014
 pengu+0.014
 rh+0.014
Neg logit contributions
eware-0.014
 knob-0.013
 ok-0.013
 nearer-0.013
 closer-0.013
Token to
Token ID284
Feature activation-2.70e-01

Pos logit contributions
eware+0.025
angs+0.023
ricanes+0.021
isable+0.021
 nearer+0.021
Neg logit contributions
 And-0.024
 playing-0.023
 enjoying-0.023
 having-0.023
mun-0.023
Token You
Token ID921
Feature activation+4.62e-02

Pos logit contributions
mun+0.033
 riding+0.029
 enjoying+0.029
 playing+0.029
 continuing+0.029
Neg logit contributions
eware-0.084
angs-0.079
ricanes-0.076
 knob-0.074
 upwards-0.074
Token are
Token ID389
Feature activation-3.42e+00

Pos logit contributions
eware+0.002
angs+0.002
ricanes+0.002
 nearer+0.002
 knob+0.002
Neg logit contributions
mun-0.001
 riding-0.001
 continuing-0.001
 And-0.001
 playing-0.001
Token both
Token ID1111
Feature activation-2.91e+00

Pos logit contributions
mun+0.120
rob+0.110
 And+0.108
 continuing+0.108
Che+0.108
Neg logit contributions
eware-0.119
angs-0.114
 nearer-0.106
 knob-0.105
isable-0.105
Token my
Token ID616
Feature activation-1.40e+00

Pos logit contributions
mun+0.100
rob+0.095
 continuing+0.095
oc+0.092
Che+0.091
Neg logit contributions
eware-0.104
angs-0.099
 knob-0.090
 ok-0.088
isable-0.088
Token beautiful
Token ID4950
Feature activation-3.11e+00

Pos logit contributions
rob+0.052
mun+0.051
 continuing+0.050
 riding+0.047
oc+0.047
Neg logit contributions
eware-0.046
 knob-0.042
angs-0.042
 closer-0.040
 ok-0.039
Token girls
Token ID4813
Feature activation-8.75e+00

Pos logit contributions
mun+0.093
 And+0.089
 enjoying+0.087
 continuing+0.086
 riding+0.086
Neg logit contributions
eware-0.128
angs-0.120
 knob-0.111
ricanes-0.111
 nearer-0.110
Token.
Token ID13
Feature activation-1.84e+00

Pos logit contributions
mun+0.329
Che+0.329
rob+0.320
 sidelines+0.307
 continuing+0.300
Neg logit contributions
eware-0.268
angs-0.259
 knob-0.242
 ok-0.238
 closer-0.236
Token Now
Token ID2735
Feature activation-1.47e+00

Pos logit contributions
mun+0.039
 enjoying+0.035
 playing+0.034
 riding+0.034
 continuing+0.034
Neg logit contributions
eware-0.092
angs-0.087
ricanes-0.083
 nearer-0.080
 knob-0.080
Token,
Token ID11
Feature activation-1.47e-02

Pos logit contributions
mun+0.043
rob+0.041
 And+0.039
 riding+0.038
 continuing+0.038
Neg logit contributions
eware-0.061
angs-0.055
 knob-0.054
 nearer-0.054
ricanes-0.054
Token let
Token ID1309
Feature activation-5.23e-01

Pos logit contributions
 playing+0.000
mun+0.000
 And+0.000
 enjoying+0.000
 having+0.000
Neg logit contributions
eware-0.001
angs-0.001
ricanes-0.000
isable-0.000
 nearer-0.000
Token's
Token ID338
Feature activation+2.85e+00

Pos logit contributions
mun+0.017
 And+0.016
 playing+0.016
 enjoying+0.016
 riding+0.016
Neg logit contributions
eware-0.020
angs-0.019
ricanes-0.018
 nearer-0.017
 knob-0.017
Token"
Token ID1
Feature activation+1.20e+00

Pos logit contributions
mun+0.036
 And+0.034
 playing+0.034
 enjoying+0.034
 riding+0.034
Neg logit contributions
eware-0.045
angs-0.043
ricanes-0.039
 nearer-0.038
 knob-0.038
TokenYou
Token ID1639
Feature activation-4.11e-01

Pos logit contributions
eware+0.046
angs+0.042
 nearer+0.042
ricanes+0.041
 knob+0.040
Neg logit contributions
mun-0.036
 playing-0.035
 And-0.035
 riding-0.034
oc-0.034
Token are
Token ID389
Feature activation-3.47e+00

Pos logit contributions
mun+0.010
 And+0.009
 playing+0.009
 enjoying+0.009
 riding+0.009
Neg logit contributions
eware-0.020
angs-0.019
ricanes-0.017
 nearer-0.017
 knob-0.017
Token the
Token ID262
Feature activation-3.69e+00

Pos logit contributions
mun+0.130
oc+0.121
rob+0.120
Che+0.115
 couple+0.112
Neg logit contributions
eware-0.112
 ok-0.110
angs-0.108
 nearer-0.105
isable-0.102
Token best
Token ID1266
Feature activation-5.04e+00

Pos logit contributions
mun+0.139
 continuing+0.132
 enjoying+0.131
 And+0.129
 playing+0.128
Neg logit contributions
eware-0.114
 knob-0.108
angs-0.105
 nearer-0.103
 ok-0.102
Token twins
Token ID20345
Feature activation-8.71e+00

Pos logit contributions
Have+0.187
mun+0.187
Che+0.181
 sidelines+0.175
 enjoying+0.173
Neg logit contributions
eware-0.169
 knob-0.158
angs-0.140
 key-0.138
 outage-0.137
Token ever
Token ID1683
Feature activation-1.17e+00

Pos logit contributions
Che+0.336
mun+0.323
rob+0.315
 continuing+0.315
 sidelines+0.312
Neg logit contributions
eware-0.276
angs-0.252
out-0.240
 closer-0.235
 ok-0.233
Token!"
Token ID2474
Feature activation-1.70e+00

Pos logit contributions
Che+0.052
mun+0.051
Have+0.051
 continuing+0.050
 sidelines+0.049
Neg logit contributions
eware-0.032
angs-0.027
 nearer-0.023
out-0.023
rated-0.022
Token she
Token ID673
Feature activation-1.19e+00

Pos logit contributions
mun+0.050
rob+0.049
 enjoying+0.047
 riding+0.047
 Have+0.047
Neg logit contributions
eware-0.068
angs-0.064
 nearer-0.062
ricanes-0.060
 knob-0.060
Token said
Token ID531
Feature activation-2.76e+00

Pos logit contributions
mun+0.042
 enjoying+0.040
 And+0.040
 playing+0.040
 riding+0.039
Neg logit contributions
eware-0.042
angs-0.039
 nearer-0.036
ricanes-0.035
 knob-0.035
Token.
Token ID13
Feature activation-3.62e-01

Pos logit contributions
rob+0.104
mun+0.095
Have+0.093
 carn+0.092
 rh+0.092
Neg logit contributions
eware-0.096
 firmly-0.094
 nearer-0.091
 closer-0.091
angs-0.090
Token pain
Token ID2356
Feature activation-9.80e-01

Pos logit contributions
mun+0.175
Have+0.163
rob+0.160
 continuing+0.159
Che+0.158
Neg logit contributions
eware-0.192
 knob-0.175
angs-0.174
out-0.155
 nearer-0.151
Tokenters
Token ID1010
Feature activation-4.47e+00

Pos logit contributions
mun+0.031
Che+0.029
 continuing+0.029
rob+0.029
 And+0.029
Neg logit contributions
eware-0.039
angs-0.037
 knob-0.034
out-0.033
 nearer-0.033
Token and
Token ID290
Feature activation-1.93e+00

Pos logit contributions
mun+0.149
rob+0.148
Che+0.145
 And+0.138
 continuing+0.135
Neg logit contributions
eware-0.162
angs-0.157
 knob-0.144
 nearer-0.142
out-0.142
Token the
Token ID262
Feature activation-3.38e+00

Pos logit contributions
mun+0.066
rob+0.062
 continuing+0.059
Che+0.059
 And+0.058
Neg logit contributions
eware-0.072
angs-0.067
ricanes-0.063
 knob-0.063
 disrespectful-0.061
Token best
Token ID1266
Feature activation-5.23e+00

Pos logit contributions
mun+0.119
 continuing+0.113
 And+0.112
rob+0.111
 riding+0.109
Neg logit contributions
eware-0.118
angs-0.110
 knob-0.106
isable-0.101
ricanes-0.099
Token twins
Token ID20345
Feature activation-8.71e+00

Pos logit contributions
mun+0.184
rob+0.172
 continuing+0.169
Che+0.167
 And+0.165
Neg logit contributions
eware-0.194
angs-0.178
 knob-0.173
out-0.161
 nearer-0.158
Token in
Token ID287
Feature activation-3.49e+00

Pos logit contributions
mun+0.323
rob+0.319
Che+0.315
 continuing+0.289
 sidelines+0.285
Neg logit contributions
eware-0.280
angs-0.271
out-0.263
 closer-0.254
 knob-0.243
Token the
Token ID262
Feature activation-2.39e+00

Pos logit contributions
mun+0.141
rob+0.133
oun+0.125
Che+0.121
oc+0.118
Neg logit contributions
angs-0.100
eware-0.100
 half-0.099
 locked-0.095
 prick-0.095
Token world
Token ID995
Feature activation-1.58e+00

Pos logit contributions
mun+0.066
 continuing+0.064
 riding+0.064
 Evan+0.062
 enjoying+0.061
Neg logit contributions
eware-0.098
angs-0.093
 knob-0.090
isable-0.090
ricanes-0.089
Token!
Token ID0
Feature activation-1.75e-01

Pos logit contributions
mun+0.057
Che+0.055
 continuing+0.053
 And+0.052
Have+0.052
Neg logit contributions
eware-0.056
angs-0.052
out-0.049
 nearer-0.046
ricanes-0.046
Token I
Token ID314
Feature activation-8.79e-02

Pos logit contributions
mun+0.005
 continuing+0.005
 enjoying+0.005
 sidelines+0.005
rob+0.005
Neg logit contributions
eware-0.007
angs-0.006
 Knife-0.006
ricanes-0.006
 ok-0.006
Token!
Token ID0
Feature activation-3.52e-01

Pos logit contributions
eware+0.011
angs+0.010
ricanes+0.009
 nearer+0.009
isable+0.009
Neg logit contributions
mun-0.006
 And-0.006
 playing-0.006
 enjoying-0.006
 riding-0.006
Token You
Token ID921
Feature activation-1.66e-01

Pos logit contributions
mun+0.011
 continuing+0.010
 couple+0.010
 enjoying+0.010
rob+0.010
Neg logit contributions
eware-0.015
angs-0.013
ricanes-0.013
 Knife-0.012
ker-0.012
Token are
Token ID389
Feature activation-3.45e+00

Pos logit contributions
mun+0.003
 And+0.003
 riding+0.003
 continuing+0.003
 enjoying+0.003
Neg logit contributions
eware-0.008
angs-0.008
 nearer-0.007
ricanes-0.007
 knob-0.007
Token the
Token ID262
Feature activation-3.57e+00

Pos logit contributions
mun+0.114
rob+0.103
oc+0.102
 And+0.102
Che+0.102
Neg logit contributions
eware-0.129
angs-0.125
 nearer-0.115
isable-0.114
 upwards-0.112
Token best
Token ID1266
Feature activation-5.26e+00

Pos logit contributions
mun+0.105
 And+0.100
 playing+0.099
 enjoying+0.099
 riding+0.099
Neg logit contributions
eware-0.149
angs-0.141
ricanes-0.130
 nearer-0.129
isable-0.127
Token twins
Token ID20345
Feature activation-8.64e+00

Pos logit contributions
mun+0.170
 enjoying+0.155
 continuing+0.155
 And+0.155
rob+0.155
Neg logit contributions
eware-0.209
angs-0.196
 knob-0.181
 nearer-0.179
ricanes-0.177
Token ever
Token ID1683
Feature activation-1.11e+00

Pos logit contributions
Che+0.306
mun+0.302
rob+0.285
 continuing+0.284
 sidelines+0.280
Neg logit contributions
eware-0.291
angs-0.279
out-0.270
 closer-0.255
 knob-0.253
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
mun+0.041
Che+0.040
 continuing+0.039
 riding+0.039
 enjoying+0.038
Neg logit contributions
eware-0.038
angs-0.035
 nearer-0.031
ricanes-0.031
out-0.030
Token This
Token ID770
Feature activation+5.77e-02

Pos logit contributions
mun+0.031
 enjoying+0.028
 continuing+0.028
 riding+0.027
 playing+0.027
Neg logit contributions
eware-0.066
angs-0.062
ricanes-0.059
 nearer-0.056
 Knife-0.056
Token is
Token ID318
Feature activation-1.43e+00

Pos logit contributions
eware+0.002
angs+0.002
 knob+0.002
 powder+0.001
 happens+0.001
Neg logit contributions
 continuing-0.002
mun-0.002
 Evan-0.002
 enjoying-0.002
Che-0.002
Token very
Token ID845
Feature activation-1.03e+00

Pos logit contributions
 And+0.041
mun+0.041
 playing+0.040
 having+0.040
 enjoying+0.040
Neg logit contributions
eware-0.061
angs-0.058
ricanes-0.053
 nearer-0.053
 upwards-0.052
Token and
Token ID290
Feature activation-4.19e-01

Pos logit contributions
mun+0.059
 And+0.056
 playing+0.054
 enjoying+0.054
 riding+0.054
Neg logit contributions
eware-0.068
angs-0.063
 nearer-0.058
ricanes-0.058
 knob-0.057
Token she
Token ID673
Feature activation-2.26e+00

Pos logit contributions
mun+0.013
rob+0.012
 And+0.012
Che+0.012
oc+0.012
Neg logit contributions
eware-0.016
angs-0.015
 knob-0.014
 nearer-0.014
ricanes-0.014
Token was
Token ID373
Feature activation-2.20e+00

Pos logit contributions
rob+0.079
mun+0.079
 sidelines+0.074
Che+0.074
 continuing+0.073
Neg logit contributions
eware-0.072
 locked-0.066
angs-0.065
 knob-0.065
nob-0.064
Token the
Token ID262
Feature activation-3.52e+00

Pos logit contributions
mun+0.073
rob+0.072
 And+0.066
oc+0.065
Che+0.064
Neg logit contributions
eware-0.079
angs-0.076
 nearer-0.074
 ok-0.073
 upwards-0.072
Token happiest
Token ID49414
Feature activation-5.94e+00

Pos logit contributions
mun+0.122
 And+0.118
 playing+0.115
 riding+0.115
rob+0.114
Neg logit contributions
eware-0.125
angs-0.115
 knob-0.109
 nearer-0.108
ricanes-0.108
Token girl
Token ID2576
Feature activation-8.64e+00

Pos logit contributions
mun+0.174
rob+0.167
 And+0.165
Che+0.163
oc+0.162
Neg logit contributions
eware-0.234
 knob-0.221
angs-0.215
 nearer-0.209
 upwards-0.207
Token around
Token ID1088
Feature activation-2.78e+00

Pos logit contributions
mun+0.305
rob+0.303
Che+0.292
 sidelines+0.285
 Many+0.278
Neg logit contributions
eware-0.289
angs-0.264
 knob-0.264
pot-0.261
 ok-0.261
Token!
Token ID0
Feature activation-1.47e-01

Pos logit contributions
mun+0.105
rob+0.105
Che+0.103
oun+0.103
oc+0.102
Neg logit contributions
out-0.077
 knob-0.074
 upwards-0.073
eware-0.073
 closer-0.073
Token<|endoftext|>
Token ID50256
Feature activation+6.00e-01

Pos logit contributions
mun+0.004
rob+0.004
 pengu+0.004
 rh+0.003
 sailing+0.003
Neg logit contributions
eware-0.006
angs-0.006
 Judy-0.006
ricanes-0.006
piece-0.006
TokenOne
Token ID3198
Feature activation+4.81e+00

Pos logit contributions
eware+0.020
 nearer+0.019
nob+0.018
angs+0.018
 closer+0.018
Neg logit contributions
 sidelines-0.021
 wedding-0.020
Che-0.019
 rh-0.019
mun-0.019
Token day
Token ID1110
Feature activation-2.95e+00

Pos logit contributions
eware+0.242
angs+0.224
right+0.216
 knob+0.215
 nearer+0.215
Neg logit contributions
mun-0.103
rob-0.097
Che-0.088
 And-0.087
 continuing-0.087
Token "
Token ID366
Feature activation+8.78e-01

Pos logit contributions
mun+0.007
 enjoying+0.007
 And+0.007
 playing+0.007
 riding+0.007
Neg logit contributions
eware-0.014
angs-0.014
ricanes-0.013
 nearer-0.013
 knob-0.013
TokenYou
Token ID1639
Feature activation-1.46e-01

Pos logit contributions
eware+0.025
iders+0.023
ricanes+0.023
right+0.023
piece+0.023
Neg logit contributions
mun-0.031
 je-0.029
 continuing-0.029
 playing-0.029
 gor-0.028
Token are
Token ID389
Feature activation-3.19e+00

Pos logit contributions
mun+0.003
 riding+0.003
 continuing+0.003
 And+0.003
 enjoying+0.003
Neg logit contributions
eware-0.007
angs-0.007
ricanes-0.006
 nearer-0.006
 knob-0.006
Token the
Token ID262
Feature activation-3.60e+00

Pos logit contributions
mun+0.111
oc+0.104
rob+0.101
 continuing+0.097
Che+0.097
Neg logit contributions
eware-0.109
angs-0.106
 nearer-0.100
 knob-0.100
 ok-0.099
Token best
Token ID1266
Feature activation-4.86e+00

Pos logit contributions
mun+0.100
 And+0.095
 playing+0.094
 enjoying+0.094
 riding+0.093
Neg logit contributions
eware-0.159
angs-0.150
ricanes-0.139
 nearer-0.138
isable-0.135
Token twins
Token ID20345
Feature activation-8.61e+00

Pos logit contributions
mun+0.148
rob+0.138
Che+0.136
Have+0.136
 continuing+0.135
Neg logit contributions
eware-0.199
angs-0.185
 knob-0.179
 nearer-0.169
ricanes-0.167
Token ever
Token ID1683
Feature activation-1.19e+00

Pos logit contributions
mun+0.307
Che+0.305
rob+0.292
 sidelines+0.287
 continuing+0.285
Neg logit contributions
eware-0.289
angs-0.274
out-0.266
 knob-0.257
 closer-0.252
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
mun+0.047
Che+0.046
 continuing+0.044
 riding+0.043
 Evan+0.043
Neg logit contributions
eware-0.038
angs-0.035
out-0.031
 nearer-0.030
 knob-0.029
Token You
Token ID921
Feature activation+1.42e-01

Pos logit contributions
mun+0.039
 continuing+0.036
 enjoying+0.036
rob+0.035
 riding+0.035
Neg logit contributions
eware-0.072
angs-0.067
ricanes-0.064
 Knife-0.062
right-0.061
Token are
Token ID389
Feature activation-3.40e+00

Pos logit contributions
eware+0.007
angs+0.006
ricanes+0.006
 nearer+0.006
 knob+0.006
Neg logit contributions
mun-0.003
 continuing-0.003
 riding-0.003
 And-0.003
 playing-0.003
Token so
Token ID523
Feature activation-3.13e+00

Pos logit contributions
mun+0.120
oc+0.111
rob+0.110
 And+0.107
Che+0.105
Neg logit contributions
eware-0.117
angs-0.112
 nearer-0.107
 knob-0.105
isable-0.104
Token "
Token ID366
Feature activation+2.15e-01

Pos logit contributions
mun+0.003
rob+0.003
 enjoying+0.003
 riding+0.003
 rh+0.003
Neg logit contributions
eware-0.005
angs-0.004
 knob-0.004
ricanes-0.004
 nearer-0.004
TokenYou
Token ID1639
Feature activation-7.98e-01

Pos logit contributions
eware+0.008
angs+0.008
ricanes+0.007
 nearer+0.007
 upwards+0.007
Neg logit contributions
 playing-0.007
 riding-0.007
 enjoying-0.007
mun-0.007
 sailing-0.006
Token are
Token ID389
Feature activation-3.68e+00

Pos logit contributions
mun+0.015
 And+0.014
 playing+0.014
 enjoying+0.014
 riding+0.014
Neg logit contributions
eware-0.042
angs-0.040
ricanes-0.037
 nearer-0.037
 knob-0.037
Token such
Token ID884
Feature activation-3.08e+00

Pos logit contributions
mun+0.118
oc+0.109
rob+0.108
Che+0.105
 continuing+0.104
Neg logit contributions
eware-0.138
angs-0.135
 nearer-0.126
 knob-0.124
isable-0.124
Token good
Token ID922
Feature activation-2.93e+00

Pos logit contributions
mun+0.101
 And+0.095
 enjoying+0.095
 playing+0.094
 riding+0.094
Neg logit contributions
eware-0.118
angs-0.110
 nearer-0.101
ricanes-0.101
 knob-0.099
Token twins
Token ID20345
Feature activation-8.58e+00

Pos logit contributions
Have+0.076
 Have+0.074
Che+0.074
mun+0.073
rob+0.072
Neg logit contributions
eware-0.128
angs-0.124
 knob-0.117
 nearer-0.113
out-0.112
Token.
Token ID13
Feature activation-2.24e+00

Pos logit contributions
mun+0.295
Che+0.288
rob+0.282
 continuing+0.269
 sidelines+0.261
Neg logit contributions
eware-0.308
angs-0.298
out-0.275
 knob-0.267
 ok-0.263
Token You
Token ID921
Feature activation-3.61e-01

Pos logit contributions
mun+0.051
 enjoying+0.047
 riding+0.046
 continuing+0.046
 playing+0.046
Neg logit contributions
eware-0.109
angs-0.103
ricanes-0.097
 nearer-0.094
 knob-0.094
Token are
Token ID389
Feature activation-3.81e+00

Pos logit contributions
mun+0.009
 And+0.009
 riding+0.009
 playing+0.009
 enjoying+0.009
Neg logit contributions
eware-0.016
angs-0.015
ricanes-0.014
 nearer-0.014
 knob-0.014
Token such
Token ID884
Feature activation-3.19e+00

Pos logit contributions
mun+0.126
 And+0.116
rob+0.115
Che+0.113
oc+0.113
Neg logit contributions
eware-0.142
angs-0.136
 nearer-0.126
isable-0.124
 knob-0.124
Token good
Token ID922
Feature activation-2.94e+00

Pos logit contributions
mun+0.107
 And+0.100
 enjoying+0.099
 riding+0.098
 playing+0.098
Neg logit contributions
eware-0.121
angs-0.113
 nearer-0.104
ricanes-0.103
 knob-0.102
Token "
Token ID366
Feature activation+1.87e-01

Pos logit contributions
mun+0.090
 And+0.082
rob+0.082
 enjoying+0.082
 riding+0.081
Neg logit contributions
eware-0.131
angs-0.123
 nearer-0.115
ricanes-0.114
 upwards-0.113
TokenWe
Token ID1135
Feature activation-1.97e+00

Pos logit contributions
eware+0.007
pot+0.006
isable+0.006
angs+0.006
piece+0.006
Neg logit contributions
 playing-0.006
mun-0.006
 enjoying-0.006
 riding-0.006
 continuing-0.006
Token are
Token ID389
Feature activation-3.56e+00

Pos logit contributions
mun+0.045
 And+0.042
 riding+0.041
 continuing+0.041
 enjoying+0.041
Neg logit contributions
eware-0.095
angs-0.090
ricanes-0.084
 nearer-0.084
 knob-0.084
Token the
Token ID262
Feature activation-4.12e+00

Pos logit contributions
mun+0.130
oc+0.126
rob+0.122
Che+0.114
Have+0.111
Neg logit contributions
 ok-0.113
angs-0.111
eware-0.110
 nearer-0.108
 closer-0.106
Token best
Token ID1266
Feature activation-5.42e+00

Pos logit contributions
mun+0.121
 And+0.115
 playing+0.114
 enjoying+0.113
 riding+0.113
Neg logit contributions
eware-0.172
angs-0.162
ricanes-0.150
 nearer-0.149
 knob-0.147
Token friends
Token ID2460
Feature activation-8.58e+00

Pos logit contributions
mun+0.181
Che+0.174
Have+0.168
 continuing+0.158
rob+0.158
Neg logit contributions
eware-0.210
angs-0.202
 knob-0.193
adoes-0.180
out-0.177
Token ever
Token ID1683
Feature activation-1.46e+00

Pos logit contributions
mun+0.330
Che+0.320
rob+0.303
 continuing+0.301
 sidelines+0.300
Neg logit contributions
eware-0.280
angs-0.260
out-0.246
 closer-0.230
 nearer-0.228
Token!"
Token ID2474
Feature activation-1.62e+00

Pos logit contributions
mun+0.055
Che+0.054
 continuing+0.052
 Evan+0.051
 riding+0.051
Neg logit contributions
eware-0.049
angs-0.044
out-0.039
 nearer-0.039
leys-0.037
Token They
Token ID1119
Feature activation-2.87e+00

Pos logit contributions
mun+0.039
rob+0.035
 continuing+0.034
 enjoying+0.032
 rh+0.031
Neg logit contributions
eware-0.077
angs-0.075
ricanes-0.071
ups-0.069
ocular-0.069
Token were
Token ID547
Feature activation-2.92e+00

Pos logit contributions
mun+0.076
 And+0.072
 riding+0.072
 Have+0.072
rob+0.070
Neg logit contributions
eware-0.117
angs-0.112
isable-0.106
 knob-0.106
ricanes-0.106
Token not
Token ID407
Feature activation+3.99e+00

Pos logit contributions
rob+0.085
oc+0.083
mun+0.083
Che+0.071
Have+0.069
Neg logit contributions
 ok-0.118
 closer-0.113
angs-0.110
 nearer-0.110
 locked-0.109
Token.
Token ID13
Feature activation-1.76e+00

Pos logit contributions
mun+0.064
 enjoying+0.059
 riding+0.058
 And+0.058
 playing+0.058
Neg logit contributions
eware-0.113
angs-0.107
ricanes-0.100
 nearer-0.099
 knob-0.099
Token You
Token ID921
Feature activation-4.74e-02

Pos logit contributions
mun+0.040
 enjoying+0.035
 riding+0.035
 playing+0.035
 continuing+0.035
Neg logit contributions
eware-0.086
angs-0.081
ricanes-0.077
 knob-0.075
 nearer-0.075
Token're
Token ID821
Feature activation-2.14e+00

Pos logit contributions
mun+0.001
 And+0.001
 playing+0.001
 riding+0.001
 enjoying+0.001
Neg logit contributions
eware-0.002
angs-0.002
ricanes-0.002
 nearer-0.002
 knob-0.002
Token my
Token ID616
Feature activation-1.23e+00

Pos logit contributions
mun+0.070
 And+0.064
 riding+0.063
rob+0.063
 enjoying+0.063
Neg logit contributions
eware-0.082
angs-0.078
 nearer-0.072
ricanes-0.071
 knob-0.071
Token sweet
Token ID6029
Feature activation-2.33e+00

Pos logit contributions
mun+0.043
rob+0.041
 continuing+0.040
 riding+0.040
 having+0.040
Neg logit contributions
eware-0.044
angs-0.041
 knob-0.039
 nearer-0.038
isable-0.037
Token girl
Token ID2576
Feature activation-8.57e+00

Pos logit contributions
mun+0.051
 And+0.049
 playing+0.048
 enjoying+0.047
 riding+0.047
Neg logit contributions
eware-0.115
angs-0.109
ricanes-0.103
 nearer-0.102
isable-0.100
Token."
Token ID526
Feature activation-1.49e+00

Pos logit contributions
mun+0.234
 And+0.215
 enjoying+0.215
 riding+0.215
 playing+0.214
Neg logit contributions
eware-0.373
angs-0.353
ricanes-0.326
 nearer-0.326
 knob-0.323
Token They
Token ID1119
Feature activation-2.75e+00

Pos logit contributions
mun+0.043
rob+0.043
 riding+0.038
 rh+0.038
 sailing+0.038
Neg logit contributions
eware-0.057
ricanes-0.055
angs-0.055
 wider-0.054
piece-0.053
Token hug
Token ID16225
Feature activation-4.62e-01

Pos logit contributions
mun+0.095
rob+0.091
oc+0.087
 Have+0.085
 riding+0.084
Neg logit contributions
 knob-0.090
ricanes-0.087
eware-0.087
 closer-0.086
angs-0.086
Token and
Token ID290
Feature activation-6.38e-01

Pos logit contributions
mun+0.016
rob+0.016
 Have+0.015
 riding+0.015
 carn+0.015
Neg logit contributions
eware-0.016
 knob-0.015
adoes-0.015
angs-0.015
 closer-0.014
Token thank
Token ID5875
Feature activation-3.64e+00

Pos logit contributions
mun+0.021
rob+0.020
 riding+0.019
oc+0.019
 having+0.019
Neg logit contributions
eware-0.022
ricanes-0.021
 knob-0.021
 nearer-0.020
angs-0.020
Token.
Token ID13
Feature activation-6.64e-01

Pos logit contributions
angs+0.018
eware+0.018
 nearer+0.018
 closer+0.018
 upwards+0.017
Neg logit contributions
rob-0.017
mun-0.016
oc-0.015
 And-0.015
 rh-0.015
Token It
Token ID632
Feature activation+2.81e+00

Pos logit contributions
mun+0.012
 And+0.012
 playing+0.011
 enjoying+0.011
 riding+0.011
Neg logit contributions
eware-0.035
angs-0.034
ricanes-0.032
 nearer-0.032
 knob-0.031
Token was
Token ID373
Feature activation-1.56e+00

Pos logit contributions
eware+0.136
angs+0.130
ricanes+0.121
 nearer+0.120
 knob+0.118
Neg logit contributions
mun-0.064
 And-0.061
 enjoying-0.060
 playing-0.060
 having-0.059
Token the
Token ID262
Feature activation-2.79e+00

Pos logit contributions
 having+0.038
 playing+0.038
 enjoying+0.038
 riding+0.035
 celebrating+0.035
Neg logit contributions
eware-0.079
angs-0.074
ricanes-0.070
 Knife-0.067
 nearer-0.066
Token happiest
Token ID49414
Feature activation-5.68e+00

Pos logit contributions
mun+0.088
 enjoying+0.083
 playing+0.083
 And+0.083
 riding+0.083
Neg logit contributions
eware-0.113
angs-0.106
ricanes-0.097
 nearer-0.096
 upwards-0.094
Token day
Token ID1110
Feature activation-8.54e+00

Pos logit contributions
mun+0.151
 And+0.143
 playing+0.141
 enjoying+0.141
 riding+0.140
Neg logit contributions
eware-0.252
angs-0.238
ricanes-0.221
 nearer-0.221
 knob-0.218
Token ever
Token ID1683
Feature activation-1.79e+00

Pos logit contributions
mun+0.271
rob+0.270
 rh+0.262
oc+0.258
Che+0.251
Neg logit contributions
eware-0.334
angs-0.303
out-0.288
 knob-0.288
 nearer-0.286
Token!
Token ID0
Feature activation-4.47e-01

Pos logit contributions
mun+0.068
Che+0.067
 rh+0.064
 pengu+0.062
rob+0.062
Neg logit contributions
eware-0.059
angs-0.055
out-0.054
 nearer-0.051
 upwards-0.051
Token<|endoftext|>
Token ID50256
Feature activation+4.38e-01

Pos logit contributions
mun+0.007
rob+0.006
 pengu+0.006
 rh+0.005
 enjoying+0.005
Neg logit contributions
eware-0.025
angs-0.024
ricanes-0.023
 upwards-0.023
 nearer-0.023
TokenOnce
Token ID7454
Feature activation+1.49e+00

Pos logit contributions
eware+0.017
nob+0.016
angs+0.015
 nearer+0.015
piece+0.015
Neg logit contributions
 sidelines-0.014
 wedding-0.013
mun-0.013
 continuing-0.012
 rh-0.012
Token upon
Token ID2402
Feature activation+2.38e+00

Pos logit contributions
eware+0.048
angs+0.044
ricanes+0.040
 nearer+0.040
 knob+0.039
Neg logit contributions
mun-0.058
 And-0.056
 enjoying-0.055
 riding-0.055
 playing-0.055
Token.
Token ID13
Feature activation-2.48e+00

Pos logit contributions
mun+0.103
rob+0.097
Che+0.095
 continuing+0.093
 rh+0.090
Neg logit contributions
eware-0.122
angs-0.116
out-0.109
 knob-0.108
 nearer-0.104
Token You
Token ID921
Feature activation-4.03e-01

Pos logit contributions
mun+0.064
 riding+0.056
 playing+0.056
 continuing+0.056
 enjoying+0.056
Neg logit contributions
eware-0.118
angs-0.110
ricanes-0.103
 Knife-0.100
 knob-0.098
Token are
Token ID389
Feature activation-3.75e+00

Pos logit contributions
mun+0.010
 riding+0.009
rob+0.009
 And+0.009
 continuing+0.009
Neg logit contributions
eware-0.018
angs-0.017
 nearer-0.016
 knob-0.016
ricanes-0.016
Token my
Token ID616
Feature activation-1.18e+00

Pos logit contributions
mun+0.127
rob+0.117
 And+0.115
oc+0.113
Che+0.113
Neg logit contributions
eware-0.137
angs-0.132
 nearer-0.123
 knob-0.122
isable-0.121
Token precious
Token ID14186
Feature activation+2.98e-01

Pos logit contributions
mun+0.042
rob+0.041
 continuing+0.039
 riding+0.039
Che+0.038
Neg logit contributions
eware-0.041
angs-0.038
 knob-0.037
 nearer-0.036
isable-0.035
Token twins
Token ID20345
Feature activation-8.54e+00

Pos logit contributions
eware+0.012
angs+0.011
 knob+0.011
 nearer+0.010
ricanes+0.010
Neg logit contributions
mun-0.009
Che-0.008
rob-0.008
 And-0.008
 continuing-0.008
Token."
Token ID526
Feature activation-1.49e+00

Pos logit contributions
mun+0.331
rob+0.322
Che+0.320
 continuing+0.297
 sidelines+0.297
Neg logit contributions
eware-0.259
angs-0.249
out-0.234
 knob-0.232
 ok-0.232
Token<|endoftext|>
Token ID50256
Feature activation+5.41e-01

Pos logit contributions
mun+0.034
 riding+0.032
 enjoying+0.031
 playing+0.031
 having+0.031
Neg logit contributions
eware-0.072
angs-0.068
ricanes-0.064
 nearer-0.064
 knob-0.063
TokenL
Token ID43
Feature activation+2.91e+00

Pos logit contributions
eware+0.020
angs+0.019
 nearer+0.018
 iv+0.018
nob+0.017
Neg logit contributions
 sidelines-0.017
 continuing-0.016
Che-0.016
 couple-0.016
 wedding-0.015
Tokenily
Token ID813
Feature activation+1.94e+00

Pos logit contributions
eware+0.096
angs+0.082
ricanes+0.081
 nearer+0.078
isable+0.078
Neg logit contributions
 And-0.115
 playing-0.114
mun-0.112
 having-0.111
 enjoying-0.108
Token and
Token ID290
Feature activation+1.77e+00

Pos logit contributions
eware+0.088
angs+0.083
 knob+0.077
ricanes+0.077
isable+0.077
Neg logit contributions
mun-0.049
 continuing-0.044
 having-0.043
 riding-0.043
Che-0.043
Token toes
Token ID23932
Feature activation+5.48e-01

Pos logit contributions
mun+0.056
 And+0.051
rob+0.050
oc+0.050
 continuing+0.049
Neg logit contributions
angs-0.068
eware-0.066
 prick-0.063
 nearer-0.061
 upwards-0.061
Token made
Token ID925
Feature activation-3.63e-01

Pos logit contributions
eware+0.024
angs+0.023
 nearer+0.021
ricanes+0.021
 knob+0.021
Neg logit contributions
mun-0.015
 And-0.014
Che-0.014
rob-0.014
 enjoying-0.013
Token him
Token ID683
Feature activation+1.08e-01

Pos logit contributions
mun+0.010
rob+0.010
oc+0.009
 Have+0.009
Have+0.009
Neg logit contributions
 nearer-0.015
angs-0.015
eware-0.014
 closer-0.014
out-0.014
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
eware+0.004
angs+0.004
 nearer+0.004
 closer+0.004
 upwards+0.004
Neg logit contributions
mun-0.003
rob-0.003
 And-0.003
Che-0.003
 Have-0.003
Token happiest
Token ID49414
Feature activation-5.55e+00

Pos logit contributions
mun+0.058
 And+0.056
rob+0.054
 continuing+0.054
oc+0.053
Neg logit contributions
eware-0.045
angs-0.041
 knob-0.040
 nearer-0.038
 upwards-0.038
Token boy
Token ID2933
Feature activation-8.53e+00

Pos logit contributions
mun+0.183
rob+0.173
Che+0.171
oc+0.171
 And+0.169
Neg logit contributions
eware-0.199
 knob-0.198
angs-0.188
 upwards-0.183
 nearer-0.180
Token in
Token ID287
Feature activation-4.27e+00

Pos logit contributions
mun+0.344
Che+0.337
rob+0.331
 sidelines+0.324
 Many+0.318
Neg logit contributions
eware-0.235
angs-0.235
out-0.232
 closer-0.231
piece-0.215
Token the
Token ID262
Feature activation-2.91e+00

Pos logit contributions
mun+0.182
 And+0.175
oc+0.171
rob+0.170
Che+0.168
Neg logit contributions
 nearer-0.114
 closer-0.113
 locked-0.113
 upwards-0.105
out-0.104
Token world
Token ID995
Feature activation-1.64e+00

Pos logit contributions
mun+0.079
 And+0.076
 having+0.071
 continuing+0.069
 enjoying+0.069
Neg logit contributions
eware-0.122
 upwards-0.113
isable-0.113
 knob-0.113
 nearer-0.113
Token.
Token ID13
Feature activation-7.85e-01

Pos logit contributions
mun+0.064
Che+0.062
 And+0.057
rob+0.056
 Evan+0.055
Neg logit contributions
eware-0.049
angs-0.049
out-0.049
 upwards-0.045
nob-0.044
Token<|endoftext|>
Token ID50256
Feature activation+4.52e-01

Pos logit contributions
mun+0.025
 sidelines+0.023
 enjoying+0.022
 chatting+0.022
 wedding+0.022
Neg logit contributions
eware-0.028
angs-0.026
 Knife-0.026
ricanes-0.026
ray-0.026
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
Che+0.097
rob+0.096
mun+0.095
 sidelines+0.093
 continuing+0.093
Neg logit contributions
eware-0.084
angs-0.079
 ok-0.076
out-0.075
ups-0.073
Token You
Token ID921
Feature activation+1.57e-01

Pos logit contributions
mun+0.028
rob+0.025
 riding+0.025
 enjoying+0.025
 playing+0.025
Neg logit contributions
eware-0.071
angs-0.066
ricanes-0.064
 knob-0.061
 nearer-0.061
Token are
Token ID389
Feature activation-3.33e+00

Pos logit contributions
eware+0.007
angs+0.006
ricanes+0.006
 nearer+0.006
 knob+0.006
Neg logit contributions
mun-0.005
 And-0.004
 playing-0.004
 riding-0.004
 enjoying-0.004
Token our
Token ID674
Feature activation-1.95e+00

Pos logit contributions
mun+0.123
rob+0.114
Che+0.112
oc+0.111
 And+0.110
Neg logit contributions
eware-0.109
angs-0.105
 nearer-0.098
 knob-0.097
isable-0.096
Token best
Token ID1266
Feature activation-5.08e+00

Pos logit contributions
mun+0.070
rob+0.069
 continuing+0.066
 riding+0.065
 enjoying+0.064
Neg logit contributions
eware-0.068
angs-0.062
 knob-0.060
 nearer-0.057
ricanes-0.056
Token girl
Token ID2576
Feature activation-8.49e+00

Pos logit contributions
mun+0.215
rob+0.202
 continuing+0.200
 enjoying+0.199
Che+0.199
Neg logit contributions
eware-0.152
angs-0.137
 knob-0.123
 nearer-0.120
ricanes-0.119
Token."
Token ID526
Feature activation-1.20e+00

Pos logit contributions
mun+0.258
Che+0.242
 continuing+0.241
rob+0.234
 enjoying+0.233
Neg logit contributions
eware-0.344
angs-0.323
ricanes-0.293
 knob-0.292
 nearer-0.291
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
rob+0.041
 sailing+0.037
 carn+0.036
mun+0.035
 riding+0.035
Neg logit contributions
eware-0.040
 wider-0.039
 Knife-0.039
 half-0.038
ups-0.037
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
rob+0.042
 sailing+0.042
 celebrating+0.041
 continuing+0.041
mun+0.041
Neg logit contributions
 closer-0.033
 half-0.033
out-0.032
 wider-0.032
ups-0.032
TokenAnna
Token ID31160
Feature activation-8.70e-01

Pos logit contributions
 sailing+0.050
 riding+0.049
 playing+0.049
 enjoying+0.048
rob+0.048
Neg logit contributions
ups-0.020
 tighter-0.019
out-0.019
eware-0.018
 half-0.018
Token smiled
Token ID13541
Feature activation-3.17e-01

Pos logit contributions
mun+0.031
rob+0.030
 riding+0.030
 Have+0.030
 continuing+0.029
Neg logit contributions
eware-0.028
angs-0.025
 knob-0.024
 nearer-0.024
isable-0.024
Token thinking
Token ID3612
Feature activation-1.12e-01

Pos logit contributions
mun+0.027
rob+0.027
oc+0.024
 town+0.023
 rh+0.023
Neg logit contributions
eware-0.035
 nearer-0.034
 closer-0.034
 upwards-0.034
 wider-0.034
Token it
Token ID340
Feature activation+3.53e+00

Pos logit contributions
mun+0.003
 And+0.003
 playing+0.003
 enjoying+0.003
 riding+0.003
Neg logit contributions
eware-0.005
angs-0.005
ricanes-0.004
 nearer-0.004
isable-0.004
Token was
Token ID373
Feature activation-1.74e+00

Pos logit contributions
eware+0.164
angs+0.157
ricanes+0.145
 nearer+0.143
isable+0.142
Neg logit contributions
mun-0.087
 And-0.084
 enjoying-0.083
 playing-0.083
 having-0.082
Token the
Token ID262
Feature activation-3.15e+00

Pos logit contributions
mun+0.048
 playing+0.047
 enjoying+0.047
 And+0.047
 having+0.047
Neg logit contributions
eware-0.076
angs-0.071
ricanes-0.066
 nearer-0.065
isable-0.064
Token happiest
Token ID49414
Feature activation-5.77e+00

Pos logit contributions
mun+0.107
 And+0.104
 riding+0.101
 playing+0.101
 enjoying+0.100
Neg logit contributions
eware-0.115
angs-0.106
 nearer-0.101
 knob-0.098
ricanes-0.098
Token day
Token ID1110
Feature activation-8.48e+00

Pos logit contributions
mun+0.178
rob+0.176
 And+0.174
oc+0.170
Che+0.170
Neg logit contributions
eware-0.220
angs-0.200
 knob-0.199
 nearer-0.199
 upwards-0.194
Token of
Token ID286
Feature activation-5.01e+00

Pos logit contributions
mun+0.277
rob+0.273
 rh+0.258
oc+0.257
Che+0.252
Neg logit contributions
eware-0.330
angs-0.300
out-0.288
 nearer-0.285
 knob-0.285
Token all
Token ID477
Feature activation-1.19e+00

Pos logit contributions
oc+0.181
mun+0.167
Che+0.166
rob+0.165
 And+0.163
Neg logit contributions
angs-0.167
 nearer-0.166
 knob-0.162
eware-0.162
 closer-0.161
Token.
Token ID13
Feature activation-7.33e-01

Pos logit contributions
Che+0.041
mun+0.040
rob+0.039
 And+0.039
 rh+0.038
Neg logit contributions
out-0.040
eware-0.039
angs-0.039
 nearer-0.039
 upwards-0.039
Token Her
Token ID2332
Feature activation+5.82e-01

Pos logit contributions
rob+0.016
mun+0.015
 pengu+0.015
 rh+0.014
 sailing+0.014
Neg logit contributions
eware-0.035
angs-0.033
ricanes-0.032
 upwards-0.032
piece-0.032
Token mom
Token ID1995
Feature activation+1.05e+00

Pos logit contributions
eware+0.018
 knob+0.016
angs+0.016
 nearer+0.015
ricanes+0.015
Neg logit contributions
mun-0.023
rob-0.023
 And-0.021
Che-0.021
Have-0.021
TokenHonest
Token ID37411
Feature activation+1.15e+00

Pos logit contributions
eware+0.010
angs+0.009
 nearer+0.009
ricanes+0.009
 upwards+0.009
Neg logit contributions
mun-0.007
 playing-0.007
 And-0.007
 enjoying-0.006
 riding-0.006
Token friends
Token ID2460
Feature activation-5.32e+00

Pos logit contributions
eware+0.043
angs+0.040
ricanes+0.036
 nearer+0.036
 knob+0.035
Neg logit contributions
mun-0.039
 And-0.038
 enjoying-0.037
 riding-0.037
 playing-0.037
Token are
Token ID389
Feature activation-3.78e+00

Pos logit contributions
mun+0.196
rob+0.189
Che+0.184
 And+0.182
 continuing+0.182
Neg logit contributions
eware-0.180
angs-0.162
 knob-0.152
 nearer-0.149
ricanes-0.149
Token the
Token ID262
Feature activation-3.86e+00

Pos logit contributions
mun+0.124
 And+0.115
rob+0.113
Che+0.112
 enjoying+0.111
Neg logit contributions
eware-0.146
angs-0.137
 nearer-0.128
ricanes-0.126
 knob-0.125
Token best
Token ID1266
Feature activation-5.38e+00

Pos logit contributions
mun+0.114
 playing+0.109
 enjoying+0.109
 And+0.108
 having+0.108
Neg logit contributions
eware-0.163
angs-0.153
ricanes-0.142
 nearer-0.139
isable-0.137
Token friends
Token ID2460
Feature activation-8.48e+00

Pos logit contributions
mun+0.169
 And+0.158
 enjoying+0.156
 riding+0.154
rob+0.154
Neg logit contributions
eware-0.218
angs-0.203
 nearer-0.187
 knob-0.186
ricanes-0.186
Token!".
Token ID48220
Feature activation-3.03e-01

Pos logit contributions
mun+0.324
Che+0.319
rob+0.292
 continuing+0.289
 sidelines+0.289
Neg logit contributions
eware-0.285
angs-0.264
out-0.239
 nearer-0.237
 knob-0.232
Token<|endoftext|>
Token ID50256
Feature activation+6.69e-01

Pos logit contributions
rob+0.008
mun+0.008
 wedding+0.008
 rh+0.007
Che+0.007
Neg logit contributions
eware-0.013
 Judy-0.012
 nearer-0.012
piece-0.012
 Knife-0.012
TokenA
Token ID32
Feature activation+4.49e+00

Pos logit contributions
eware+0.028
angs+0.026
 nearer+0.025
nob+0.025
 upwards+0.024
Neg logit contributions
 sidelines-0.018
 wedding-0.018
mun-0.018
Che-0.018
 continuing-0.017
Token little
Token ID1310
Feature activation-4.74e-01

Pos logit contributions
eware+0.194
right+0.166
ricanes+0.165
 knob+0.164
angs+0.162
Neg logit contributions
mun-0.133
 having-0.122
 riding-0.118
 enjoying-0.118
 continuing-0.118
Token boy
Token ID2933
Feature activation-3.14e+00

Pos logit contributions
mun+0.013
 And+0.012
 continuing+0.012
 having+0.012
Have+0.012
Neg logit contributions
eware-0.020
 knob-0.018
angs-0.018
ricanes-0.018
 nearer-0.017
TokenYou
Token ID1639
Feature activation-1.09e+00

Pos logit contributions
mun+0.000
 playing+0.000
 And+0.000
 riding+0.000
 enjoying+0.000
Neg logit contributions
eware-0.001
angs-0.001
ricanes-0.001
 nearer-0.001
isable-0.001
Token're
Token ID821
Feature activation-2.54e+00

Pos logit contributions
 And+0.024
mun+0.023
 playing+0.023
 having+0.023
 were+0.023
Neg logit contributions
eware-0.053
angs-0.051
ricanes-0.048
 nearer-0.048
isable-0.047
Token such
Token ID884
Feature activation-3.19e+00

Pos logit contributions
mun+0.071
 And+0.067
 playing+0.066
 enjoying+0.066
 riding+0.066
Neg logit contributions
eware-0.110
angs-0.104
ricanes-0.096
 nearer-0.096
 knob-0.095
Token a
Token ID257
Feature activation-3.43e+00

Pos logit contributions
mun+0.107
 And+0.101
 enjoying+0.100
 playing+0.100
 riding+0.100
Neg logit contributions
eware-0.120
angs-0.112
 nearer-0.102
ricanes-0.102
isable-0.100
Token good
Token ID922
Feature activation-2.89e+00

Pos logit contributions
mun+0.106
rob+0.099
 riding+0.098
 having+0.097
 playing+0.096
Neg logit contributions
eware-0.137
angs-0.124
 nearer-0.120
isable-0.119
 knob-0.119
Token girl
Token ID2576
Feature activation-8.46e+00

Pos logit contributions
mun+0.092
 And+0.088
 playing+0.087
 enjoying+0.087
 riding+0.086
Neg logit contributions
eware-0.115
angs-0.108
ricanes-0.099
 nearer-0.099
isable-0.097
Token,
Token ID11
Feature activation-2.03e+00

Pos logit contributions
mun+0.246
 continuing+0.227
 enjoying+0.225
Che+0.224
 riding+0.224
Neg logit contributions
eware-0.356
angs-0.333
ricanes-0.306
 nearer-0.305
 knob-0.304
Token Lily
Token ID20037
Feature activation-2.43e+00

Pos logit contributions
mun+0.061
rob+0.057
 continuing+0.055
 riding+0.054
 enjoying+0.054
Neg logit contributions
eware-0.083
angs-0.076
 knob-0.073
ricanes-0.072
 nearer-0.072
Token."
Token ID526
Feature activation-1.12e+00

Pos logit contributions
mun+0.077
Che+0.073
 continuing+0.072
rob+0.072
 riding+0.072
Neg logit contributions
eware-0.091
angs-0.085
 knob-0.080
out-0.078
ricanes-0.078
Token Lily
Token ID20037
Feature activation-5.51e-01

Pos logit contributions
rob+0.036
 rh+0.032
mun+0.032
 pengu+0.032
 gor+0.032
Neg logit contributions
eware-0.044
outed-0.042
piece-0.041
tr-0.041
ricanes-0.041
Token smiled
Token ID13541
Feature activation-1.10e+00

Pos logit contributions
mun+0.018
 Have+0.017
rob+0.017
 riding+0.017
 continuing+0.017
Neg logit contributions
eware-0.019
angs-0.018
isable-0.017
 knob-0.017
 nearer-0.017
Token "
Token ID366
Feature activation+3.42e-01

Pos logit contributions
eware+0.015
 closer+0.014
 nearer+0.014
 upwards+0.014
piece+0.013
Neg logit contributions
mun-0.012
rob-0.011
 pengu-0.009
 sidelines-0.009
 concerts-0.009
TokenThis
Token ID1212
Feature activation-1.73e+00

Pos logit contributions
eware+0.011
 nearer+0.010
ricanes+0.010
 upwards+0.010
pot+0.009
Neg logit contributions
 playing-0.012
 enjoying-0.012
 sailing-0.011
 having-0.011
 riding-0.011
Token is
Token ID318
Feature activation-1.97e+00

Pos logit contributions
mun+0.060
 enjoying+0.059
Che+0.058
 continuing+0.058
 And+0.058
Neg logit contributions
eware-0.061
angs-0.054
 knob-0.053
 nearer-0.052
ricanes-0.050
Token the
Token ID262
Feature activation-3.86e+00

Pos logit contributions
 And+0.051
 playing+0.051
 having+0.051
 enjoying+0.050
mun+0.050
Neg logit contributions
eware-0.089
angs-0.085
ricanes-0.078
 nearer-0.077
isable-0.077
Token best
Token ID1266
Feature activation-5.31e+00

Pos logit contributions
mun+0.127
 And+0.122
oc+0.118
 continuing+0.118
 enjoying+0.117
Neg logit contributions
eware-0.142
angs-0.131
 knob-0.128
 nearer-0.127
ricanes-0.123
Token day
Token ID1110
Feature activation-8.45e+00

Pos logit contributions
mun+0.187
Che+0.187
rob+0.175
 continuing+0.170
Have+0.168
Neg logit contributions
eware-0.191
 knob-0.171
angs-0.162
 nearer-0.159
out-0.154
Token ever
Token ID1683
Feature activation-1.13e+00

Pos logit contributions
mun+0.297
rob+0.281
Che+0.275
 continuing+0.262
 rh+0.259
Neg logit contributions
eware-0.327
angs-0.283
out-0.267
 nearer-0.259
 closer-0.259
Token.
Token ID13
Feature activation-1.84e+00

Pos logit contributions
mun+0.042
Che+0.041
 continuing+0.039
 riding+0.039
 sidelines+0.039
Neg logit contributions
eware-0.040
angs-0.035
out-0.033
 nearer-0.032
 closer-0.031
Token We
Token ID775
Feature activation-1.30e+00

Pos logit contributions
mun+0.050
 enjoying+0.045
 playing+0.045
 continuing+0.044
 riding+0.044
Neg logit contributions
eware-0.085
angs-0.076
ricanes-0.074
 Knife-0.070
adoes-0.069
Token love
Token ID1842
Feature activation-1.51e+00

Pos logit contributions
mun+0.033
 riding+0.031
 And+0.031
 playing+0.031
 enjoying+0.030
Neg logit contributions
eware-0.058
angs-0.055
ricanes-0.052
 nearer-0.051
 knob-0.051
Token these
Token ID777
Feature activation-9.18e-01

Pos logit contributions
mun+0.059
he+0.057
oc+0.056
rob+0.056
Che+0.056
Neg logit contributions
eware-0.047
 closer-0.041
angs-0.041
ricanes-0.039
 nearer-0.039
Token scared
Token ID12008
Feature activation+2.03e+00

Pos logit contributions
 having+0.037
 playing+0.037
 enjoying+0.036
 riding+0.035
mun+0.033
Neg logit contributions
eware-0.057
angs-0.052
ricanes-0.051
 nearer-0.048
 knob-0.048
Token.
Token ID13
Feature activation+9.26e-02

Pos logit contributions
eware+0.082
angs+0.081
 nearer+0.073
 upwards+0.072
out+0.072
Neg logit contributions
mun-0.063
rob-0.061
Che-0.060
 Have-0.056
 rh-0.056
Token But
Token ID887
Feature activation+2.35e+00

Pos logit contributions
eware+0.005
angs+0.004
ricanes+0.004
 Knife+0.004
 nearer+0.004
Neg logit contributions
mun-0.002
 enjoying-0.002
 continuing-0.002
rob-0.002
Che-0.002
Token he
Token ID339
Feature activation-9.78e-01

Pos logit contributions
eware+0.111
angs+0.104
 nearer+0.099
ricanes+0.098
 knob+0.097
Neg logit contributions
mun-0.057
 And-0.052
 enjoying-0.051
 riding-0.051
 playing-0.050
Token could
Token ID714
Feature activation+4.87e-01

Pos logit contributions
 playing+0.024
 were+0.023
 enjoying+0.023
 And+0.023
 having+0.023
Neg logit contributions
eware-0.048
angs-0.046
ricanes-0.044
 upwards-0.043
adoes-0.042
Token not
Token ID407
Feature activation+6.08e+00

Pos logit contributions
eware+0.014
angs+0.013
ricanes+0.012
 upwards+0.011
 nearer+0.011
Neg logit contributions
 playing-0.020
 enjoying-0.020
 having-0.020
mun-0.020
 riding-0.020
Token stop
Token ID2245
Feature activation+1.46e+00

Pos logit contributions
eware+0.278
angs+0.261
ricanes+0.245
 nearer+0.240
 upwards+0.238
Neg logit contributions
mun-0.152
 And-0.150
 playing-0.149
 enjoying-0.148
 having-0.146
Token shrinking
Token ID27382
Feature activation+1.91e+00

Pos logit contributions
angs+0.052
 closer+0.051
 nearer+0.050
eware+0.048
 upwards+0.048
Neg logit contributions
rob-0.052
mun-0.051
oun-0.048
 Have-0.047
oc-0.046
Token.
Token ID13
Feature activation-2.53e-01

Pos logit contributions
eware+0.080
angs+0.078
 nearer+0.072
 knob+0.071
 upwards+0.071
Neg logit contributions
mun-0.056
Che-0.051
 And-0.051
rob-0.050
 Have-0.050
Token Tim
Token ID5045
Feature activation-1.15e-01

Pos logit contributions
mun+0.006
rob+0.005
 enjoying+0.005
 continuing+0.005
 couple+0.005
Neg logit contributions
eware-0.013
angs-0.012
ricanes-0.011
 Knife-0.011
 nearer-0.011
Token got
Token ID1392
Feature activation+1.45e+00

Pos logit contributions
mun+0.003
 playing+0.003
 And+0.003
 enjoying+0.003
 having+0.003
Neg logit contributions
eware-0.005
angs-0.005
ricanes-0.004
 nearer-0.004
 upwards-0.004
Token and
Token ID290
Feature activation+2.08e-01

Pos logit contributions
 And+0.022
mun+0.022
rob+0.021
oc+0.020
Che+0.020
Neg logit contributions
 closer-0.022
 nearer-0.022
eware-0.021
 upwards-0.021
 knob-0.021
Token people
Token ID661
Feature activation-1.33e+00

Pos logit contributions
eware+0.009
angs+0.008
 knob+0.008
 nearer+0.008
ricanes+0.008
Neg logit contributions
mun-0.006
 And-0.006
Che-0.005
rob-0.005
 continuing-0.005
Token.
Token ID13
Feature activation+1.53e-01

Pos logit contributions
 And+0.048
rob+0.048
 Have+0.045
Che+0.044
oun+0.044
Neg logit contributions
 closer-0.045
angs-0.044
 nearer-0.043
 knob-0.043
 upwards-0.042
Token He
Token ID679
Feature activation-1.08e+00

Pos logit contributions
eware+0.007
angs+0.007
 Knife+0.007
 upwards+0.006
ricanes+0.006
Neg logit contributions
mun-0.004
rob-0.004
 celebrating-0.004
 continuing-0.004
 riding-0.004
Token did
Token ID750
Feature activation-2.96e-01

Pos logit contributions
mun+0.033
 playing+0.031
 And+0.031
 enjoying+0.031
 riding+0.031
Neg logit contributions
eware-0.044
angs-0.041
ricanes-0.038
 nearer-0.038
 upwards-0.037
Token not
Token ID407
Feature activation+5.94e+00

Pos logit contributions
mun+0.015
 And+0.015
rob+0.015
 enjoying+0.014
Che+0.014
Neg logit contributions
eware-0.006
angs-0.005
 nearer-0.004
ricanes-0.004
 knob-0.004
Token hear
Token ID3285
Feature activation+1.77e-01

Pos logit contributions
eware+0.256
angs+0.245
 nearer+0.230
 knob+0.224
ricanes+0.223
Neg logit contributions
mun-0.174
rob-0.159
 And-0.158
 continuing-0.154
 enjoying-0.153
Token his
Token ID465
Feature activation+1.42e+00

Pos logit contributions
angs+0.007
eware+0.007
out+0.006
 prick+0.006
 knob+0.006
Neg logit contributions
mun-0.006
rob-0.006
Che-0.005
 continuing-0.005
Have-0.005
Token mom
Token ID1995
Feature activation+1.62e+00

Pos logit contributions
eware+0.044
angs+0.041
 knob+0.038
 nearer+0.036
ricanes+0.035
Neg logit contributions
mun-0.058
rob-0.055
 And-0.055
 Have-0.054
Che-0.054
Token calling
Token ID4585
Feature activation-1.65e+00

Pos logit contributions
angs+0.047
 closer+0.045
 knob+0.043
 locked+0.042
 nearer+0.042
Neg logit contributions
rob-0.069
oun-0.065
 couple-0.064
mun-0.064
 Evan-0.062
Token him
Token ID683
Feature activation+1.17e+00

Pos logit contributions
mun+0.040
rob+0.039
Che+0.034
 enjoying+0.033
 Have+0.033
Neg logit contributions
eware-0.079
angs-0.077
 nearer-0.074
 upwards-0.073
 knob-0.073
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
mun+0.030
 And+0.028
Che+0.027
rob+0.027
 continuing+0.026
Neg logit contributions
eware-0.036
angs-0.035
 knob-0.031
adoes-0.031
 nearer-0.031
Token TV
Token ID3195
Feature activation-9.86e-01

Pos logit contributions
mun+0.033
 And+0.031
 continuing+0.030
Che+0.030
 riding+0.030
Neg logit contributions
eware-0.040
angs-0.038
 knob-0.036
ricanes-0.035
 nearer-0.035
Token.
Token ID13
Feature activation-3.01e-01

Pos logit contributions
mun+0.030
Che+0.027
 continuing+0.027
rob+0.027
 riding+0.027
Neg logit contributions
eware-0.040
angs-0.038
 knob-0.035
ricanes-0.035
out-0.035
Token He
Token ID679
Feature activation-1.47e+00

Pos logit contributions
mun+0.006
 enjoying+0.005
 continuing+0.005
 playing+0.005
rob+0.005
Neg logit contributions
eware-0.016
angs-0.015
ricanes-0.014
 Knife-0.014
 nearer-0.014
Token can
Token ID460
Feature activation+1.87e+00

Pos logit contributions
mun+0.055
 continuing+0.054
Che+0.053
 riding+0.053
 enjoying+0.052
Neg logit contributions
eware-0.048
angs-0.045
ricanes-0.040
 knob-0.040
 nearer-0.039
Token't
Token ID470
Feature activation+6.84e+00

Pos logit contributions
eware+0.075
angs+0.071
 nearer+0.067
ricanes+0.066
 knob+0.066
Neg logit contributions
mun-0.056
 And-0.054
 enjoying-0.051
 riding-0.051
 playing-0.051
Token hurt
Token ID5938
Feature activation+2.76e+00

Pos logit contributions
eware+0.253
angs+0.230
 nearer+0.225
 closer+0.225
 knob+0.220
Neg logit contributions
mun-0.235
rob-0.225
 And-0.218
 celebrating-0.209
 riding-0.207
Token you
Token ID345
Feature activation+9.72e-01

Pos logit contributions
eware+0.111
angs+0.106
 nearer+0.098
 upwards+0.095
 closer+0.094
Neg logit contributions
mun-0.085
Che-0.081
rob-0.080
 continuing-0.080
 And-0.078
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
eware+0.041
angs+0.039
 nearer+0.036
ricanes+0.036
 knob+0.035
Neg logit contributions
mun-0.028
 And-0.027
 enjoying-0.026
 playing-0.026
 riding-0.026
Token You
Token ID921
Feature activation+8.01e-01

Pos logit contributions
mun+0.005
 enjoying+0.004
 playing+0.004
 continuing+0.004
 riding+0.004
Neg logit contributions
eware-0.013
angs-0.012
ricanes-0.012
 nearer-0.011
 Knife-0.011
Token are
Token ID389
Feature activation-2.90e+00

Pos logit contributions
eware+0.035
angs+0.033
ricanes+0.030
 nearer+0.030
 knob+0.030
Neg logit contributions
mun-0.022
 And-0.021
 enjoying-0.021
 playing-0.021
 riding-0.021
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
eware+0.099
angs+0.092
ricanes+0.084
 nearer+0.083
 upwards+0.079
Neg logit contributions
 playing-0.068
mun-0.066
 having-0.066
 And-0.065
 enjoying-0.065
Token house
Token ID2156
Feature activation-4.99e-01

Pos logit contributions
 playing+0.035
 town+0.033
 having+0.033
 And+0.033
 riding+0.033
Neg logit contributions
eware-0.041
angs-0.040
 nearer-0.037
ricanes-0.035
leys-0.033
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
 having+0.010
 playing+0.009
 And+0.009
 enjoying+0.009
 riding+0.008
Neg logit contributions
eware-0.027
angs-0.026
ricanes-0.023
 nearer-0.023
isable-0.023
Token Lily
Token ID20037
Feature activation+5.89e-01

Pos logit contributions
eware+0.058
angs+0.053
ricanes+0.052
 upwards+0.051
 knob+0.051
Neg logit contributions
mun-0.033
rob-0.031
 rh-0.031
 riding-0.031
 pengu-0.030
Token didn
Token ID1422
Feature activation+3.61e+00

Pos logit contributions
angs+0.032
eware+0.031
 nearer+0.029
 upwards+0.028
ricanes+0.028
Neg logit contributions
 And-0.013
mun-0.013
 playing-0.012
 were-0.012
 happily-0.012
Token't
Token ID470
Feature activation+6.55e+00

Pos logit contributions
eware+0.153
angs+0.144
ricanes+0.133
 nearer+0.133
 knob+0.131
Neg logit contributions
mun-0.104
 And-0.098
 enjoying-0.097
 playing-0.097
 riding-0.096
Token want
Token ID765
Feature activation+4.45e-01

Pos logit contributions
eware+0.302
angs+0.290
ricanes+0.270
 nearer+0.265
adoes+0.264
Neg logit contributions
 And-0.165
 having-0.161
 playing-0.159
mun-0.158
 enjoying-0.158
Token to
Token ID284
Feature activation+1.32e+00

Pos logit contributions
rated+0.023
eware+0.023
angs+0.021
leys+0.021
ffic+0.021
Neg logit contributions
 playing-0.013
 having-0.011
-0.011
 riding-0.010
 And-0.010
Token stop
Token ID2245
Feature activation+1.90e+00

Pos logit contributions
eware+0.055
angs+0.054
ricanes+0.048
 nearer+0.048
 upwards+0.047
Neg logit contributions
 playing-0.041
 And-0.039
 enjoying-0.039
 having-0.039
 riding-0.038
Token playing
Token ID2712
Feature activation-4.45e+00

Pos logit contributions
 knob+0.077
eware+0.075
angs+0.073
 ok+0.072
 Knife+0.071
Neg logit contributions
rob-0.055
mun-0.053
oc-0.050
 rh-0.048
 Have-0.047
Token with
Token ID351
Feature activation-1.34e+00

Pos logit contributions
mun+0.122
rob+0.110
 And+0.109
Che+0.108
 rh+0.108
Neg logit contributions
eware-0.192
angs-0.181
 knob-0.173
ricanes-0.171
 nearer-0.171
Tokenly
Token ID306
Feature activation-1.45e+00

Pos logit contributions
eware+0.042
angs+0.038
 upwards+0.036
out+0.036
 nearer+0.035
Neg logit contributions
mun-0.055
rob-0.055
Che-0.054
 continuing-0.052
Have-0.052
Token,
Token ID11
Feature activation-1.44e-01

Pos logit contributions
rob+0.049
mun+0.049
Che+0.044
Have+0.043
 continuing+0.043
Neg logit contributions
eware-0.056
angs-0.053
 upwards-0.049
 nearer-0.049
 knob-0.048
Token but
Token ID475
Feature activation+1.43e+00

Pos logit contributions
mun+0.005
rob+0.005
oun+0.004
 Evan+0.004
Che+0.004
Neg logit contributions
eware-0.005
 nearer-0.005
angs-0.005
 closer-0.005
 prick-0.005
Token it
Token ID340
Feature activation+3.79e+00

Pos logit contributions
eware+0.052
 nearer+0.047
 closer+0.045
angs+0.045
 upwards+0.044
Neg logit contributions
mun-0.049
rob-0.047
 And-0.046
Che-0.043
 riding-0.043
Token could
Token ID714
Feature activation+1.81e-01

Pos logit contributions
eware+0.158
angs+0.150
ricanes+0.140
 upwards+0.135
isable+0.134
Neg logit contributions
mun-0.112
 enjoying-0.108
 playing-0.107
 having-0.107
 And-0.107
Token not
Token ID407
Feature activation+5.56e+00

Pos logit contributions
eware+0.005
angs+0.004
 nearer+0.004
 knob+0.004
ricanes+0.004
Neg logit contributions
mun-0.008
rob-0.008
 And-0.008
 playing-0.008
 celebrating-0.008
Token win
Token ID1592
Feature activation-1.79e+00

Pos logit contributions
eware+0.209
 nearer+0.193
angs+0.189
 closer+0.182
 knob+0.180
Neg logit contributions
mun-0.195
rob-0.188
 And-0.179
 riding-0.173
 celebrating-0.172
Token.
Token ID13
Feature activation-8.99e-01

Pos logit contributions
mun+0.063
Che+0.059
rob+0.058
 And+0.056
 wedding+0.056
Neg logit contributions
eware-0.068
angs-0.063
 nearer-0.061
 closer-0.057
 upwards-0.057
Token In
Token ID554
Feature activation-4.20e-01

Pos logit contributions
mun+0.029
rob+0.027
 pengu+0.025
 wedding+0.025
 playing+0.024
Neg logit contributions
eware-0.037
right-0.033
 Knife-0.032
 ok-0.032
angs-0.032
Token the
Token ID262
Feature activation-3.51e-01

Pos logit contributions
mun+0.014
 And+0.013
Che+0.013
rob+0.012
oc+0.012
Neg logit contributions
eware-0.015
angs-0.014
 nearer-0.014
 knob-0.014
 prick-0.013
Token end
Token ID886
Feature activation-9.43e-01

Pos logit contributions
mun+0.012
 And+0.012
 riding+0.011
rob+0.011
 enjoying+0.011
Neg logit contributions
eware-0.013
angs-0.012
 nearer-0.011
 knob-0.011
isable-0.011
Token and
Token ID290
Feature activation+5.77e-01

Pos logit contributions
eware+0.008
angs+0.008
 nearer+0.008
 knob+0.008
 upwards+0.007
Neg logit contributions
mun-0.006
rob-0.005
 rh-0.005
 Have-0.005
Che-0.005
Token waited
Token ID13488
Feature activation-7.27e-02

Pos logit contributions
eware+0.021
angs+0.019
ricanes+0.017
 nearer+0.017
 knob+0.017
Neg logit contributions
mun-0.021
 And-0.020
 enjoying-0.020
 playing-0.020
 riding-0.019
Token,
Token ID11
Feature activation+4.50e-01

Pos logit contributions
mun+0.002
rob+0.002
 rh+0.002
Che+0.002
oc+0.002
Neg logit contributions
eware-0.003
angs-0.003
 knob-0.003
 nearer-0.003
 upwards-0.003
Token but
Token ID475
Feature activation+1.90e+00

Pos logit contributions
eware+0.016
 nearer+0.015
 knob+0.015
 upwards+0.015
 closer+0.015
Neg logit contributions
mun-0.015
rob-0.015
 rh-0.014
 pengu-0.013
oc-0.013
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
angs+0.103
eware+0.099
ricanes+0.089
iqu+0.087
iddle+0.086
Neg logit contributions
 playing-0.045
 enjoying-0.045
 having-0.043
 celebrating-0.040
 continuing-0.039
Token pie
Token ID2508
Feature activation+9.23e-01

Pos logit contributions
 playing+0.039
mun+0.039
 And+0.039
 having+0.038
 enjoying+0.038
Neg logit contributions
eware-0.053
angs-0.051
ricanes-0.046
 nearer-0.045
 upwards-0.045
Token didn
Token ID1422
Feature activation+2.55e+00

Pos logit contributions
eware+0.043
angs+0.041
ricanes+0.038
 nearer+0.037
isable+0.036
Neg logit contributions
mun-0.024
 enjoying-0.022
 playing-0.022
 having-0.022
 And-0.022
Token't
Token ID470
Feature activation+5.27e+00

Pos logit contributions
eware+0.107
angs+0.101
 nearer+0.093
ricanes+0.093
 knob+0.092
Neg logit contributions
mun-0.074
 And-0.070
 enjoying-0.069
 playing-0.069
 riding-0.068
Token seem
Token ID1283
Feature activation+2.51e+00

Pos logit contributions
eware+0.215
angs+0.204
ricanes+0.188
isable+0.184
 nearer+0.183
Neg logit contributions
mun-0.156
 enjoying-0.155
 playing-0.153
 having-0.153
 And-0.151
Token to
Token ID284
Feature activation-9.02e-02

Pos logit contributions
eware+0.094
angs+0.090
ricanes+0.084
isable+0.079
adoes+0.078
Neg logit contributions
 enjoying-0.085
 having-0.085
 playing-0.084
 riding-0.080
 And-0.079
Token cool
Token ID3608
Feature activation+1.20e+00

Pos logit contributions
mun+0.003
 And+0.003
rob+0.003
 riding+0.003
 playing+0.003
Neg logit contributions
eware-0.004
angs-0.003
 nearer-0.003
 knob-0.003
ricanes-0.003
Token,
Token ID11
Feature activation+8.71e-01

Pos logit contributions
 playing+0.078
mun+0.076
 And+0.075
 riding+0.073
 enjoying+0.072
Neg logit contributions
eware-0.202
angs-0.199
isable-0.186
ricanes-0.186
 nearer-0.182
Token they
Token ID484
Feature activation-1.08e+00

Pos logit contributions
angs+0.055
eware+0.054
isable+0.051
iddle+0.051
ricanes+0.050
Neg logit contributions
 playing-0.009
 having-0.008
 were-0.007
 enjoying-0.007
 riding-0.007
Token saw
Token ID2497
Feature activation+1.32e+00

Pos logit contributions
mun+0.027
 playing+0.026
 And+0.026
 enjoying+0.026
 having+0.026
Neg logit contributions
eware-0.050
angs-0.047
ricanes-0.044
 nearer-0.044
 upwards-0.043
Token a
Token ID257
Feature activation+6.35e-01

Pos logit contributions
eware+0.064
angs+0.059
ricanes+0.056
rated+0.055
 upwards+0.055
Neg logit contributions
 playing-0.036
 having-0.033
 riding-0.032
 And-0.032
 rh-0.031
Token big
Token ID1263
Feature activation+6.93e-01

Pos logit contributions
eware+0.024
angs+0.023
ricanes+0.021
 nearer+0.021
 knob+0.021
Neg logit contributions
mun-0.021
 And-0.020
 enjoying-0.020
 playing-0.020
 riding-0.019
Token box
Token ID3091
Feature activation+1.64e+00

Pos logit contributions
eware+0.024
angs+0.023
 knob+0.021
ricanes+0.021
 nearer+0.021
Neg logit contributions
mun-0.025
 And-0.024
 enjoying-0.023
 having-0.023
 riding-0.023
Token in
Token ID287
Feature activation-9.36e-01

Pos logit contributions
eware+0.073
angs+0.070
ricanes+0.065
 nearer+0.065
 knob+0.064
Neg logit contributions
mun-0.043
 And-0.040
 enjoying-0.039
 playing-0.039
 riding-0.039
Token the
Token ID262
Feature activation-7.63e-01

Pos logit contributions
mun+0.018
 And+0.017
 playing+0.017
 having+0.017
 riding+0.017
Neg logit contributions
eware-0.049
angs-0.047
ricanes-0.044
 nearer-0.043
isable-0.043
Token living
Token ID2877
Feature activation-3.95e+00

Pos logit contributions
mun+0.020
 And+0.019
 playing+0.019
 riding+0.019
 enjoying+0.019
Neg logit contributions
eware-0.035
angs-0.033
 nearer-0.031
ricanes-0.030
isable-0.029
Token room
Token ID2119
Feature activation-7.41e-01

Pos logit contributions
 town+0.112
 playing+0.105
 And+0.101
 having+0.100
 enjoying+0.099
Neg logit contributions
eware-0.186
angs-0.172
 nearer-0.160
ricanes-0.158
iqu-0.155
Token.
Token ID13
Feature activation+5.09e-01

Pos logit contributions
mun+0.016
 And+0.016
 playing+0.016
 enjoying+0.015
 riding+0.015
Neg logit contributions
eware-0.036
angs-0.034
ricanes-0.032
 nearer-0.032
isable-0.032
TokenOh
Token ID5812
Feature activation+2.00e+00

Pos logit contributions
eware+0.129
angs+0.126
ricanes+0.112
 nearer+0.111
 knob+0.110
Neg logit contributions
mun-0.081
Che-0.078
Have-0.077
 And-0.076
 enjoying-0.074
Token no
Token ID645
Feature activation+2.34e+00

Pos logit contributions
eware+0.092
angs+0.091
ricanes+0.086
 upwards+0.084
isable+0.083
Neg logit contributions
 playing-0.051
 And-0.050
 enjoying-0.047
mun-0.046
 having-0.046
Token,"
Token ID553
Feature activation-2.31e+00

Pos logit contributions
eware+0.096
angs+0.089
 nearer+0.084
 knob+0.083
ricanes+0.081
Neg logit contributions
mun-0.071
 And-0.068
 enjoying-0.066
 having-0.065
 riding-0.065
Token Ben
Token ID3932
Feature activation-1.56e-01

Pos logit contributions
mun+0.076
 riding+0.072
 continuing+0.072
 enjoying+0.072
rob+0.072
Neg logit contributions
eware-0.085
angs-0.079
 nearer-0.075
ricanes-0.074
 knob-0.074
Token said
Token ID531
Feature activation-1.88e+00

Pos logit contributions
mun+0.004
 And+0.004
 playing+0.004
 enjoying+0.004
 having+0.004
Neg logit contributions
eware-0.007
angs-0.006
ricanes-0.006
 upwards-0.006
 nearer-0.006
Token.
Token ID13
Feature activation+4.05e-01

Pos logit contributions
mun+0.041
 And+0.040
 playing+0.039
 enjoying+0.039
 having+0.038
Neg logit contributions
eware-0.093
angs-0.088
ricanes-0.084
isable-0.081
 nearer-0.081
Token "
Token ID366
Feature activation+1.67e+00

Pos logit contributions
eware+0.017
angs+0.016
 nearer+0.015
 Knife+0.015
 knob+0.015
Neg logit contributions
mun-0.012
rob-0.012
 enjoying-0.011
 celebrating-0.011
 riding-0.011
TokenWe
Token ID1135
Feature activation-5.75e-01

Pos logit contributions
eware+0.066
angs+0.062
 nearer+0.057
ricanes+0.057
 Knife+0.057
Neg logit contributions
mun-0.053
 playing-0.051
 enjoying-0.050
 continuing-0.050
 celebrating-0.049
Token broke
Token ID6265
Feature activation+4.26e+00

Pos logit contributions
 were+0.014
 playing+0.014
 And+0.013
mun+0.013
 having+0.013
Neg logit contributions
eware-0.027
angs-0.025
 nearer-0.024
ricanes-0.024
 upwards-0.023
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
eware+0.223
angs+0.209
ricanes+0.198
iddle+0.193
isable+0.192
Neg logit contributions
 playing-0.092
 having-0.089
 enjoying-0.084
 town-0.083
 riding-0.082
Token window
Token ID4324
Feature activation+7.78e-01

Pos logit contributions
 playing+0.043
 enjoying+0.042
 riding+0.042
 rh+0.042
mun+0.042
Neg logit contributions
eware-0.045
angs-0.043
ricanes-0.039
 nearer-0.038
isable-0.037
Token the
Token ID262
Feature activation-8.65e-01

Pos logit contributions
eware+0.072
angs+0.068
ricanes+0.063
 nearer+0.062
isable+0.062
Neg logit contributions
mun-0.035
 And-0.034
 playing-0.034
 enjoying-0.033
 having-0.033
Token watch
Token ID2342
Feature activation-9.77e-01

Pos logit contributions
 And+0.025
 playing+0.025
 riding+0.025
 having+0.025
 enjoying+0.024
Neg logit contributions
eware-0.037
angs-0.034
ricanes-0.032
isable-0.031
 nearer-0.031
Token.
Token ID13
Feature activation+4.16e-01

Pos logit contributions
mun+0.027
 And+0.025
 enjoying+0.025
 playing+0.025
 riding+0.025
Neg logit contributions
eware-0.043
angs-0.040
ricanes-0.037
 nearer-0.037
 knob-0.037
Token
Token ID198
Feature activation-5.91e-01

Pos logit contributions
eware+0.020
angs+0.018
 upwards+0.017
piece+0.017
ricanes+0.017
Neg logit contributions
rob-0.010
mun-0.010
 wedding-0.010
 pengu-0.009
 concerts-0.009
Token
Token ID198
Feature activation-5.04e-01

Pos logit contributions
mun+0.014
 rh+0.013
 continuing+0.013
 celebrating+0.013
 sidelines+0.013
Neg logit contributions
eware-0.027
angs-0.025
nob-0.025
 nearer-0.024
out-0.024
TokenBut
Token ID1537
Feature activation+3.06e+00

Pos logit contributions
mun+0.016
 playing+0.015
 And+0.015
 enjoying+0.015
 riding+0.015
Neg logit contributions
eware-0.020
angs-0.018
 nearer-0.017
ricanes-0.017
isable-0.016
Token then
Token ID788
Feature activation-3.07e+00

Pos logit contributions
eware+0.145
angs+0.144
ricanes+0.132
isable+0.127
 upwards+0.127
Neg logit contributions
 playing-0.075
 having-0.073
 enjoying-0.072
 And-0.072
 riding-0.071
Token,
Token ID11
Feature activation+9.88e-01

Pos logit contributions
 playing+0.058
mun+0.056
 And+0.055
 riding+0.052
 enjoying+0.052
Neg logit contributions
eware-0.160
angs-0.159
ricanes-0.149
 upwards-0.146
isable-0.146
Token something
Token ID1223
Feature activation+4.75e+00

Pos logit contributions
eware+0.043
angs+0.041
ricanes+0.038
 upwards+0.037
isable+0.037
Neg logit contributions
mun-0.028
 playing-0.027
 And-0.027
 enjoying-0.027
 having-0.026
Token bad
Token ID2089
Feature activation+1.37e+00

Pos logit contributions
eware+0.187
angs+0.183
ricanes+0.166
 Knife+0.161
 upwards+0.160
Neg logit contributions
 playing-0.146
mun-0.143
 having-0.142
 enjoying-0.141
 were-0.141
Token happened
Token ID3022
Feature activation-1.23e+00

Pos logit contributions
eware+0.055
angs+0.053
 upwards+0.051
 nearer+0.051
ricanes+0.050
Neg logit contributions
 were-0.040
 playing-0.039
 And-0.037
 riding-0.037
 having-0.037
Tokenudd
Token ID4185
Feature activation+5.72e-01

Pos logit contributions
eware+0.116
 nearer+0.106
 ok+0.105
angs+0.102
 Knife+0.101
Neg logit contributions
 And-0.064
mun-0.062
 playing-0.061
 enjoying-0.056
 town-0.054
Tokenles
Token ID829
Feature activation-1.19e+00

Pos logit contributions
eware+0.024
angs+0.023
ricanes+0.021
 nearer+0.021
isable+0.021
Neg logit contributions
mun-0.017
 And-0.016
 playing-0.016
 enjoying-0.016
 riding-0.016
Token and
Token ID290
Feature activation+2.71e-01

Pos logit contributions
mun+0.036
rob+0.035
Che+0.033
 And+0.033
 Have+0.032
Neg logit contributions
eware-0.046
angs-0.045
out-0.043
 knob-0.043
 nearer-0.042
Token watch
Token ID2342
Feature activation-3.50e-01

Pos logit contributions
eware+0.012
angs+0.011
 nearer+0.011
 knob+0.011
ricanes+0.010
Neg logit contributions
mun-0.007
 And-0.007
rob-0.007
Che-0.006
 riding-0.006
Token the
Token ID262
Feature activation-7.10e-01

Pos logit contributions
mun+0.010
 Have+0.009
 And+0.009
 continuing+0.009
Che+0.009
Neg logit contributions
eware-0.014
angs-0.014
 knob-0.013
 upwards-0.013
 nearer-0.013
Token rain
Token ID6290
Feature activation+3.36e+00

Pos logit contributions
mun+0.023
 And+0.023
 continuing+0.022
 riding+0.022
rob+0.022
Neg logit contributions
eware-0.027
 knob-0.024
angs-0.024
 nearer-0.023
ricanes-0.023
Tokendrops
Token ID49253
Feature activation+7.13e-01

Pos logit contributions
eware+0.114
angs+0.107
 knob+0.098
 nearer+0.097
ricanes+0.096
Neg logit contributions
mun-0.122
 And-0.118
 Have-0.117
 Evan-0.116
 couple-0.115
Token fall
Token ID2121
Feature activation+3.25e+00

Pos logit contributions
eware+0.023
angs+0.022
 knob+0.022
 nearer+0.021
 upwards+0.021
Neg logit contributions
mun-0.027
 And-0.026
rob-0.025
oc-0.025
 Have-0.024
Token.
Token ID13
Feature activation+7.40e-01

Pos logit contributions
eware+0.121
angs+0.113
ricanes+0.104
 nearer+0.103
isable+0.101
Neg logit contributions
mun-0.109
 And-0.105
 playing-0.105
 enjoying-0.105
 riding-0.104
Token
Token ID198
Feature activation-2.39e-02

Pos logit contributions
eware+0.035
ricanes+0.032
angs+0.032
 knob+0.031
 Knife+0.031
Neg logit contributions
mun-0.017
 continuing-0.015
 couple-0.015
 celebrating-0.015
rob-0.015
Token
Token ID198
Feature activation+7.34e-02

Pos logit contributions
mun+0.000
 continuing+0.000
 enjoying+0.000
 rh+0.000
 celebrating+0.000
Neg logit contributions
eware-0.001
angs-0.001
 nearer-0.001
 closer-0.001
out-0.001
Token bit
Token ID1643
Feature activation+2.67e+00

Pos logit contributions
mun+0.156
rob+0.154
 riding+0.149
 playing+0.145
 And+0.144
Neg logit contributions
eware-0.125
angs-0.115
 nearer-0.113
 closer-0.108
isable-0.106
Token better
Token ID1365
Feature activation-2.44e+00

Pos logit contributions
eware+0.096
angs+0.091
 nearer+0.085
ricanes+0.082
isable+0.082
Neg logit contributions
mun-0.091
 And-0.088
 riding-0.087
 playing-0.087
rob-0.087
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
mun+0.083
rob+0.075
Che+0.073
 And+0.071
 rh+0.070
Neg logit contributions
eware-0.095
angs-0.087
 nearer-0.086
out-0.084
 closer-0.084
Token
Token ID220
Feature activation+1.98e+00

Pos logit contributions
mun+0.006
 wedding+0.005
rob+0.005
 celebrating+0.005
 couple+0.005
Neg logit contributions
eware-0.008
piece-0.008
ricanes-0.008
 Knife-0.008
ray-0.008
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
eware+0.092
angs+0.088
piece+0.083
 nearer+0.082
 upwards+0.081
Neg logit contributions
 wedding-0.049
 couple-0.047
mun-0.046
 pengu-0.045
rob-0.044
Token
Token ID198
Feature activation-9.24e-01

Pos logit contributions
 wedding+0.031
 rh+0.030
mun+0.030
 celebrating+0.029
 pengu+0.028
Neg logit contributions
eware-0.039
 nearer-0.038
nob-0.037
 closer-0.037
piece-0.036
TokenThe
Token ID464
Feature activation-5.11e-01

Pos logit contributions
mun+0.032
 playing+0.031
 enjoying+0.031
 celebrating+0.030
rob+0.030
Neg logit contributions
eware-0.032
angs-0.028
ricanes-0.028
 nearer-0.028
right-0.028
Token rabbit
Token ID22746
Feature activation-1.58e+00

Pos logit contributions
mun+0.017
 And+0.016
 riding+0.016
 enjoying+0.016
rob+0.016
Neg logit contributions
eware-0.019
angs-0.017
 knob-0.017
 nearer-0.017
ricanes-0.017
Token kept
Token ID4030
Feature activation-8.00e-01

Pos logit contributions
mun+0.049
rob+0.047
 riding+0.046
Che+0.045
 Have+0.045
Neg logit contributions
eware-0.060
angs-0.054
 nearer-0.053
ricanes-0.052
 knob-0.052
Token walking
Token ID6155
Feature activation-1.81e+00

Pos logit contributions
mun+0.022
 And+0.020
oun+0.020
Che+0.019
rob+0.019
Neg logit contributions
 nearer-0.034
 closer-0.033
eware-0.032
angs-0.032
 knob-0.032
Token and
Token ID290
Feature activation+2.90e-01

Pos logit contributions
mun+0.050
Che+0.046
rob+0.045
 riding+0.043
 celebrating+0.043
Neg logit contributions
eware-0.078
 nearer-0.076
 closer-0.074
 upwards-0.073
angs-0.073
Token right
Token ID826
Feature activation-2.18e-01

Pos logit contributions
mun+0.059
rob+0.055
 And+0.054
Che+0.053
 continuing+0.053
Neg logit contributions
eware-0.066
 knob-0.061
angs-0.061
 upwards-0.061
isable-0.060
Token places
Token ID4113
Feature activation-1.95e+00

Pos logit contributions
 town+0.006
 enjoying+0.006
 playing+0.006
 having+0.005
 riding+0.005
Neg logit contributions
eware-0.010
angs-0.010
ricanes-0.009
 Knife-0.008
isable-0.008
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
mun+0.060
rob+0.056
Che+0.054
 pengu+0.053
 rh+0.052
Neg logit contributions
eware-0.079
angs-0.073
out-0.071
 nearer-0.070
ricanes-0.070
Token It
Token ID632
Feature activation+3.30e+00

Pos logit contributions
eware+0.036
right+0.033
 upwards+0.032
ricanes+0.032
angs+0.032
Neg logit contributions
rob-0.043
mun-0.043
 continuing-0.039
 pengu-0.038
 rh-0.038
Token was
Token ID373
Feature activation-7.21e-01

Pos logit contributions
eware+0.160
angs+0.154
ricanes+0.142
 nearer+0.140
isable+0.140
Neg logit contributions
mun-0.076
 enjoying-0.071
 playing-0.071
 And-0.071
 having-0.071
Token a
Token ID257
Feature activation-9.68e-01

Pos logit contributions
 playing+0.020
 having+0.020
 enjoying+0.020
 riding+0.019
 continuing+0.019
Neg logit contributions
eware-0.032
angs-0.031
ricanes-0.029
 Knife-0.027
isable-0.027
Token rare
Token ID4071
Feature activation+1.30e+00

Pos logit contributions
mun+0.032
rob+0.030
 And+0.030
 riding+0.029
 having+0.029
Neg logit contributions
eware-0.036
 knob-0.033
angs-0.033
 nearer-0.032
ricanes-0.031
Token thing
Token ID1517
Feature activation+1.73e+00

Pos logit contributions
eware+0.054
angs+0.049
 knob+0.048
 nearer+0.047
ricanes+0.046
Neg logit contributions
mun-0.039
 And-0.036
Che-0.036
rob-0.035
 having-0.035
Token that
Token ID326
Feature activation-2.40e+00

Pos logit contributions
eware+0.063
angs+0.059
ricanes+0.054
 nearer+0.054
isable+0.054
Neg logit contributions
mun-0.058
 playing-0.058
 And-0.058
 enjoying-0.057
 riding-0.057
Token had
Token ID550
Feature activation-1.85e+00

Pos logit contributions
mun+0.068
 playing+0.067
 enjoying+0.066
 having+0.066
 And+0.066
Neg logit contributions
eware-0.101
angs-0.096
ricanes-0.088
 nearer-0.087
isable-0.087
Token never
Token ID1239
Feature activation+3.21e+00

Pos logit contributions
mun+0.061
 And+0.058
 playing+0.057
 enjoying+0.057
 riding+0.057
Neg logit contributions
eware-0.070
angs-0.066
ricanes-0.060
 nearer-0.060
 knob-0.059
Token,
Token ID11
Feature activation-2.96e-01

Pos logit contributions
eware+0.095
angs+0.093
ricanes+0.083
ups+0.081
leys+0.080
Neg logit contributions
 playing-0.086
 rh-0.085
 riding-0.084
 enjoying-0.084
 pengu-0.083
Token round
Token ID2835
Feature activation+2.44e+00

Pos logit contributions
 playing+0.009
 riding+0.009
 enjoying+0.009
 having+0.009
 rh+0.009
Neg logit contributions
eware-0.012
angs-0.012
ricanes-0.010
leys-0.010
ups-0.010
Token rock
Token ID3881
Feature activation+4.06e-01

Pos logit contributions
eware+0.088
angs+0.084
ricanes+0.076
 nearer+0.073
iqu+0.073
Neg logit contributions
 playing-0.087
 pengu-0.085
 riding-0.085
 rh-0.085
 And-0.084
Token.
Token ID13
Feature activation+7.10e-01

Pos logit contributions
eware+0.019
angs+0.018
ricanes+0.017
 nearer+0.017
isable+0.017
Neg logit contributions
mun-0.010
 And-0.009
 playing-0.009
 enjoying-0.009
 riding-0.009
Token She
Token ID1375
Feature activation-5.67e-01

Pos logit contributions
eware+0.034
angs+0.032
ricanes+0.030
 nearer+0.030
 knob+0.030
Neg logit contributions
mun-0.016
 And-0.015
 playing-0.015
 enjoying-0.015
 riding-0.015
Token put
Token ID1234
Feature activation-1.65e+00

Pos logit contributions
mun+0.016
 playing+0.016
 enjoying+0.015
 riding+0.015
 And+0.015
Neg logit contributions
eware-0.025
angs-0.024
ricanes-0.022
 nearer-0.022
 upwards-0.021
Token it
Token ID340
Feature activation+4.00e+00

Pos logit contributions
 playing+0.038
 having+0.038
 riding+0.037
 enjoying+0.037
 And+0.036
Neg logit contributions
eware-0.082
angs-0.078
ricanes-0.071
isable-0.071
 outage-0.070
Token up
Token ID510
Feature activation+3.81e-03

Pos logit contributions
eware+0.259
angs+0.249
 outage+0.235
 disrespectful+0.233
ricanes+0.226
Neg logit contributions
 playing-0.064
 riding-0.053
 having-0.051
 happily-0.051
 enjoying-0.048
Token to
Token ID284
Feature activation+9.98e-01

Pos logit contributions
eware+0.000
angs+0.000
 Knife+0.000
ricanes+0.000
 outage+0.000
Neg logit contributions
 playing-0.000
 enjoying-0.000
 riding-0.000
 having-0.000
 happily-0.000
Token her
Token ID607
Feature activation+1.42e+00

Pos logit contributions
eware+0.040
 nearer+0.037
angs+0.037
 knob+0.036
 upwards+0.035
Neg logit contributions
mun-0.031
rob-0.029
 And-0.028
 riding-0.027
 rh-0.027
Token mouth
Token ID5422
Feature activation+3.76e+00

Pos logit contributions
eware+0.040
 knob+0.039
angs+0.036
 nearer+0.034
 upwards+0.034
Neg logit contributions
mun-0.061
rob-0.058
Che-0.057
Have-0.054
 continuing-0.053
TokenThe
Token ID464
Feature activation+2.35e-01

Pos logit contributions
eware+0.009
angs+0.009
 nearer+0.008
ricanes+0.008
 knob+0.008
Neg logit contributions
 And-0.006
Che-0.006
mun-0.005
 playing-0.005
 riding-0.005
Token spider
Token ID19230
Feature activation+2.03e+00

Pos logit contributions
angs+0.010
eware+0.009
leys+0.009
ricanes+0.009
ocular+0.009
Neg logit contributions
 playing-0.008
 town-0.008
 having-0.007
 And-0.007
 pengu-0.007
Token replied
Token ID8712
Feature activation-1.53e+00

Pos logit contributions
eware+0.100
angs+0.095
ricanes+0.088
 upwards+0.087
out+0.086
Neg logit contributions
 playing-0.051
mun-0.047
 And-0.047
 enjoying-0.046
 were-0.044
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
 playing+0.029
 And+0.029
mun+0.028
 enjoying+0.028
 having+0.027
Neg logit contributions
eware-0.080
angs-0.077
ricanes-0.074
isable-0.072
 knob-0.071
Token "
Token ID366
Feature activation+1.41e+00

Pos logit contributions
eware+0.042
angs+0.039
 nearer+0.037
 knob+0.037
ricanes+0.036
Neg logit contributions
mun-0.030
rob-0.028
Che-0.026
 And-0.026
 riding-0.026
TokenI
Token ID40
Feature activation+8.30e-03

Pos logit contributions
eware+0.064
angs+0.061
 nearer+0.057
ricanes+0.056
 knob+0.056
Neg logit contributions
mun-0.037
 And-0.035
 playing-0.034
 enjoying-0.034
 riding-0.034
Token'm
Token ID1101
Feature activation-1.31e+00

Pos logit contributions
eware+0.000
angs+0.000
ricanes+0.000
 nearer+0.000
 upwards+0.000
Neg logit contributions
mun-0.000
 And-0.000
 playing-0.000
 enjoying-0.000
 riding-0.000
Token thirsty
Token ID47124
Feature activation+1.05e+00

Pos logit contributions
 playing+0.030
 having+0.029
 enjoying+0.029
mun+0.029
 riding+0.028
Neg logit contributions
eware-0.064
angs-0.060
ricanes-0.058
 nearer-0.056
 upwards-0.056
Token.
Token ID13
Feature activation-3.11e-02

Pos logit contributions
eware+0.055
angs+0.053
ricanes+0.050
 nearer+0.049
isable+0.048
Neg logit contributions
 playing-0.022
 enjoying-0.021
 having-0.020
 And-0.020
mun-0.019
Token I
Token ID314
Feature activation+8.49e-01

Pos logit contributions
 And+0.001
mun+0.001
 playing+0.001
 enjoying+0.001
 having+0.001
Neg logit contributions
eware-0.001
angs-0.001
 nearer-0.001
ricanes-0.001
isable-0.001
Token need
Token ID761
Feature activation+5.52e-03

Pos logit contributions
eware+0.039
angs+0.038
ricanes+0.035
 nearer+0.035
 upwards+0.035
Neg logit contributions
mun-0.021
 And-0.020
 playing-0.020
 enjoying-0.020
 having-0.019
Token always
Token ID1464
Feature activation-4.27e+00

Pos logit contributions
oun+0.040
mun+0.039
rob+0.039
Che+0.038
 sidelines+0.037
Neg logit contributions
eware-0.055
 prick-0.049
 locked-0.047
angs-0.047
 nearer-0.047
Token took
Token ID1718
Feature activation-1.96e+00

Pos logit contributions
mun+0.146
 And+0.138
 riding+0.135
Che+0.135
rob+0.135
Neg logit contributions
eware-0.155
angs-0.142
 nearer-0.132
ricanes-0.132
isable-0.131
Token care
Token ID1337
Feature activation+5.51e-02

Pos logit contributions
mun+0.076
 continuing+0.073
Have+0.073
Che+0.072
rob+0.070
Neg logit contributions
eware-0.061
angs-0.058
 nearer-0.054
 upwards-0.054
out-0.053
Token of
Token ID286
Feature activation-4.01e+00

Pos logit contributions
eware+0.002
angs+0.002
out+0.002
ricanes+0.002
 nearer+0.002
Neg logit contributions
mun-0.001
rob-0.001
 continuing-0.001
Che-0.001
 enjoying-0.001
Token each
Token ID1123
Feature activation-3.23e+00

Pos logit contributions
mun+0.103
 And+0.096
Che+0.095
rob+0.093
 Have+0.092
Neg logit contributions
eware-0.171
angs-0.166
 knob-0.162
adoes-0.159
 nearer-0.159
Token other
Token ID584
Feature activation-3.79e+00

Pos logit contributions
 continuing+0.110
mun+0.104
 enjoying+0.102
Che+0.100
 celebrating+0.099
Neg logit contributions
eware-0.115
angs-0.110
 knob-0.110
out-0.107
 closer-0.104
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
mun+0.138
Che+0.136
rob+0.135
 continuing+0.132
 Have+0.128
Neg logit contributions
eware-0.126
angs-0.117
out-0.113
ups-0.112
 upwards-0.111
Token<|endoftext|>
Token ID50256
Feature activation+4.79e-01

Pos logit contributions
mun+0.039
 sidelines+0.037
 continuing+0.034
rob+0.033
 couple+0.033
Neg logit contributions
eware-0.062
tr-0.056
angs-0.055
ricanes-0.053
ker-0.053
TokenOnce
Token ID7454
Feature activation+1.61e+00

Pos logit contributions
eware+0.019
nob+0.019
angs+0.018
 nearer+0.018
 closer+0.017
Neg logit contributions
 sidelines-0.014
mun-0.013
 wedding-0.012
 continuing-0.012
Che-0.012
Token upon
Token ID2402
Feature activation+2.47e+00

Pos logit contributions
eware+0.054
angs+0.050
ricanes+0.046
 nearer+0.045
 knob+0.044
Neg logit contributions
mun-0.060
 And-0.058
 playing-0.057
 enjoying-0.057
 riding-0.057
Token a
Token ID257
Feature activation+2.77e+00

Pos logit contributions
eware+0.056
angs+0.050
 closer+0.048
 nearer+0.046
nob+0.045
Neg logit contributions
mun-0.116
rob-0.112
 sidelines-0.110
oun-0.108
 continuing-0.108
Token special
Token ID2041
Feature activation+2.30e-01

Pos logit contributions
mun+0.024
 And+0.022
rob+0.022
 having+0.022
 continuing+0.022
Neg logit contributions
eware-0.024
angs-0.022
 knob-0.022
 nearer-0.021
ricanes-0.020
Token message
Token ID3275
Feature activation+9.72e-01

Pos logit contributions
eware+0.008
angs+0.008
ricanes+0.007
 nearer+0.007
isable+0.007
Neg logit contributions
mun-0.008
 And-0.008
 playing-0.008
 enjoying-0.008
 riding-0.007
Token for
Token ID329
Feature activation-2.61e+00

Pos logit contributions
eware+0.043
angs+0.041
ricanes+0.038
 nearer+0.038
 knob+0.037
Neg logit contributions
mun-0.026
 And-0.024
 enjoying-0.024
 playing-0.024
 riding-0.024
Token a
Token ID257
Feature activation-4.05e-01

Pos logit contributions
mun+0.097
rob+0.094
oc+0.087
Che+0.086
oun+0.083
Neg logit contributions
eware-0.091
angs-0.086
 knob-0.080
 cigarettes-0.078
 nearer-0.078
Token special
Token ID2041
Feature activation+7.95e-01

Pos logit contributions
mun+0.014
rob+0.014
 having+0.012
 continuing+0.012
 And+0.012
Neg logit contributions
eware-0.016
 knob-0.014
 closer-0.013
angs-0.013
 nearer-0.013
Token girl
Token ID2576
Feature activation-5.59e+00

Pos logit contributions
eware+0.032
angs+0.029
 knob+0.027
ricanes+0.027
 nearer+0.027
Neg logit contributions
mun-0.025
 And-0.024
 enjoying-0.023
 having-0.023
 riding-0.023
Token."
Token ID526
Feature activation-2.31e-01

Pos logit contributions
mun+0.166
rob+0.153
 continuing+0.151
Che+0.150
 enjoying+0.145
Neg logit contributions
eware-0.235
angs-0.223
 nearer-0.202
 knob-0.201
out-0.200
Token
Token ID198
Feature activation-6.39e-01

Pos logit contributions
rob+0.007
mun+0.006
 sailing+0.006
 rh+0.006
 celebrating+0.006
Neg logit contributions
eware-0.009
 Judy-0.009
 Knife-0.009
 closer-0.008
 nearer-0.008
Token
Token ID198
Feature activation-5.28e-01

Pos logit contributions
mun+0.013
 enjoying+0.012
 celebrating+0.012
rob+0.012
 continuing+0.011
Neg logit contributions
eware-0.031
angs-0.030
 nearer-0.030
 closer-0.029
ricanes-0.029
TokenAnna
Token ID31160
Feature activation+1.27e-01

Pos logit contributions
mun+0.019
 enjoying+0.018
 having+0.018
 playing+0.018
 celebrating+0.018
Neg logit contributions
eware-0.019
angs-0.017
ricanes-0.016
 nearer-0.016
isable-0.015
Token thanked
Token ID26280
Feature activation-3.54e+00

Pos logit contributions
eware+0.005
angs+0.005
ricanes+0.004
 nearer+0.004
 knob+0.004
Neg logit contributions
mun-0.004
 And-0.004
 playing-0.004
 enjoying-0.004
 riding-0.004
Token leader
Token ID3554
Feature activation-1.32e+00

Pos logit contributions
 And+0.024
mun+0.024
rob+0.023
oc+0.023
 enjoying+0.022
Neg logit contributions
eware-0.020
 knob-0.019
isable-0.018
ricanes-0.017
 nearer-0.017
Token of
Token ID286
Feature activation-1.90e+00

Pos logit contributions
rob+0.043
mun+0.043
Che+0.042
 continuing+0.041
Have+0.041
Neg logit contributions
eware-0.045
out-0.042
angs-0.042
up-0.041
 nearer-0.040
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
mun+0.057
 And+0.057
rob+0.054
Che+0.054
oun+0.052
Neg logit contributions
angs-0.070
 nearer-0.069
eware-0.069
 closer-0.067
 knob-0.065
Token band
Token ID4097
Feature activation-1.59e+00

Pos logit contributions
 And+0.047
mun+0.043
rob+0.043
oc+0.042
 continuing+0.041
Neg logit contributions
eware-0.046
 knob-0.045
isable-0.043
 disrespectful-0.042
 key-0.042
Token kept
Token ID4030
Feature activation-1.60e+00

Pos logit contributions
mun+0.052
Have+0.051
rob+0.051
 Evan+0.050
 gor+0.050
Neg logit contributions
eware-0.054
up-0.052
ups-0.051
angs-0.049
row-0.048
Token waving
Token ID25849
Feature activation-4.77e+00

Pos logit contributions
mun+0.051
rob+0.046
oc+0.046
 And+0.045
 rh+0.044
Neg logit contributions
 nearer-0.060
 closer-0.060
eware-0.058
 upwards-0.057
angs-0.057
Token his
Token ID465
Feature activation-4.56e-01

Pos logit contributions
mun+0.142
 And+0.130
rob+0.129
 enjoying+0.129
 riding+0.128
Neg logit contributions
eware-0.198
angs-0.187
 nearer-0.175
ricanes-0.173
 upwards-0.173
Token arms
Token ID5101
Feature activation+1.69e+00

Pos logit contributions
mun+0.019
rob+0.019
Che+0.018
 continuing+0.018
 And+0.017
Neg logit contributions
eware-0.013
 knob-0.012
angs-0.012
 nearer-0.011
ricanes-0.011
Token and
Token ID290
Feature activation-3.84e-01

Pos logit contributions
eware+0.079
angs+0.075
ricanes+0.070
 nearer+0.070
isable+0.069
Neg logit contributions
mun-0.040
 And-0.038
 playing-0.038
 enjoying-0.038
 riding-0.038
Token the
Token ID262
Feature activation-2.08e+00

Pos logit contributions
mun+0.010
 And+0.010
Che+0.010
rob+0.010
oun+0.010
Neg logit contributions
eware-0.015
 nearer-0.015
 closer-0.015
angs-0.014
 upwards-0.014
Token band
Token ID4097
Feature activation-2.23e+00

Pos logit contributions
 And+0.075
mun+0.072
oc+0.071
rob+0.068
 continuing+0.067
Neg logit contributions
eware-0.070
 knob-0.066
 nearer-0.062
angs-0.062
isable-0.061
Token,
Token ID11
Feature activation+3.48e-01

Pos logit contributions
mun+0.039
 And+0.037
 playing+0.036
 enjoying+0.036
 riding+0.036
Neg logit contributions
eware-0.063
angs-0.060
ricanes-0.056
 nearer-0.055
isable-0.055
Token "
Token ID366
Feature activation+8.36e-01

Pos logit contributions
eware+0.014
angs+0.013
 nearer+0.013
 knob+0.012
 upwards+0.012
Neg logit contributions
mun-0.011
rob-0.011
 rh-0.009
oc-0.009
 pengu-0.009
TokenWhat
Token ID2061
Feature activation-8.57e-01

Pos logit contributions
eware+0.032
angs+0.029
 nearer+0.027
ricanes+0.027
 knob+0.026
Neg logit contributions
mun-0.028
 And-0.028
 playing-0.027
 enjoying-0.027
 having-0.027
Token are
Token ID389
Feature activation-3.59e+00

Pos logit contributions
mun+0.021
 And+0.021
 playing+0.021
 riding+0.020
 having+0.020
Neg logit contributions
eware-0.039
angs-0.037
ricanes-0.035
 nearer-0.035
isable-0.035
Token you
Token ID345
Feature activation-1.02e+00

Pos logit contributions
mun+0.084
 And+0.079
 playing+0.078
 enjoying+0.078
 riding+0.077
Neg logit contributions
eware-0.172
angs-0.163
ricanes-0.152
 nearer-0.152
 knob-0.150
Token doing
Token ID1804
Feature activation-5.19e+00

Pos logit contributions
mun+0.014
 playing+0.013
 enjoying+0.013
 riding+0.013
 having+0.013
Neg logit contributions
eware-0.059
angs-0.057
ricanes-0.054
 nearer-0.053
isable-0.053
Token up
Token ID510
Feature activation-1.57e+00

Pos logit contributions
 playing+0.197
 riding+0.193
 enjoying+0.192
 having+0.189
 celebrating+0.188
Neg logit contributions
eware-0.178
angs-0.171
ricanes-0.154
isable-0.146
 nearer-0.145
Token there
Token ID612
Feature activation-1.01e+00

Pos logit contributions
 playing+0.054
 enjoying+0.053
 riding+0.053
 town+0.051
 having+0.051
Neg logit contributions
angs-0.062
eware-0.060
leys-0.056
ricanes-0.056
outed-0.055
Token?"
Token ID1701
Feature activation+7.55e-01

Pos logit contributions
mun+0.049
 playing+0.048
 enjoying+0.048
 And+0.048
 riding+0.048
Neg logit contributions
eware-0.023
angs-0.021
ricanes-0.018
 nearer-0.017
isable-0.017
Token Suddenly
Token ID24975
Feature activation+1.84e-01

Pos logit contributions
eware+0.037
 nearer+0.033
angs+0.033
ricanes+0.033
 Knife+0.033
Neg logit contributions
mun-0.017
rob-0.015
 rh-0.014
 pengu-0.014
 celebrating-0.013
Token the
Token ID262
Feature activation-3.34e-01

Pos logit contributions
eware+0.009
angs+0.009
ricanes+0.008
isable+0.008
 nearer+0.008
Neg logit contributions
mun-0.004
 playing-0.004
 And-0.004
 riding-0.004
 enjoying-0.004
Token They
Token ID1119
Feature activation-2.11e+00

Pos logit contributions
eware+0.042
angs+0.039
ricanes+0.038
 nearer+0.038
 upwards+0.037
Neg logit contributions
mun-0.018
rob-0.017
 continuing-0.016
 enjoying-0.016
 riding-0.015
Token had
Token ID550
Feature activation-4.39e-01

Pos logit contributions
mun+0.051
 And+0.048
 enjoying+0.047
 playing+0.047
 riding+0.047
Neg logit contributions
eware-0.099
angs-0.094
ricanes-0.088
 nearer-0.088
 knob-0.086
Token fun
Token ID1257
Feature activation-7.49e-01

Pos logit contributions
mun+0.012
 playing+0.012
 having+0.012
 enjoying+0.012
 And+0.012
Neg logit contributions
eware-0.019
angs-0.018
ricanes-0.017
 nearer-0.016
isable-0.016
Token with
Token ID351
Feature activation-1.70e+00

Pos logit contributions
Che+0.023
mun+0.023
 Evan+0.023
 rh+0.023
oun+0.022
Neg logit contributions
eware-0.028
angs-0.027
 nearer-0.026
out-0.025
 closer-0.025
Token their
Token ID511
Feature activation-4.93e-01

Pos logit contributions
mun+0.031
 playing+0.030
 And+0.029
 riding+0.029
 enjoying+0.029
Neg logit contributions
eware-0.090
angs-0.086
ricanes-0.081
 nearer-0.080
isable-0.080
Token friends
Token ID2460
Feature activation-5.22e+00

Pos logit contributions
mun+0.016
 And+0.015
 enjoying+0.015
 riding+0.015
 continuing+0.015
Neg logit contributions
eware-0.019
angs-0.018
ricanes-0.016
 nearer-0.016
 knob-0.016
Token.
Token ID13
Feature activation+6.45e-01

Pos logit contributions
mun+0.157
rob+0.149
Che+0.146
 continuing+0.138
 Have+0.137
Neg logit contributions
eware-0.210
angs-0.203
out-0.188
 knob-0.186
 upwards-0.185
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
eware+0.035
angs+0.032
ricanes+0.032
 nearer+0.031
 upwards+0.031
Neg logit contributions
mun-0.011
rob-0.010
 continuing-0.009
 riding-0.009
 enjoying-0.009
Token
Token ID198
Feature activation-5.11e-02

Pos logit contributions
mun+0.002
 rh+0.002
rob+0.002
 continuing+0.002
 enjoying+0.002
Neg logit contributions
eware-0.006
 nearer-0.005
 closer-0.005
angs-0.005
out-0.005
TokenBut
Token ID1537
Feature activation+3.21e+00

Pos logit contributions
mun+0.002
Che+0.002
 And+0.002
Have+0.002
 playing+0.002
Neg logit contributions
eware-0.002
angs-0.002
ricanes-0.002
 nearer-0.002
 upwards-0.002
Token then
Token ID788
Feature activation-3.02e+00

Pos logit contributions
angs+0.150
eware+0.150
ricanes+0.134
 upwards+0.132
iqu+0.131
Neg logit contributions
 playing-0.083
 having-0.080
 enjoying-0.078
 riding-0.077
 And-0.076
Token did
Token ID750
Feature activation-7.20e-01

Pos logit contributions
mun+0.085
rob+0.084
Che+0.079
 And+0.079
 riding+0.077
Neg logit contributions
eware-0.095
angs-0.091
 nearer-0.087
 locked-0.086
 knob-0.085
Token not
Token ID407
Feature activation+5.61e+00

Pos logit contributions
mun+0.035
 And+0.034
 playing+0.034
 enjoying+0.034
 riding+0.033
Neg logit contributions
eware-0.017
angs-0.015
ricanes-0.013
 nearer-0.013
 knob-0.012
Token know
Token ID760
Feature activation-1.20e+00

Pos logit contributions
eware+0.223
angs+0.210
 nearer+0.195
ricanes+0.191
 knob+0.189
Neg logit contributions
mun-0.179
 And-0.170
rob-0.169
 riding-0.164
 enjoying-0.164
Token what
Token ID644
Feature activation-1.19e+00

Pos logit contributions
mun+0.043
rob+0.041
Che+0.041
 And+0.041
 enjoying+0.040
Neg logit contributions
eware-0.042
angs-0.039
 nearer-0.036
 knob-0.035
ricanes-0.035
Token to
Token ID284
Feature activation-4.69e-01

Pos logit contributions
mun+0.044
 And+0.042
 enjoying+0.041
 riding+0.041
rob+0.041
Neg logit contributions
eware-0.041
angs-0.038
ricanes-0.035
 nearer-0.034
 knob-0.034
Token do
Token ID466
Feature activation-4.82e+00

Pos logit contributions
mun+0.011
 And+0.010
rob+0.010
 enjoying+0.010
Che+0.010
Neg logit contributions
eware-0.023
angs-0.021
 knob-0.020
 nearer-0.020
ricanes-0.020
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
mun+0.134
Che+0.123
 And+0.120
rob+0.120
 rh+0.120
Neg logit contributions
eware-0.211
angs-0.196
 nearer-0.185
ricanes-0.184
 knob-0.182
Token They
Token ID1119
Feature activation-2.73e+00

Pos logit contributions
mun+0.007
rob+0.007
 riding+0.006
 enjoying+0.006
 continuing+0.006
Neg logit contributions
eware-0.018
angs-0.017
ricanes-0.016
 Knife-0.016
 upwards-0.016
Token wanted
Token ID2227
Feature activation+1.01e+00

Pos logit contributions
mun+0.081
 And+0.077
 riding+0.076
 enjoying+0.075
 playing+0.075
Neg logit contributions
eware-0.112
angs-0.106
 nearer-0.099
ricanes-0.098
 knob-0.097
Token to
Token ID284
Feature activation+1.26e+00

Pos logit contributions
eware+0.036
angs+0.034
ricanes+0.031
isable+0.030
 upwards+0.029
Neg logit contributions
 playing-0.037
 having-0.036
 enjoying-0.036
mun-0.036
 And-0.035
Token help
Token ID1037
Feature activation+5.76e-01

Pos logit contributions
eware+0.048
angs+0.044
 nearer+0.043
 knob+0.043
ricanes+0.041
Neg logit contributions
mun-0.041
rob-0.040
 And-0.037
Che-0.037
 enjoying-0.037