TOP ACTIVATIONS
MAX = 5.771

stickers . " King Tom , I have a
! You are the best tutor ever !" Tom smiled and
, " Yes , my Queen . The shield will protect
fly and thought , " Hmm , maybe I can bite
sick . " Here , Tim , let me
mom . " Here , you can have my
on her chest . " Hmm , it sounds good .
Let 's go and see what is inside ," Bee said
. He thought , " Hmm , maybe this hole will
behind the couch . " Here I am !" she shouted
Lily 's dress . That boy was very bad and he
him feel better . " Here , take this medicine .
her mom said " That glove has been sitting here for
" Let 's see what is in the sack ,"
. " Let 's see what 's inside !" said Bun
looked and said , " Hmm , it seems like a
Alice . Every day , Princess Alice liked to look nice
Benny and asked , " What 's wrong , Benny ?"
finds the car . " Here it is ! It is
" Hello , children . Who are you ? What do

MIN ACTIVATIONS
MIN = -5.419

a swing and pumped his legs back and forth . He
this egg ?" he said , holding it up .
your trip !" Dad said , picking her up and spinning
so he stomp ed his feet and shouted . Everyone in
I made !" James said , folding his arms in front
swinging . He pumped his legs higher and higher as he
, Mama !" Drake said , amazed . M
Mom ," she said quietly , her eyes full of tears
than yours !" Ben said , z ooming his red boat
star fish !" Sam said , pointing to a red and
to the bird and whispered , " I will miss you
it is !" Lily whispered , pointing to the doll .
this one !" she said , picking up the bunny .
to sleep , she whispered , " I love you ,
is gone !" he said , between so bs .
L ila ?" she asked , smiling . L
something together !" said Emma , adm iring their work .
do it !" Sarah said , laughing .
you go ," she said , pat ting the little girl
the crane fl apped his wings and flew from tree to

INTERVAL 2.973 - 5.771
CONTAINS 0.926%

, " Hello , Elsa . I am happy to meet
can give him to someone who 's lonely , like me
, a little girl named Lucy wanted to play . She
was so impressed . " Wow , that 's perfect !"
on the mattress . But sometimes they make too much noise

INTERVAL 0.176 - 2.973
CONTAINS 42.391%

When they get home , Tom goes to his
felt relieved . She realised the monster was not real and
upon a time , there was a little girl named Lily
of the ham sandwich . She did the same for Ben
a little bunny named Betsy . Betsy loved to hop around

INTERVAL -2.622 - 0.176
CONTAINS 55.199%

room and played with their dolls . They waited for the
, they decided to play a prank on Lily 's big
. They are happy . They like to play with the
the car , mom my turned on the radio and everyone
looked around , she felt so happy and proud of herself

INTERVAL -5.419 - -2.622
CONTAINS 1.483%

caught it on a tw ig . " Oh
beef ! Please !" His mom replied , "
see ? â His mom answered ,
. â Hello ! â
." Lily smiled and said , " Thank you . Do
Token stickers
Token ID28568
Feature activation-4.86e-01

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.014
eyed+0.014
Just+0.014
 widening+0.013
Neg logit contributions
 happens-0.010
 is-0.010
 doesn-0.009
 guys-0.009
 isn-0.009
Token.
Token ID13
Feature activation+3.45e-01

Pos logit contributions
Unfortunately+0.027
Meanwhile+0.027
eyed+0.026
Just+0.026
 widening+0.025
Neg logit contributions
 happens-0.017
 is-0.017
 doesn-0.016
 guys-0.016
 belongs-0.016
Token
Token ID198
Feature activation-1.18e+00

Pos logit contributions
 happens+0.018
 belongs+0.017
 guys+0.017
 doesn+0.017
 is+0.017
Neg logit contributions
Unfortunately-0.014
Meanwhile-0.013
eyed-0.013
Just-0.013
 widening-0.012
Token
Token ID198
Feature activation-1.53e+00

Pos logit contributions
 widening+0.056
 sidelines+0.056
 pounding+0.056
eyed+0.055
Unfortunately+0.054
Neg logit contributions
 is-0.050
 happens-0.046
 isn-0.045
 doesn-0.044
 belongs-0.044
Token"
Token ID1
Feature activation-9.58e-01

Pos logit contributions
 pounding+0.058
 victorious+0.058
 widening+0.057
har+0.056
eyed+0.056
Neg logit contributions
 is-0.078
 happens-0.072
 isn-0.072
 belongs-0.071
 doesn-0.071
TokenKing
Token ID15708
Feature activation+5.77e+00

Pos logit contributions
rolling+0.041
 pounding+0.041
eyed+0.041
Unfortunately+0.040
 victorious+0.039
Neg logit contributions
 happens-0.044
 is-0.043
 guys-0.041
 isn-0.041
 doesn-0.040
Token Tom
Token ID4186
Feature activation+3.49e+00

Pos logit contributions
 needs+0.248
 belongs+0.238
 happens+0.233
 doesn+0.224
mm+0.218
Neg logit contributions
 �-0.172
shadow-0.166
king-0.164
On-0.162
eyed-0.161
Token,
Token ID11
Feature activation+2.43e+00

Pos logit contributions
 guys+0.143
 happens+0.142
unn+0.142
mm+0.128
 belongs+0.126
Neg logit contributions
 pounding-0.135
eyed-0.131
 widening-0.125
Meanwhile-0.123
 victorious-0.122
Token I
Token ID314
Feature activation+8.80e-01

Pos logit contributions
unn+0.085
 happens+0.083
 belongs+0.080
ishes+0.077
 doesn+0.075
Neg logit contributions
Unfortunately-0.114
On-0.108
However-0.106
Meanwhile-0.105
Just-0.104
Token have
Token ID423
Feature activation+1.25e+00

Pos logit contributions
 happens+0.036
 belongs+0.033
 doesn+0.033
 guys+0.033
 isn+0.033
Neg logit contributions
Unfortunately-0.042
eyed-0.042
Meanwhile-0.041
Just-0.039
 pounding-0.039
Token a
Token ID257
Feature activation+2.97e-01

Pos logit contributions
 belongs+0.060
 happens+0.060
 doesn+0.060
 isn+0.058
 is+0.057
Neg logit contributions
Unfortunately-0.049
Meanwhile-0.048
Just-0.046
eyed-0.044
 pounding-0.043
Token!
Token ID0
Feature activation+2.53e+00

Pos logit contributions
 happens+0.170
 guys+0.167
unn+0.164
 belongs+0.157
 lives+0.151
Neg logit contributions
Just-0.081
But-0.081
 pounding-0.080
eyed-0.079
His-0.078
Token You
Token ID921
Feature activation+1.52e+00

Pos logit contributions
 happens+0.086
 guys+0.086
 belongs+0.084
ishes+0.078
 tastes+0.075
Neg logit contributions
Unfortunately-0.137
Just-0.129
eyed-0.129
Meanwhile-0.128
However-0.126
Token are
Token ID389
Feature activation+4.68e-01

Pos logit contributions
 belongs+0.037
 happens+0.037
 doesn+0.034
 needs+0.033
 isn+0.033
Neg logit contributions
Unfortunately-0.092
 victorious-0.089
eyed-0.089
 widening-0.088
Meanwhile-0.087
Token the
Token ID262
Feature activation+2.76e-01

Pos logit contributions
 happens+0.022
 belongs+0.022
 doesn+0.021
 is+0.021
 guys+0.021
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.019
eyed-0.019
 pounding-0.018
 widening-0.018
Token best
Token ID1266
Feature activation+1.23e+00

Pos logit contributions
 happens+0.008
 belongs+0.007
 doesn+0.007
 is+0.007
 isn+0.007
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.017
eyed-0.017
Just-0.016
 widening-0.016
Token tutor
Token ID48680
Feature activation+5.41e+00

Pos logit contributions
 belongs+0.051
 happens+0.050
 doesn+0.050
 isn+0.047
 needs+0.046
Neg logit contributions
Unfortunately-0.057
eyed-0.056
Meanwhile-0.055
 crashing-0.055
 pounding-0.054
Token ever
Token ID1683
Feature activation+2.12e+00

Pos logit contributions
 guys+0.269
mm+0.257
 happens+0.256
unn+0.251
ishes+0.250
Neg logit contributions
eyed-0.192
 victorious-0.164
Just-0.156
 nearby-0.149
 triumphant-0.148
Token!"
Token ID2474
Feature activation+1.75e-01

Pos logit contributions
uffy+0.079
ishes+0.079
 belongs+0.078
 happens+0.077
 guys+0.076
Neg logit contributions
eyed-0.096
 victorious-0.090
shadow-0.088
Just-0.088
 free-0.088
Token Tom
Token ID4186
Feature activation+3.57e-01

Pos logit contributions
 happens+0.006
 doesn+0.006
 belongs+0.006
 is+0.006
 guys+0.006
Neg logit contributions
Unfortunately-0.010
Meanwhile-0.010
eyed-0.009
Just-0.009
 widening-0.009
Token smiled
Token ID13541
Feature activation-9.55e-01

Pos logit contributions
 happens+0.016
 belongs+0.016
 guys+0.016
 doesn+0.016
 is+0.016
Neg logit contributions
Unfortunately-0.015
Meanwhile-0.015
eyed-0.015
Just-0.014
 widening-0.014
Token and
Token ID290
Feature activation+3.75e-02

Pos logit contributions
Unfortunately+0.056
Meanwhile+0.054
 sidelines+0.054
eyed+0.052
Finally+0.052
Neg logit contributions
 is-0.033
 doesn-0.031
 happens-0.031
 guys-0.030
 isn-0.029
Token,
Token ID11
Feature activation-3.20e+00

Pos logit contributions
 belongs+0.028
 doesn+0.027
 happens+0.027
 needs+0.026
 isn+0.026
Neg logit contributions
Unfortunately-0.054
Meanwhile-0.052
eyed-0.052
His-0.052
Just-0.052
Token "
Token ID366
Feature activation-8.32e-01

Pos logit contributions
har+0.216
eyed+0.213
inge+0.209
 sidelines+0.208
Meanwhile+0.206
Neg logit contributions
 is-0.073
 can-0.066
 I-0.066
 isn-0.065
 doesn-0.062
TokenYes
Token ID5297
Feature activation+1.85e+00

Pos logit contributions
Unfortunately+0.039
Meanwhile+0.038
 pounding+0.038
rolling+0.038
eyed+0.037
Neg logit contributions
 is-0.034
 happens-0.034
 doesn-0.033
 isn-0.033
 belongs-0.032
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
 belongs+0.073
 happens+0.073
 lives+0.068
 needs+0.068
ishes+0.066
Neg logit contributions
Unfortunately-0.087
Just-0.084
 crashing-0.083
His-0.082
Meanwhile-0.081
Token my
Token ID616
Feature activation+1.36e+00

Pos logit contributions
 happens+0.026
 belongs+0.025
 doesn+0.023
 is+0.023
 needs+0.022
Neg logit contributions
Unfortunately-0.066
Meanwhile-0.064
Just-0.062
However-0.061
eyed-0.061
Token Queen
Token ID7542
Feature activation+5.41e+00

Pos logit contributions
 happens+0.063
 belongs+0.058
 doesn+0.056
 isn+0.055
 means+0.054
Neg logit contributions
 pounding-0.054
Just-0.054
Unfortunately-0.054
 widening-0.054
 victorious-0.053
Token.
Token ID13
Feature activation+2.25e+00

Pos logit contributions
mm+0.208
 guys+0.206
 happens+0.201
 doesn+0.197
 belongs+0.192
Neg logit contributions
eyed-0.196
 victorious-0.182
 pat-0.171
 grate-0.170
 pounding-0.167
Token The
Token ID383
Feature activation+1.82e-01

Pos logit contributions
 happens+0.070
 guys+0.068
 belongs+0.062
 happened+0.061
 doesn+0.058
Neg logit contributions
Unfortunately-0.133
eyed-0.128
Just-0.127
Meanwhile-0.127
His-0.122
Token shield
Token ID7614
Feature activation+2.27e+00

Pos logit contributions
 happens+0.007
 is+0.007
 doesn+0.007
 belongs+0.007
 isn+0.007
Neg logit contributions
Unfortunately-0.009
Meanwhile-0.009
eyed-0.009
Just-0.008
 widening-0.008
Token will
Token ID481
Feature activation-2.21e+00

Pos logit contributions
 guys+0.039
 happens+0.038
 doesn+0.028
 isn+0.028
unn+0.026
Neg logit contributions
Unfortunately-0.153
eyed-0.152
Meanwhile-0.151
Just-0.148
 pounding-0.147
Token protect
Token ID1805
Feature activation+3.81e-01

Pos logit contributions
Meanwhile+0.114
Unfortunately+0.112
eyed+0.106
rolling+0.104
Just+0.104
Neg logit contributions
 is-0.096
 can-0.088
 needs-0.086
 belongs-0.086
?"-0.085
Token fly
Token ID6129
Feature activation-8.15e-01

Pos logit contributions
 happens+0.000
 is+0.000
 doesn+0.000
 belongs+0.000
 isn+0.000
Neg logit contributions
Unfortunately-0.000
Meanwhile-0.000
eyed-0.000
Just-0.000
 pounding-0.000
Token and
Token ID290
Feature activation+5.00e-01

Pos logit contributions
Unfortunately+0.046
Meanwhile+0.045
eyed+0.044
Just+0.043
Finally+0.042
Neg logit contributions
 is-0.029
 doesn-0.028
 belongs-0.028
 happens-0.028
 isn-0.028
Token thought
Token ID1807
Feature activation+1.08e+00

Pos logit contributions
 happens+0.022
 belongs+0.021
 is+0.021
 isn+0.021
 doesn+0.021
Neg logit contributions
Unfortunately-0.023
Meanwhile-0.023
eyed-0.022
 widening-0.021
Just-0.021
Token,
Token ID11
Feature activation-1.31e+00

Pos logit contributions
 belongs+0.040
 happens+0.039
 doesn+0.038
 guys+0.038
 needs+0.038
Neg logit contributions
Unfortunately-0.054
Meanwhile-0.052
 pounding-0.051
 widening-0.051
Just-0.050
Token "
Token ID366
Feature activation-7.70e-01

Pos logit contributions
eyed+0.069
har+0.066
Unfortunately+0.066
Meanwhile+0.065
rolling+0.063
Neg logit contributions
 doesn-0.053
 is-0.053
 happens-0.051
 isn-0.051
 guys-0.050
TokenHmm
Token ID44217
Feature activation+5.41e+00

Pos logit contributions
 sidelines+0.038
Unfortunately+0.038
 pounding+0.038
rolling+0.038
 widening+0.038
Neg logit contributions
 happens-0.030
 is-0.029
 doesn-0.029
 belongs-0.029
 isn-0.028
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
unn+0.255
 cares+0.246
 needs+0.236
ishes+0.235
 guys+0.229
Neg logit contributions
Suddenly-0.135
 low-0.131
 cautiously-0.127
 firmly-0.126
 carefully-0.125
Token maybe
Token ID3863
Feature activation+3.01e+00

Pos logit contributions
 happens+0.076
 belongs+0.075
unn+0.071
 needs+0.068
 guys+0.067
Neg logit contributions
Unfortunately-0.081
Meanwhile-0.077
Just-0.075
 crashing-0.074
However-0.074
Token I
Token ID314
Feature activation+1.38e+00

Pos logit contributions
unn+0.111
 happens+0.109
 belongs+0.108
uffy+0.108
 isn+0.104
Neg logit contributions
But-0.134
Suddenly-0.130
Just-0.128
Meanwhile-0.127
On-0.127
Token can
Token ID460
Feature activation-5.03e-01

Pos logit contributions
 happens+0.031
 guys+0.027
 belongs+0.026
mm+0.026
 doesn+0.025
Neg logit contributions
Unfortunately-0.089
eyed-0.088
Meanwhile-0.085
On-0.084
Just-0.083
Token bite
Token ID13197
Feature activation+1.67e+00

Pos logit contributions
Meanwhile+0.021
Unfortunately+0.021
eyed+0.020
 pounding+0.020
 widening+0.020
Neg logit contributions
 is-0.024
 guys-0.023
 belongs-0.023
 happens-0.023
 doesn-0.023
Token sick
Token ID6639
Feature activation+1.20e+00

Pos logit contributions
Unfortunately+0.052
Meanwhile+0.050
Finally+0.048
 sidelines+0.047
eyed+0.047
Neg logit contributions
 is-0.045
 happens-0.044
?"-0.043
 doesn-0.043
 needs-0.043
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
 happens+0.054
 belongs+0.054
 isn+0.051
 doesn+0.051
 needs+0.050
Neg logit contributions
Unfortunately-0.051
eyed-0.050
Meanwhile-0.050
 pounding-0.048
Just-0.048
Token
Token ID198
Feature activation-1.63e-01

Pos logit contributions
 happens+0.010
 doesn+0.009
 belongs+0.009
 is+0.009
 guys+0.009
Neg logit contributions
Unfortunately-0.008
Meanwhile-0.008
eyed-0.008
Just-0.008
 widening-0.007
Token
Token ID198
Feature activation-9.25e-01

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.006
 widening+0.006
 pounding+0.006
Neg logit contributions
 happens-0.008
 is-0.008
 doesn-0.008
 belongs-0.008
 isn-0.008
Token"
Token ID1
Feature activation-1.48e-01

Pos logit contributions
 victorious+0.041
 sidelines+0.040
Unfortunately+0.040
 widening+0.040
 pounding+0.039
Neg logit contributions
 is-0.041
 belongs-0.038
 isn-0.037
 happens-0.037
 guys-0.036
TokenHere
Token ID4342
Feature activation+5.31e+00

Pos logit contributions
Unfortunately+0.005
Meanwhile+0.005
eyed+0.005
 pounding+0.005
 widening+0.005
Neg logit contributions
 happens-0.008
 is-0.008
 doesn-0.008
 guys-0.008
 belongs-0.008
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
unn+0.260
elly+0.256
ays+0.249
ishes+0.238
 favorites+0.238
Neg logit contributions
 free-0.138
His-0.134
 pounding-0.128
The-0.127
 calm-0.120
Token Tim
Token ID5045
Feature activation+2.86e+00

Pos logit contributions
 happens+0.077
unn+0.071
 belongs+0.069
 doesn+0.067
ishes+0.066
Neg logit contributions
Unfortunately-0.083
Meanwhile-0.079
His-0.078
 crashing-0.074
On-0.074
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
 happens+0.124
unn+0.119
mm+0.118
 guys+0.117
 isn+0.114
Neg logit contributions
 pounding-0.106
eyed-0.105
 free-0.104
Meanwhile-0.096
Just-0.096
Token let
Token ID1309
Feature activation+2.27e+00

Pos logit contributions
 happens+0.049
 belongs+0.046
unn+0.045
 guys+0.044
 doesn+0.043
Neg logit contributions
Unfortunately-0.072
Meanwhile-0.068
eyed-0.067
 crashing-0.066
His-0.065
Token me
Token ID502
Feature activation-1.10e-01

Pos logit contributions
 cares+0.103
unn+0.099
 happens+0.098
 needs+0.097
 belongs+0.096
Neg logit contributions
Unfortunately-0.086
Meanwhile-0.083
Hours-0.079
The-0.079
His-0.078
Token mom
Token ID1995
Feature activation+7.33e-01

Pos logit contributions
 happens+0.014
 belongs+0.014
 isn+0.013
 doesn+0.013
 is+0.013
Neg logit contributions
Unfortunately-0.014
Meanwhile-0.013
eyed-0.013
Just-0.013
 pounding-0.013
Token.
Token ID13
Feature activation-4.54e-02

Pos logit contributions
 happens+0.033
 belongs+0.031
 guys+0.031
 isn+0.031
 doesn+0.030
Neg logit contributions
eyed-0.034
Unfortunately-0.033
Meanwhile-0.032
Just-0.031
 pounding-0.031
Token
Token ID198
Feature activation-9.38e-01

Pos logit contributions
Unfortunately+0.002
Meanwhile+0.002
eyed+0.002
 widening+0.002
 pounding+0.002
Neg logit contributions
 happens-0.002
 is-0.002
 doesn-0.002
 belongs-0.002
 isn-0.002
Token
Token ID198
Feature activation-1.48e+00

Pos logit contributions
Unfortunately+0.043
Meanwhile+0.042
 widening+0.042
 pounding+0.042
eyed+0.041
Neg logit contributions
 is-0.042
 happens-0.040
 doesn-0.038
 belongs-0.038
 isn-0.038
Token"
Token ID1
Feature activation-9.71e-01

Pos logit contributions
 pounding+0.076
 widening+0.076
rolling+0.075
 crashing+0.074
 victorious+0.074
Neg logit contributions
 is-0.057
 happens-0.049
?"-0.047
 needs-0.047
 belongs-0.046
TokenHere
Token ID4342
Feature activation+5.23e+00

Pos logit contributions
rolling+0.043
eyed+0.042
 pounding+0.042
Unfortunately+0.042
Meanwhile+0.041
Neg logit contributions
 happens-0.043
 is-0.042
 doesn-0.040
 isn-0.039
 needs-0.038
Token,
Token ID11
Feature activation+1.57e+00

Pos logit contributions
unn+0.280
akes+0.274
ishes+0.274
 guys+0.274
eer+0.260
Neg logit contributions
Her-0.134
But-0.122
The-0.122
 cheer-0.120
 firm-0.114
Token you
Token ID345
Feature activation+1.30e+00

Pos logit contributions
 happens+0.060
 belongs+0.057
 guys+0.057
unn+0.054
 doesn+0.052
Neg logit contributions
Unfortunately-0.075
Meanwhile-0.075
Just-0.070
However-0.069
Her-0.069
Token can
Token ID460
Feature activation+6.80e-01

Pos logit contributions
 belongs+0.038
 happens+0.037
mm+0.035
 doesn+0.034
 isn+0.034
Neg logit contributions
Unfortunately-0.071
eyed-0.070
Meanwhile-0.068
rolling-0.066
 victorious-0.066
Token have
Token ID423
Feature activation+1.57e+00

Pos logit contributions
 happens+0.032
 doesn+0.030
 belongs+0.030
 isn+0.030
 guys+0.030
Neg logit contributions
eyed-0.029
Unfortunately-0.029
Meanwhile-0.028
Just-0.027
 widening-0.027
Token my
Token ID616
Feature activation+1.74e+00

Pos logit contributions
 belongs+0.070
 doesn+0.068
 isn+0.068
 needs+0.067
 happens+0.067
Neg logit contributions
Unfortunately-0.067
Just-0.064
Meanwhile-0.064
However-0.062
Their-0.061
Token on
Token ID319
Feature activation-1.01e+00

Pos logit contributions
Unfortunately+0.108
Meanwhile+0.106
 sidelines+0.105
rolling+0.101
 widening+0.101
Neg logit contributions
 is-0.067
 happens-0.065
 doesn-0.063
 guys-0.062
 belongs-0.062
Token her
Token ID607
Feature activation-5.75e-01

Pos logit contributions
Meanwhile+0.054
Unfortunately+0.054
eyed+0.053
rolling+0.052
 widening+0.052
Neg logit contributions
 is-0.038
 doesn-0.035
 isn-0.035
 happens-0.035
 guys-0.035
Token chest
Token ID7721
Feature activation-2.45e+00

Pos logit contributions
Unfortunately+0.027
Meanwhile+0.027
eyed+0.025
 widening+0.024
Finally+0.024
Neg logit contributions
 is-0.026
 doesn-0.025
 belongs-0.025
 happens-0.025
 guys-0.025
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
Unfortunately+0.171
 sidelines+0.169
Meanwhile+0.164
Eventually+0.163
Finally+0.162
Neg logit contributions
 is-0.058
 belongs-0.052
 doesn-0.051
 needs-0.047
 happens-0.046
Token "
Token ID366
Feature activation-2.42e+00

Pos logit contributions
eyed+0.073
Unfortunately+0.069
Meanwhile+0.069
 pounding+0.069
har+0.068
Neg logit contributions
 is-0.049
 isn-0.047
 happens-0.047
 doesn-0.045
 can-0.042
TokenHmm
Token ID44217
Feature activation+5.23e+00

Pos logit contributions
rolling+0.119
 sidelines+0.113
 pounding+0.111
 widening+0.110
 victorious+0.108
Neg logit contributions
 is-0.099
 happens-0.095
 can-0.094
 doesn-0.093
 likes-0.091
Token,
Token ID11
Feature activation+1.66e+00

Pos logit contributions
unn+0.215
 guys+0.209
 cares+0.198
ishes+0.192
cers+0.191
Neg logit contributions
Suddenly-0.173
 carefully-0.169
Just-0.158
shadow-0.158
 pounding-0.158
Token it
Token ID340
Feature activation+2.22e+00

Pos logit contributions
 happens+0.058
 belongs+0.056
unn+0.053
 guys+0.053
 needs+0.052
Neg logit contributions
Unfortunately-0.086
Meanwhile-0.082
Just-0.080
 pounding-0.079
However-0.079
Token sounds
Token ID5238
Feature activation+1.33e+00

Pos logit contributions
 guys+0.051
mm+0.043
 happens+0.041
unn+0.040
 guy+0.038
Neg logit contributions
Unfortunately-0.132
Meanwhile-0.130
 pounding-0.130
eyed-0.129
Just-0.128
Token good
Token ID922
Feature activation+2.79e+00

Pos logit contributions
 belongs+0.063
 happens+0.062
unn+0.062
 guys+0.060
 doesn+0.060
Neg logit contributions
Unfortunately-0.050
 widening-0.047
 pounding-0.046
eyed-0.046
Just-0.045
Token.
Token ID13
Feature activation+9.90e-01

Pos logit contributions
 isn+0.127
mm+0.126
 belongs+0.126
uffy+0.126
 doesn+0.125
Neg logit contributions
eyed-0.088
Just-0.084
 pounding-0.081
Meanwhile-0.080
 realizing-0.079
TokenLet
Token ID5756
Feature activation+2.20e+00

Pos logit contributions
Unfortunately+0.017
eyed+0.016
Meanwhile+0.016
 pounding+0.016
rolling+0.015
Neg logit contributions
 happens-0.019
 is-0.019
 guys-0.018
 doesn-0.018
 isn-0.018
Token's
Token ID338
Feature activation-4.14e-02

Pos logit contributions
unn+0.104
mm+0.098
 cares+0.097
 needs+0.096
 dinosaurs+0.096
Neg logit contributions
Unfortunately-0.082
Meanwhile-0.078
The-0.078
Her-0.077
Just-0.077
Token go
Token ID467
Feature activation+4.25e-03

Pos logit contributions
Unfortunately+0.002
Meanwhile+0.002
eyed+0.002
Just+0.002
 widening+0.002
Neg logit contributions
 happens-0.002
 is-0.002
 doesn-0.002
 belongs-0.002
 guys-0.002
Token and
Token ID290
Feature activation+5.78e-02

Pos logit contributions
 happens+0.000
 is+0.000
 doesn+0.000
 belongs+0.000
 isn+0.000
Neg logit contributions
Unfortunately-0.000
Meanwhile-0.000
eyed-0.000
 widening-0.000
Just-0.000
Token see
Token ID766
Feature activation+2.31e+00

Pos logit contributions
 happens+0.003
 is+0.003
 doesn+0.003
 belongs+0.003
 isn+0.003
Neg logit contributions
Unfortunately-0.002
Meanwhile-0.002
eyed-0.002
Just-0.002
 widening-0.002
Token what
Token ID644
Feature activation+5.22e+00

Pos logit contributions
 happens+0.104
 belongs+0.103
 needs+0.100
 guys+0.099
 cares+0.097
Neg logit contributions
Unfortunately-0.086
Suddenly-0.085
eyed-0.085
shadow-0.084
But-0.084
Token is
Token ID318
Feature activation+1.29e+00

Pos logit contributions
unn+0.196
mm+0.177
ishes+0.174
 guys+0.173
ems+0.171
Neg logit contributions
The-0.226
 low-0.206
On-0.202
 nearby-0.200
 slowly-0.199
Token inside
Token ID2641
Feature activation+2.54e+00

Pos logit contributions
 doesn+0.063
 isn+0.062
 happens+0.062
 needs+0.061
 belongs+0.061
Neg logit contributions
Unfortunately-0.047
Meanwhile-0.045
eyed-0.044
 widening-0.043
 pounding-0.043
Token,"
Token ID553
Feature activation+1.30e+00

Pos logit contributions
 happens+0.093
 guys+0.088
 cares+0.084
 belongs+0.083
 doesn+0.082
Neg logit contributions
eyed-0.123
Unfortunately-0.122
Meanwhile-0.120
 lower-0.115
On-0.115
Token Bee
Token ID24719
Feature activation-7.66e-02

Pos logit contributions
 isn+0.054
 doesn+0.054
 belongs+0.054
 guys+0.053
 happens+0.053
Neg logit contributions
Meanwhile-0.060
Unfortunately-0.059
eyed-0.056
His-0.056
Just-0.056
Token said
Token ID531
Feature activation-4.51e-01

Pos logit contributions
Unfortunately+0.004
Meanwhile+0.004
eyed+0.004
 widening+0.004
Just+0.004
Neg logit contributions
 happens-0.003
 is-0.003
 doesn-0.003
 belongs-0.003
 isn-0.003
Token.
Token ID13
Feature activation+6.57e-01

Pos logit contributions
Unfortunately+0.045
Meanwhile+0.044
eyed+0.043
Just+0.042
 widening+0.042
Neg logit contributions
 is-0.024
 belongs-0.023
 happens-0.023
 doesn-0.022
 isn-0.022
Token He
Token ID679
Feature activation-2.59e-01

Pos logit contributions
 happens+0.032
 belongs+0.030
 guys+0.030
 doesn+0.030
 is+0.030
Neg logit contributions
Unfortunately-0.028
Meanwhile-0.027
Just-0.025
eyed-0.025
 widening-0.025
Token thought
Token ID1807
Feature activation+1.42e+00

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.014
eyed+0.014
 widening+0.013
 sidelines+0.013
Neg logit contributions
 happens-0.009
 is-0.009
 doesn-0.009
 belongs-0.009
 isn-0.009
Token,
Token ID11
Feature activation-1.36e+00

Pos logit contributions
 belongs+0.063
 doesn+0.060
 happens+0.060
 needs+0.059
 isn+0.059
Neg logit contributions
Unfortunately-0.061
 pounding-0.058
Meanwhile-0.057
His-0.056
 crashing-0.056
Token "
Token ID366
Feature activation-8.37e-01

Pos logit contributions
eyed+0.071
har+0.070
Unfortunately+0.067
Meanwhile+0.067
 sidelines+0.065
Neg logit contributions
 is-0.055
 doesn-0.055
 happens-0.053
 isn-0.053
 guys-0.050
TokenHmm
Token ID44217
Feature activation+5.21e+00

Pos logit contributions
 sidelines+0.038
Unfortunately+0.038
 widening+0.037
Meanwhile+0.037
rolling+0.037
Neg logit contributions
 is-0.036
 doesn-0.035
 belongs-0.035
 happens-0.035
 isn-0.035
Token,
Token ID11
Feature activation+1.69e+00

Pos logit contributions
 cares+0.260
unn+0.252
ishes+0.246
 needs+0.245
 acts+0.242
Neg logit contributions
Suddenly-0.124
shadow-0.117
His-0.117
 low-0.111
 firmly-0.111
Token maybe
Token ID3863
Feature activation+2.99e+00

Pos logit contributions
 happens+0.080
 belongs+0.076
 needs+0.072
unn+0.072
 guys+0.070
Neg logit contributions
Unfortunately-0.070
Meanwhile-0.064
Just-0.063
However-0.063
On-0.062
Token this
Token ID428
Feature activation+2.51e+00

Pos logit contributions
unn+0.116
 happens+0.114
 belongs+0.112
uffy+0.109
 needs+0.108
Neg logit contributions
But-0.133
Suddenly-0.127
His-0.127
Just-0.126
On-0.123
Token hole
Token ID7604
Feature activation+4.13e+00

Pos logit contributions
unn+0.094
mm+0.093
ishes+0.088
 guys+0.080
 cares+0.075
Neg logit contributions
Unfortunately-0.119
Meanwhile-0.113
 lower-0.113
 ledge-0.112
On-0.111
Token will
Token ID481
Feature activation-1.06e+00

Pos logit contributions
 guys+0.076
mm+0.074
unn+0.070
 guy+0.055
 dreams+0.052
Neg logit contributions
eyed-0.235
 lower-0.235
 aside-0.234
Meanwhile-0.232
 victorious-0.230
Token behind
Token ID2157
Feature activation+2.44e-01

Pos logit contributions
 happens+0.012
 doesn+0.012
 is+0.012
 belongs+0.012
 isn+0.012
Neg logit contributions
Unfortunately-0.010
Meanwhile-0.009
eyed-0.009
 widening-0.009
Just-0.009
Token the
Token ID262
Feature activation+4.43e-01

Pos logit contributions
 happens+0.011
 belongs+0.011
 doesn+0.011
 is+0.011
 isn+0.011
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.010
 widening-0.010
Just-0.010
Token couch
Token ID18507
Feature activation-1.84e+00

Pos logit contributions
 happens+0.020
 doesn+0.019
 belongs+0.019
 guys+0.019
 isn+0.019
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.020
eyed-0.019
 widening-0.019
 pounding-0.018
Token.
Token ID13
Feature activation-9.49e-02

Pos logit contributions
Unfortunately+0.126
Meanwhile+0.121
Finally+0.120
Eventually+0.119
eyed+0.118
Neg logit contributions
 is-0.042
 guys-0.039
 doesn-0.036
 happens-0.035
 belongs-0.035
Token "
Token ID366
Feature activation-1.08e+00

Pos logit contributions
Unfortunately+0.005
Meanwhile+0.005
eyed+0.004
Just+0.004
 widening+0.004
Neg logit contributions
 happens-0.004
 is-0.004
 doesn-0.004
 belongs-0.004
 isn-0.004
TokenHere
Token ID4342
Feature activation+5.20e+00

Pos logit contributions
rolling+0.044
eyed+0.042
 widening+0.042
Unfortunately+0.042
 victorious+0.041
Neg logit contributions
 happens-0.051
 is-0.049
 doesn-0.049
 guys-0.048
 isn-0.048
Token I
Token ID314
Feature activation+1.96e+00

Pos logit contributions
unn+0.275
ishes+0.272
akes+0.270
ays+0.258
elly+0.254
Neg logit contributions
 free-0.137
 pounding-0.121
Her-0.119
 cheer-0.114
 determined-0.113
Token am
Token ID716
Feature activation+1.50e+00

Pos logit contributions
 happens+0.095
 doesn+0.094
mm+0.091
 guys+0.089
 isn+0.089
Neg logit contributions
eyed-0.070
Unfortunately-0.066
On-0.066
His-0.065
Meanwhile-0.065
Token!"
Token ID2474
Feature activation+2.41e-01

Pos logit contributions
 happens+0.053
 doesn+0.050
 belongs+0.048
 isn+0.047
 needs+0.046
Neg logit contributions
Unfortunately-0.081
eyed-0.079
Meanwhile-0.079
Just-0.077
rolling-0.077
Token she
Token ID673
Feature activation-2.96e-01

Pos logit contributions
 happens+0.009
 belongs+0.008
 is+0.008
 doesn+0.008
 guys+0.008
Neg logit contributions
Unfortunately-0.013
Meanwhile-0.013
eyed-0.013
Just-0.012
 widening-0.012
Token shouted
Token ID17293
Feature activation-9.69e-01

Pos logit contributions
Unfortunately+0.015
Meanwhile+0.015
eyed+0.015
 widening+0.014
Just+0.014
Neg logit contributions
 happens-0.012
 is-0.011
 doesn-0.011
 belongs-0.011
 guys-0.011
Token Lily
Token ID20037
Feature activation+1.85e+00

Pos logit contributions
 happens+0.009
 is+0.008
 doesn+0.008
 belongs+0.008
 isn+0.008
Neg logit contributions
Unfortunately-0.008
Meanwhile-0.008
eyed-0.008
Just-0.007
 pounding-0.007
Token's
Token ID338
Feature activation+1.64e-01

Pos logit contributions
 happens+0.076
 guys+0.072
 isn+0.067
 belongs+0.067
 doesn+0.065
Neg logit contributions
eyed-0.086
Unfortunately-0.083
Just-0.081
Meanwhile-0.081
 pounding-0.081
Token dress
Token ID6576
Feature activation+1.29e+00

Pos logit contributions
 happens+0.008
 is+0.007
 belongs+0.007
 doesn+0.007
 isn+0.007
Neg logit contributions
Unfortunately-0.007
Meanwhile-0.007
eyed-0.007
Just-0.006
 pounding-0.006
Token.
Token ID13
Feature activation+2.02e+00

Pos logit contributions
 happens+0.054
 guys+0.050
 belongs+0.049
 isn+0.049
 doesn+0.049
Neg logit contributions
Unfortunately-0.059
eyed-0.058
Meanwhile-0.058
Just-0.057
 pounding-0.056
Token That
Token ID1320
Feature activation+2.16e+00

Pos logit contributions
 guys+0.088
 happens+0.084
 belongs+0.080
 happened+0.078
ishes+0.075
Neg logit contributions
Unfortunately-0.094
Just-0.088
eyed-0.088
Meanwhile-0.088
Her-0.082
Token boy
Token ID2933
Feature activation+5.19e+00

Pos logit contributions
unn+0.080
 guys+0.079
mm+0.078
ishes+0.076
 owns+0.070
Neg logit contributions
Meanwhile-0.094
Unfortunately-0.094
 pounding-0.091
 lower-0.090
 distance-0.089
Token was
Token ID373
Feature activation+1.03e+00

Pos logit contributions
 guys+0.176
 mushrooms+0.144
mm+0.142
unn+0.137
berries+0.134
Neg logit contributions
eyed-0.240
 determined-0.238
 unt-0.237
 free-0.233
 carefully-0.232
Token very
Token ID845
Feature activation+1.32e+00

Pos logit contributions
 happens+0.055
 guys+0.055
unn+0.054
 belongs+0.053
 isn+0.052
Neg logit contributions
Unfortunately-0.036
Meanwhile-0.034
Just-0.033
 pounding-0.033
eyed-0.032
Token bad
Token ID2089
Feature activation+3.31e+00

Pos logit contributions
 guys+0.071
 happens+0.068
 isn+0.066
 doesn+0.065
 is+0.064
Neg logit contributions
eyed-0.046
Unfortunately-0.046
His-0.045
Just-0.044
Meanwhile-0.043
Token and
Token ID290
Feature activation+2.09e+00

Pos logit contributions
 belongs+0.170
ishes+0.161
 owns+0.158
uffy+0.155
 lives+0.154
Neg logit contributions
But-0.099
Just-0.097
 faster-0.091
 realizing-0.090
but-0.090
Token he
Token ID339
Feature activation+3.37e+00

Pos logit contributions
 guys+0.077
 happens+0.071
unn+0.067
 isn+0.066
mm+0.066
Neg logit contributions
Unfortunately-0.100
eyed-0.098
Meanwhile-0.097
 pounding-0.095
Just-0.093
Token him
Token ID683
Feature activation-9.72e-01

Pos logit contributions
 happens+0.019
 belongs+0.018
 doesn+0.018
 isn+0.018
 is+0.018
Neg logit contributions
Unfortunately-0.022
Meanwhile-0.021
eyed-0.021
 pounding-0.020
Just-0.020
Token feel
Token ID1254
Feature activation-2.23e-01

Pos logit contributions
Unfortunately+0.044
Meanwhile+0.044
Just+0.041
eyed+0.041
 widening+0.041
Neg logit contributions
 is-0.044
 doesn-0.044
 happens-0.044
 guys-0.043
 belongs-0.043
Token better
Token ID1365
Feature activation-3.67e-02

Pos logit contributions
Unfortunately+0.010
Meanwhile+0.010
eyed+0.009
Just+0.009
 widening+0.009
Neg logit contributions
 happens-0.010
 is-0.010
 doesn-0.010
 belongs-0.010
 isn-0.010
Token.
Token ID13
Feature activation+2.31e-01

Pos logit contributions
Unfortunately+0.002
Meanwhile+0.002
eyed+0.002
 widening+0.002
Just+0.002
Neg logit contributions
 happens-0.001
 is-0.001
 doesn-0.001
 belongs-0.001
 isn-0.001
Token "
Token ID366
Feature activation-1.48e+00

Pos logit contributions
 happens+0.009
 belongs+0.008
 is+0.008
 doesn+0.008
 guys+0.008
Neg logit contributions
Unfortunately-0.012
Meanwhile-0.012
eyed-0.012
Just-0.011
 widening-0.011
TokenHere
Token ID4342
Feature activation+5.17e+00

Pos logit contributions
rolling+0.068
 pounding+0.063
 widening+0.063
 victorious+0.062
eyed+0.061
Neg logit contributions
 doesn-0.064
 happens-0.064
 is-0.064
 isn-0.062
 needs-0.060
Token,
Token ID11
Feature activation+1.82e+00

Pos logit contributions
elly+0.216
ays+0.216
oline+0.211
unn+0.206
akes+0.204
Neg logit contributions
His-0.167
 determined-0.158
 free-0.157
But-0.153
 pounding-0.150
Token take
Token ID1011
Feature activation+1.53e+00

Pos logit contributions
 happens+0.074
 belongs+0.066
 guys+0.066
unn+0.063
ishes+0.063
Neg logit contributions
Unfortunately-0.088
Meanwhile-0.084
His-0.081
However-0.080
On-0.079
Token this
Token ID428
Feature activation+2.61e-01

Pos logit contributions
 belongs+0.065
 happens+0.060
 doesn+0.060
 isn+0.059
 needs+0.059
Neg logit contributions
Unfortunately-0.073
Meanwhile-0.069
Just-0.067
eyed-0.066
Eventually-0.065
Token medicine
Token ID9007
Feature activation+1.24e+00

Pos logit contributions
 happens+0.010
 doesn+0.010
 belongs+0.010
 is+0.010
 isn+0.010
Neg logit contributions
Unfortunately-0.013
Meanwhile-0.013
eyed-0.013
 pounding-0.012
Just-0.012
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
 happens+0.042
 belongs+0.039
 isn+0.039
 guys+0.039
 doesn+0.039
Neg logit contributions
Unfortunately-0.068
Meanwhile-0.066
eyed-0.065
Just-0.063
 widening-0.062
Token her
Token ID607
Feature activation+9.49e-01

Pos logit contributions
 belongs+0.090
unn+0.088
 needs+0.082
 lives+0.079
ishes+0.079
Neg logit contributions
Unfortunately-0.093
Meanwhile-0.091
Her-0.090
Suddenly-0.088
However-0.088
Token mom
Token ID1995
Feature activation+6.61e-01

Pos logit contributions
 belongs+0.042
 happens+0.041
 doesn+0.041
 isn+0.040
 is+0.039
Neg logit contributions
Meanwhile-0.042
Unfortunately-0.042
 pounding-0.041
eyed-0.040
Just-0.040
Token said
Token ID531
Feature activation+6.41e-01

Pos logit contributions
 happens+0.027
 belongs+0.027
 doesn+0.026
 isn+0.026
 guys+0.026
Neg logit contributions
Meanwhile-0.032
Unfortunately-0.031
eyed-0.030
 pounding-0.030
Just-0.030
Token "
Token ID366
Feature activation-1.46e+00

Pos logit contributions
 belongs+0.029
 happens+0.029
 doesn+0.029
 guys+0.028
 needs+0.028
Neg logit contributions
Unfortunately-0.027
Meanwhile-0.027
eyed-0.026
 pounding-0.026
Just-0.026
TokenThat
Token ID2504
Feature activation+2.22e+00

Pos logit contributions
rolling+0.062
 victorious+0.062
Unfortunately+0.061
eyed+0.060
 pounding+0.060
Neg logit contributions
 doesn-0.066
 happens-0.065
 is-0.065
 isn-0.064
 guys-0.060
Token glove
Token ID29144
Feature activation+5.16e+00

Pos logit contributions
mm+0.086
unn+0.085
ishes+0.081
 belongs+0.078
 happens+0.077
Neg logit contributions
Meanwhile-0.098
Unfortunately-0.097
 pounding-0.095
Just-0.091
 ledge-0.089
Token has
Token ID468
Feature activation+1.40e+00

Pos logit contributions
unn+0.108
 guys+0.097
 happens+0.094
mm+0.093
 dreams+0.086
Neg logit contributions
 pounding-0.281
 free-0.278
 barely-0.272
Unfortunately-0.268
 triumphant-0.266
Token been
Token ID587
Feature activation+1.05e+00

Pos logit contributions
 happens+0.061
 belongs+0.060
 doesn+0.060
 isn+0.058
 is+0.058
Neg logit contributions
Unfortunately-0.060
Meanwhile-0.059
 pounding-0.056
Just-0.056
 widening-0.054
Token sitting
Token ID5586
Feature activation+1.18e+00

Pos logit contributions
 happens+0.050
 belongs+0.049
 doesn+0.049
 is+0.048
 isn+0.048
Neg logit contributions
Unfortunately-0.042
Meanwhile-0.041
 pounding-0.040
Just-0.039
eyed-0.039
Token here
Token ID994
Feature activation+8.84e-01

Pos logit contributions
 happens+0.058
 belongs+0.055
 doesn+0.054
 isn+0.054
 needs+0.053
Neg logit contributions
Unfortunately-0.048
Meanwhile-0.046
Just-0.045
eyed-0.045
 victorious-0.042
Token for
Token ID329
Feature activation-4.41e-01

Pos logit contributions
 happens+0.034
 belongs+0.032
 doesn+0.032
 guys+0.031
 is+0.031
Neg logit contributions
Unfortunately-0.045
Meanwhile-0.045
eyed-0.044
Just-0.042
 widening-0.042
Token
Token ID198
Feature activation-9.31e-01

Pos logit contributions
Meanwhile+0.037
Unfortunately+0.037
 widening+0.037
 sidelines+0.036
 pounding+0.036
Neg logit contributions
 is-0.037
 happens-0.036
 isn-0.034
 doesn-0.034
 belongs-0.034
Token"
Token ID1
Feature activation-3.41e-01

Pos logit contributions
Unfortunately+0.039
Meanwhile+0.038
 pounding+0.038
eyed+0.038
 sidelines+0.038
Neg logit contributions
 is-0.042
 happens-0.041
 belongs-0.040
 isn-0.040
 doesn-0.039
TokenLet
Token ID5756
Feature activation+1.92e+00

Pos logit contributions
Unfortunately+0.013
Meanwhile+0.013
eyed+0.013
 pounding+0.012
 widening+0.012
Neg logit contributions
 happens-0.017
 is-0.017
 guys-0.016
 isn-0.016
 doesn-0.016
Token's
Token ID338
Feature activation-1.72e-01

Pos logit contributions
unn+0.081
 needs+0.078
 cares+0.076
mm+0.075
 happens+0.075
Neg logit contributions
Unfortunately-0.084
Meanwhile-0.081
Just-0.080
Their-0.078
Her-0.078
Token see
Token ID766
Feature activation+2.23e+00

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
Just+0.007
 widening+0.007
Neg logit contributions
 happens-0.008
 is-0.008
 guys-0.008
 doesn-0.008
 belongs-0.008
Token what
Token ID644
Feature activation+5.14e+00

Pos logit contributions
 happens+0.096
 needs+0.093
 belongs+0.093
 guys+0.091
unn+0.090
Neg logit contributions
Unfortunately-0.089
eyed-0.088
shadow-0.087
Suddenly-0.085
On-0.084
Token is
Token ID318
Feature activation+1.37e+00

Pos logit contributions
unn+0.229
 guys+0.185
affles+0.182
ishes+0.181
mm+0.181
Neg logit contributions
The-0.214
On-0.199
 nearby-0.192
 low-0.188
Unfortunately-0.185
Token in
Token ID287
Feature activation+1.67e+00

Pos logit contributions
 happens+0.068
 doesn+0.067
 isn+0.066
 needs+0.065
 cares+0.065
Neg logit contributions
Unfortunately-0.049
eyed-0.047
Meanwhile-0.046
Just-0.044
 pounding-0.044
Token the
Token ID262
Feature activation+6.84e-01

Pos logit contributions
 happens+0.080
 guys+0.078
unn+0.077
 isn+0.077
 doesn+0.077
Neg logit contributions
Unfortunately-0.063
Meanwhile-0.062
eyed-0.061
On-0.060
 winding-0.058
Token sack
Token ID23704
Feature activation+1.43e+00

Pos logit contributions
 happens+0.029
 doesn+0.027
 isn+0.027
 belongs+0.027
 is+0.026
Neg logit contributions
Unfortunately-0.033
Meanwhile-0.032
eyed-0.030
 sidelines-0.030
 widening-0.030
Token,"
Token ID553
Feature activation+8.16e-01

Pos logit contributions
 happens+0.039
 doesn+0.036
 isn+0.036
 belongs+0.035
 guys+0.034
Neg logit contributions
Meanwhile-0.086
Unfortunately-0.086
eyed-0.084
 widening-0.082
On-0.081
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
Unfortunately+0.081
Meanwhile+0.078
eyed+0.077
Finally+0.076
rolling+0.076
Neg logit contributions
 is-0.037
 doesn-0.033
 belongs-0.032
 happens-0.032
 isn-0.031
Token "
Token ID366
Feature activation-1.30e+00

Pos logit contributions
 happens+0.009
 is+0.008
 doesn+0.008
 belongs+0.008
 isn+0.008
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.011
Just-0.011
 widening-0.011
TokenLet
Token ID5756
Feature activation+1.87e+00

Pos logit contributions
 pounding+0.054
rolling+0.053
 widening+0.053
eyed+0.052
 sidelines+0.052
Neg logit contributions
 guys-0.057
 is-0.056
 happens-0.056
 isn-0.055
 doesn-0.055
Token's
Token ID338
Feature activation+2.01e-02

Pos logit contributions
 cares+0.076
unn+0.074
 needs+0.074
 happens+0.073
mm+0.071
Neg logit contributions
Unfortunately-0.084
Meanwhile-0.080
Just-0.079
However-0.076
Finally-0.075
Token see
Token ID766
Feature activation+1.95e+00

Pos logit contributions
 happens+0.001
 is+0.001
 doesn+0.001
 belongs+0.001
 isn+0.001
Neg logit contributions
Unfortunately-0.001
Meanwhile-0.001
eyed-0.001
Just-0.001
 widening-0.001
Token what
Token ID644
Feature activation+5.14e+00

Pos logit contributions
 happens+0.097
 belongs+0.095
 needs+0.092
 cares+0.089
 doesn+0.088
Neg logit contributions
Unfortunately-0.071
shadow-0.069
Suddenly-0.068
eyed-0.068
Meanwhile-0.067
Token's
Token ID338
Feature activation+1.32e+00

Pos logit contributions
unn+0.229
mm+0.225
ems+0.221
ishes+0.221
unes+0.219
Neg logit contributions
The-0.178
Unfortunately-0.150
 free-0.147
 slowly-0.147
 low-0.147
Token inside
Token ID2641
Feature activation+2.75e+00

Pos logit contributions
 isn+0.066
 guys+0.065
 doesn+0.065
 happens+0.065
mm+0.064
Neg logit contributions
Unfortunately-0.045
Meanwhile-0.043
eyed-0.043
 pounding-0.042
 widening-0.040
Token!"
Token ID2474
Feature activation-1.77e-01

Pos logit contributions
 happens+0.105
 guys+0.099
 cares+0.099
unn+0.094
 belongs+0.093
Neg logit contributions
Unfortunately-0.125
Meanwhile-0.121
 lower-0.118
The-0.117
 victorious-0.117
Token said
Token ID531
Feature activation+4.33e-02

Pos logit contributions
Unfortunately+0.009
Meanwhile+0.009
eyed+0.009
 widening+0.008
Just+0.008
Neg logit contributions
 happens-0.007
 is-0.007
 doesn-0.007
 belongs-0.007
 isn-0.007
Token Bun
Token ID28515
Feature activation-8.06e-02

Pos logit contributions
 happens+0.002
 is+0.002
 doesn+0.002
 belongs+0.002
 isn+0.002
Neg logit contributions
Unfortunately-0.002
Meanwhile-0.002
eyed-0.002
Just-0.002
 widening-0.002
Token looked
Token ID3114
Feature activation+5.98e-02

Pos logit contributions
Unfortunately+0.032
Meanwhile+0.031
eyed+0.030
 sidelines+0.029
 widening+0.029
Neg logit contributions
 is-0.022
 happens-0.022
 doesn-0.022
 belongs-0.021
 isn-0.021
Token and
Token ID290
Feature activation-3.77e-01

Pos logit contributions
 happens+0.003
 is+0.003
 doesn+0.003
 belongs+0.003
 isn+0.003
Neg logit contributions
Unfortunately-0.003
Meanwhile-0.003
eyed-0.003
Just-0.003
 widening-0.003
Token said
Token ID531
Feature activation+1.32e+00

Pos logit contributions
Unfortunately+0.021
Meanwhile+0.020
eyed+0.020
 pounding+0.019
Just+0.019
Neg logit contributions
 happens-0.014
 is-0.013
 doesn-0.013
 isn-0.013
 belongs-0.013
Token,
Token ID11
Feature activation-1.86e+00

Pos logit contributions
 belongs+0.042
 needs+0.041
 doesn+0.041
 happens+0.041
 guys+0.041
Neg logit contributions
Unfortunately-0.071
His-0.071
eyed-0.069
 pounding-0.069
Meanwhile-0.068
Token "
Token ID366
Feature activation-7.60e-01

Pos logit contributions
eyed+0.110
Unfortunately+0.109
har+0.107
Meanwhile+0.107
Days+0.102
Neg logit contributions
 is-0.061
 isn-0.058
 doesn-0.058
 happens-0.055
 can-0.054
TokenHmm
Token ID44217
Feature activation+5.12e+00

Pos logit contributions
Meanwhile+0.029
Unfortunately+0.029
 pounding+0.029
 widening+0.029
eyed+0.029
Neg logit contributions
 is-0.038
 happens-0.038
 isn-0.037
 doesn-0.037
 belongs-0.036
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
unn+0.272
ishes+0.248
 cares+0.246
 lives+0.234
 guys+0.233
Neg logit contributions
 �-0.122
Suddenly-0.119
 carefully-0.117
 revealing-0.116
 low-0.112
Token it
Token ID340
Feature activation+2.81e+00

Pos logit contributions
unn+0.081
 happens+0.079
 belongs+0.079
 needs+0.074
ishes+0.074
Neg logit contributions
Unfortunately-0.078
Meanwhile-0.072
However-0.071
Just-0.070
 pounding-0.069
Token seems
Token ID2331
Feature activation+4.74e-01

Pos logit contributions
mm+0.102
unn+0.101
 guys+0.100
 guy+0.088
ens+0.086
Neg logit contributions
Unfortunately-0.123
 pounding-0.122
Meanwhile-0.120
Just-0.119
 lower-0.117
Token like
Token ID588
Feature activation+1.37e+00

Pos logit contributions
 happens+0.022
 belongs+0.022
 is+0.022
 doesn+0.021
 guys+0.021
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.019
eyed-0.019
 pounding-0.018
Just-0.018
Token a
Token ID257
Feature activation-2.16e-01

Pos logit contributions
 belongs+0.063
 happens+0.062
 doesn+0.061
 is+0.060
 needs+0.060
Neg logit contributions
Unfortunately-0.057
Meanwhile-0.054
 pounding-0.052
Just-0.051
 winding-0.050
Token Alice
Token ID14862
Feature activation+2.14e+00

Pos logit contributions
 happens+0.117
 belongs+0.110
 needs+0.109
 doesn+0.106
 isn+0.105
Neg logit contributions
 pounding-0.099
eyed-0.098
Her-0.098
Just-0.098
Meanwhile-0.096
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
 happens+0.120
 guys+0.116
unn+0.109
 belongs+0.106
 doesn+0.105
Neg logit contributions
eyed-0.077
Just-0.070
Her-0.069
His-0.068
But-0.067
Token Every
Token ID3887
Feature activation+1.70e+00

Pos logit contributions
 happens+0.052
 doesn+0.051
 guys+0.051
 belongs+0.051
 isn+0.050
Neg logit contributions
Unfortunately-0.040
Meanwhile-0.039
 widening-0.038
eyed-0.038
On-0.037
Token day
Token ID1110
Feature activation+3.51e+00

Pos logit contributions
 doesn+0.075
 isn+0.073
ishes+0.072
 belongs+0.072
 happens+0.070
Neg logit contributions
Meanwhile-0.069
Unfortunately-0.068
eyed-0.068
On-0.066
Just-0.066
Token,
Token ID11
Feature activation+2.06e+00

Pos logit contributions
ishes+0.187
 belongs+0.172
iles+0.170
unn+0.169
 doesn+0.166
Neg logit contributions
Her-0.120
On-0.115
side-0.115
 low-0.113
But-0.112
Token Princess
Token ID8449
Feature activation+5.12e+00

Pos logit contributions
 belongs+0.111
 happens+0.110
unn+0.108
 doesn+0.107
 needs+0.106
Neg logit contributions
Unfortunately-0.069
On-0.069
Her-0.068
Meanwhile-0.067
However-0.065
Token Alice
Token ID14862
Feature activation+3.78e+00

Pos logit contributions
akes+0.254
mm+0.237
icer+0.235
unn+0.234
 aren+0.233
Neg logit contributions
Her-0.162
On-0.151
 carefully-0.147
eyed-0.145
 proudly-0.145
Token liked
Token ID8288
Feature activation+1.18e+00

Pos logit contributions
mm+0.170
 isn+0.161
 guys+0.159
 happens+0.156
 belongs+0.151
Neg logit contributions
eyed-0.151
On-0.137
Just-0.135
 pounding-0.134
But-0.128
Token to
Token ID284
Feature activation-3.66e-01

Pos logit contributions
 belongs+0.065
 happens+0.065
 doesn+0.064
 isn+0.063
 needs+0.062
Neg logit contributions
Unfortunately-0.038
Meanwhile-0.037
 pounding-0.037
eyed-0.036
Just-0.035
Token look
Token ID804
Feature activation+1.23e+00

Pos logit contributions
Unfortunately+0.016
Meanwhile+0.016
eyed+0.015
Just+0.015
 widening+0.015
Neg logit contributions
 happens-0.017
 is-0.017
 guys-0.017
 doesn-0.016
 belongs-0.016
Token nice
Token ID3621
Feature activation+2.03e+00

Pos logit contributions
 happens+0.058
 belongs+0.054
 doesn+0.054
 isn+0.053
 is+0.053
Neg logit contributions
eyed-0.051
Unfortunately-0.049
 int-0.049
Meanwhile-0.048
 widening-0.047
Token Benny
Token ID44275
Feature activation-8.39e-01

Pos logit contributions
 belongs+0.093
 happens+0.090
 guys+0.089
 isn+0.089
 needs+0.088
Neg logit contributions
Meanwhile-0.068
His-0.065
Unfortunately-0.065
Her-0.064
Their-0.062
Token and
Token ID290
Feature activation+8.04e-01

Pos logit contributions
Unfortunately+0.044
Meanwhile+0.042
Finally+0.040
eyed+0.040
Just+0.040
Neg logit contributions
 is-0.034
 doesn-0.033
 belongs-0.033
 needs-0.032
 happens-0.032
Token asked
Token ID1965
Feature activation+2.10e+00

Pos logit contributions
 happens+0.037
 guys+0.036
 belongs+0.036
 isn+0.035
 is+0.035
Neg logit contributions
Meanwhile-0.034
Unfortunately-0.034
 pounding-0.032
eyed-0.032
Just-0.032
Token,
Token ID11
Feature activation-1.51e+00

Pos logit contributions
 happens+0.094
 belongs+0.093
 needs+0.088
 doesn+0.086
 cares+0.085
Neg logit contributions
Her-0.085
His-0.085
 realizing-0.081
Unfortunately-0.081
 vigorously-0.081
Token "
Token ID366
Feature activation-1.22e-01

Pos logit contributions
Unfortunately+0.084
Meanwhile+0.081
eyed+0.081
 sidelines+0.078
har+0.078
Neg logit contributions
 is-0.054
 isn-0.051
 can-0.050
 doesn-0.050
 happens-0.050
TokenWhat
Token ID2061
Feature activation+5.11e+00

Pos logit contributions
Unfortunately+0.004
Meanwhile+0.004
eyed+0.004
 widening+0.004
 pounding+0.004
Neg logit contributions
 happens-0.007
 is-0.007
 doesn-0.007
 belongs-0.007
 guys-0.007
Token's
Token ID338
Feature activation+1.30e+00

Pos logit contributions
unn+0.229
ishes+0.224
mm+0.212
ley+0.204
ebra+0.203
Neg logit contributions
 overcome-0.170
 understand-0.165
 unt-0.146
On-0.144
The-0.144
Token wrong
Token ID2642
Feature activation+2.78e+00

Pos logit contributions
 isn+0.058
 happens+0.056
unn+0.056
 doesn+0.055
 guys+0.055
Neg logit contributions
Unfortunately-0.053
Meanwhile-0.051
eyed-0.050
Just-0.050
His-0.050
Token,
Token ID11
Feature activation+1.59e+00

Pos logit contributions
 belongs+0.108
 happens+0.106
 cares+0.104
 doesn+0.098
 needs+0.097
Neg logit contributions
 pounding-0.126
His-0.118
Unfortunately-0.116
Meanwhile-0.115
rolling-0.115
Token Benny
Token ID44275
Feature activation+3.49e+00

Pos logit contributions
 happens+0.065
 belongs+0.062
 lives+0.058
 cares+0.056
 needs+0.056
Neg logit contributions
Unfortunately-0.077
Meanwhile-0.075
However-0.073
His-0.071
 crashing-0.071
Token?"
Token ID1701
Feature activation+5.47e-01

Pos logit contributions
mm+0.109
 belongs+0.095
 cares+0.095
 happens+0.094
 isn+0.093
Neg logit contributions
 nearby-0.174
 pounding-0.171
eyed-0.171
On-0.170
Meanwhile-0.170
Token finds
Token ID7228
Feature activation-4.72e-01

Pos logit contributions
 happens+0.012
 guys+0.012
 belongs+0.012
 doesn+0.012
 isn+0.012
Neg logit contributions
Unfortunately-0.016
Meanwhile-0.016
eyed-0.016
 widening-0.015
 pounding-0.015
Token the
Token ID262
Feature activation-8.94e-02

Pos logit contributions
Unfortunately+0.024
Meanwhile+0.023
eyed+0.023
Just+0.023
rolling+0.022
Neg logit contributions
 happens-0.019
 is-0.019
 doesn-0.018
 belongs-0.018
 guys-0.018
Token car
Token ID1097
Feature activation-2.81e-01

Pos logit contributions
Unfortunately+0.005
Meanwhile+0.004
eyed+0.004
Just+0.004
 widening+0.004
Neg logit contributions
 happens-0.004
 is-0.003
 doesn-0.003
 belongs-0.003
 isn-0.003
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
Unfortunately+0.016
Meanwhile+0.015
eyed+0.015
Just+0.015
 widening+0.015
Neg logit contributions
 is-0.010
 happens-0.010
 belongs-0.010
 doesn-0.009
 isn-0.009
Token "
Token ID366
Feature activation-1.31e+00

Pos logit contributions
Unfortunately+0.011
Meanwhile+0.011
eyed+0.011
 pounding+0.010
Just+0.010
Neg logit contributions
 happens-0.009
 is-0.008
 doesn-0.008
 isn-0.008
 belongs-0.008
TokenHere
Token ID4342
Feature activation+5.09e+00

Pos logit contributions
rolling+0.057
 pounding+0.056
Meanwhile+0.054
 sidelines+0.052
ooting+0.052
Neg logit contributions
 happens-0.061
 is-0.061
 doesn-0.057
 guys-0.057
 belongs-0.057
Token it
Token ID340
Feature activation+2.92e+00

Pos logit contributions
unn+0.265
akes+0.257
elly+0.246
ancer+0.244
 guys+0.243
Neg logit contributions
 free-0.132
Her-0.127
But-0.124
The-0.122
 unt-0.114
Token is
Token ID318
Feature activation+1.17e+00

Pos logit contributions
 guys+0.056
unn+0.050
 cares+0.046
 happens+0.040
ishes+0.039
Neg logit contributions
 aside-0.174
 lower-0.173
 carefully-0.170
Just-0.169
eyed-0.169
Token!
Token ID0
Feature activation+1.80e+00

Pos logit contributions
 happens+0.040
 guys+0.038
 doesn+0.038
 isn+0.037
unn+0.037
Neg logit contributions
Unfortunately-0.060
Meanwhile-0.058
Just-0.058
eyed-0.057
 widening-0.057
Token It
Token ID632
Feature activation+2.51e+00

Pos logit contributions
 guys+0.071
 happens+0.070
 belongs+0.066
 happened+0.066
 doesn+0.065
Neg logit contributions
Unfortunately-0.086
eyed-0.081
Just-0.080
His-0.080
Meanwhile-0.079
Token is
Token ID318
Feature activation+5.78e-02

Pos logit contributions
 guys+0.053
mm+0.051
unn+0.047
 happens+0.044
 happened+0.041
Neg logit contributions
Unfortunately-0.146
 lower-0.145
Meanwhile-0.143
 unt-0.142
 victorious-0.142
Token"
Token ID1
Feature activation-4.50e-01

Pos logit contributions
 pounding+0.066
rolling+0.064
 widening+0.064
Unfortunately+0.062
 sidelines+0.062
Neg logit contributions
 is-0.051
 happens-0.046
 belongs-0.044
?"-0.043
 wants-0.043
TokenHello
Token ID15496
Feature activation+4.17e+00

Pos logit contributions
Unfortunately+0.019
eyed+0.018
Meanwhile+0.018
rolling+0.018
 pounding+0.018
Neg logit contributions
 happens-0.022
 is-0.021
 doesn-0.020
 isn-0.020
 belongs-0.020
Token,
Token ID11
Feature activation+1.52e+00

Pos logit contributions
 belongs+0.219
 doesn+0.208
 needs+0.203
 vitamins+0.201
 happens+0.199
Neg logit contributions
Suddenly-0.116
But-0.114
 closer-0.112
On-0.111
 slowly-0.108
Token children
Token ID1751
Feature activation+2.08e+00

Pos logit contributions
 happens+0.056
 belongs+0.053
 doesn+0.052
 guys+0.052
 isn+0.048
Neg logit contributions
Meanwhile-0.078
Unfortunately-0.076
 crashing-0.072
 sidelines-0.070
eyed-0.070
Token.
Token ID13
Feature activation+3.28e+00

Pos logit contributions
 happens+0.104
 guys+0.099
 doesn+0.094
 belongs+0.092
 isn+0.092
Neg logit contributions
eyed-0.087
Unfortunately-0.077
har-0.076
 widening-0.076
Meanwhile-0.076
Token Who
Token ID5338
Feature activation+5.08e+00

Pos logit contributions
 happens+0.136
 guys+0.136
ishes+0.128
 doesn+0.125
 belongs+0.123
Neg logit contributions
eyed-0.149
Unfortunately-0.136
Just-0.134
Meanwhile-0.131
But-0.130
Token are
Token ID389
Feature activation+2.18e+00

Pos logit contributions
unn+0.174
ummy+0.171
ishes+0.167
umm+0.164
 guys+0.161
Neg logit contributions
eyed-0.197
 unt-0.195
On-0.187
 overcome-0.187
The-0.182
Token you
Token ID345
Feature activation+1.14e+00

Pos logit contributions
 doesn+0.072
 happens+0.069
 isn+0.068
 belongs+0.065
 needs+0.063
Neg logit contributions
Unfortunately-0.118
eyed-0.117
Just-0.114
Meanwhile-0.114
Her-0.113
Token?
Token ID30
Feature activation+2.23e+00

Pos logit contributions
 happens+0.022
 doesn+0.020
 belongs+0.020
 isn+0.020
 guys+0.020
Neg logit contributions
eyed-0.078
Meanwhile-0.078
Just-0.077
Unfortunately-0.076
On-0.075
Token What
Token ID1867
Feature activation+4.35e+00

Pos logit contributions
 guys+0.085
 happens+0.082
 doesn+0.076
 belongs+0.076
 isn+0.072
Neg logit contributions
eyed-0.118
Unfortunately-0.112
Just-0.111
Meanwhile-0.110
His-0.108
Token do
Token ID466
Feature activation+2.82e+00

Pos logit contributions
ishes+0.192
unn+0.177
ish+0.162
ley+0.158
uffy+0.158
Neg logit contributions
On-0.170
 understand-0.168
The-0.161
His-0.159
 overcome-0.157
Token a
Token ID257
Feature activation-2.30e+00

Pos logit contributions
eyed+0.137
Unfortunately+0.136
Meanwhile+0.133
Finally+0.132
Days+0.131
Neg logit contributions
 is-0.064
 happens-0.051
 doesn-0.050
 guys-0.049
 isn-0.049
Token swing
Token ID9628
Feature activation-2.10e+00

Pos logit contributions
eyed+0.118
Unfortunately+0.117
Meanwhile+0.116
Just+0.109
har+0.107
Neg logit contributions
 is-0.098
 can-0.088
 belongs-0.088
 isn-0.086
 happens-0.084
Token and
Token ID290
Feature activation-5.38e-01

Pos logit contributions
Unfortunately+0.136
eyed+0.133
Meanwhile+0.131
Finally+0.130
har+0.130
Neg logit contributions
 is-0.064
 doesn-0.054
 isn-0.054
 can-0.051
 belongs-0.049
Token pumped
Token ID29104
Feature activation-2.55e+00

Pos logit contributions
Unfortunately+0.024
Meanwhile+0.023
eyed+0.023
 widening+0.022
Just+0.022
Neg logit contributions
 happens-0.025
 is-0.024
 doesn-0.024
 isn-0.023
 belongs-0.023
Token his
Token ID465
Feature activation-6.65e-01

Pos logit contributions
Unfortunately+0.160
Meanwhile+0.158
Finally+0.153
Days+0.152
eyed+0.151
Neg logit contributions
 is-0.087
 happens-0.074
 isn-0.073
 doesn-0.071
 guys-0.067
Token legs
Token ID7405
Feature activation-5.42e+00

Pos logit contributions
Unfortunately+0.032
Meanwhile+0.032
eyed+0.031
 widening+0.030
However+0.029
Neg logit contributions
 happens-0.029
 is-0.029
 guys-0.028
 doesn-0.028
 belongs-0.028
Token back
Token ID736
Feature activation-2.13e+00

Pos logit contributions
 sidelines+0.357
har+0.354
Unfortunately+0.345
Days+0.336
Meanwhile+0.335
Neg logit contributions
,-0.142
 is-0.130
 can-0.124
 doesn-0.087
 are-0.084
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
Unfortunately+0.128
Meanwhile+0.126
 sidelines+0.121
Days+0.119
Finally+0.119
Neg logit contributions
 is-0.075
 doesn-0.064
 belongs-0.063
 isn-0.063
 happens-0.063
Token forth
Token ID6071
Feature activation-2.93e+00

Pos logit contributions
Unfortunately+0.070
eyed+0.068
Meanwhile+0.067
Days+0.066
Finally+0.065
Neg logit contributions
 happens-0.065
 is-0.064
 doesn-0.062
 isn-0.060
 belongs-0.058
Token.
Token ID13
Feature activation+4.08e-01

Pos logit contributions
Unfortunately+0.214
Meanwhile+0.210
 sidelines+0.200
har+0.198
eyed+0.197
Neg logit contributions
 is-0.067
 can-0.055
 isn-0.055
 guys-0.053
 doesn-0.052
Token He
Token ID679
Feature activation-3.91e-01

Pos logit contributions
 happens+0.023
 belongs+0.022
 guys+0.022
 doesn+0.022
 is+0.022
Neg logit contributions
Unfortunately-0.014
Meanwhile-0.014
eyed-0.013
Just-0.013
 widening-0.013
Token this
Token ID428
Feature activation+9.22e-01

Pos logit contributions
 happens+0.058
 guys+0.052
 belongs+0.050
 doesn+0.049
 isn+0.048
Neg logit contributions
Unfortunately-0.105
Meanwhile-0.105
eyed-0.103
On-0.099
 pounding-0.098
Token egg
Token ID5935
Feature activation+1.77e+00

Pos logit contributions
 happens+0.032
 guys+0.031
 doesn+0.030
 belongs+0.029
 isn+0.029
Neg logit contributions
Unfortunately-0.050
Meanwhile-0.049
eyed-0.047
Just-0.047
 widening-0.046
Token?"
Token ID1701
Feature activation-8.15e-01

Pos logit contributions
 happens+0.031
 guys+0.029
 isn+0.024
 doesn+0.024
 belongs+0.023
Neg logit contributions
Meanwhile-0.123
Unfortunately-0.122
eyed-0.120
 pounding-0.118
Just-0.117
Token he
Token ID339
Feature activation-2.04e+00

Pos logit contributions
Unfortunately+0.039
Meanwhile+0.038
 widening+0.037
eyed+0.037
 pounding+0.037
Neg logit contributions
 happens-0.034
 is-0.034
 doesn-0.033
 belongs-0.032
 isn-0.032
Token said
Token ID531
Feature activation-2.48e+00

Pos logit contributions
 sidelines+0.114
Unfortunately+0.110
har+0.107
 crashing+0.107
eyed+0.106
Neg logit contributions
 happens-0.074
 is-0.071
 means-0.069
 doesn-0.068
 guys-0.065
Token,
Token ID11
Feature activation-5.36e+00

Pos logit contributions
Unfortunately+0.178
 sidelines+0.176
Meanwhile+0.176
Finally+0.175
Eventually+0.173
Neg logit contributions
 is-0.043
 happens-0.042
 doesn-0.037
?"-0.035
 means-0.035
Token holding
Token ID4769
Feature activation+1.19e-01

Pos logit contributions
Unfortunately+0.281
Eventually+0.279
Finally+0.278
Days+0.278
Years+0.271
Neg logit contributions
,-0.180
 brother-0.161
?"-0.159
 I-0.159
 is-0.155
Token it
Token ID340
Feature activation-2.57e+00

Pos logit contributions
 happens+0.005
 is+0.005
 doesn+0.005
 belongs+0.005
 isn+0.005
Neg logit contributions
Unfortunately-0.005
Meanwhile-0.005
eyed-0.005
Just-0.005
 widening-0.005
Token up
Token ID510
Feature activation-3.07e+00

Pos logit contributions
 sidelines+0.141
Unfortunately+0.139
Meanwhile+0.135
Finally+0.132
Eventually+0.130
Neg logit contributions
 is-0.098
 doesn-0.092
 belongs-0.089
 needs-0.088
 isn-0.087
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
 sidelines+0.217
Unfortunately+0.210
Eventually+0.202
Days+0.201
Meanwhile+0.201
Neg logit contributions
 is-0.064
,-0.059
 doesn-0.051
?-0.051
 happened-0.051
Token
Token ID220
Feature activation-6.84e-01

Pos logit contributions
eyed+0.085
Unfortunately+0.084
Meanwhile+0.084
Days+0.084
har+0.084
Neg logit contributions
 is-0.068
 happens-0.067
 isn-0.064
 doesn-0.064
 means-0.060
Token your
Token ID534
Feature activation+9.47e-01

Pos logit contributions
 happens+0.008
 belongs+0.008
 is+0.008
 doesn+0.008
 isn+0.007
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.016
eyed-0.016
Just-0.016
 pounding-0.015
Token trip
Token ID5296
Feature activation+4.43e-01

Pos logit contributions
 happens+0.042
 belongs+0.039
 doesn+0.039
 is+0.038
 isn+0.038
Neg logit contributions
Unfortunately-0.042
Meanwhile-0.041
eyed-0.040
 pounding-0.040
Just-0.039
Token!"
Token ID2474
Feature activation-1.03e+00

Pos logit contributions
 happens+0.016
 doesn+0.015
 belongs+0.015
 is+0.015
 guys+0.015
Neg logit contributions
Unfortunately-0.024
Meanwhile-0.024
eyed-0.023
Just-0.022
 pounding-0.022
Token Dad
Token ID17415
Feature activation-2.03e+00

Pos logit contributions
Unfortunately+0.055
Meanwhile+0.054
eyed+0.054
 widening+0.053
 pounding+0.053
Neg logit contributions
 is-0.036
 happens-0.035
 doesn-0.035
 isn-0.034
 belongs-0.033
Token said
Token ID531
Feature activation-2.42e+00

Pos logit contributions
Unfortunately+0.125
 sidelines+0.124
Days+0.120
Meanwhile+0.118
Hours+0.117
Neg logit contributions
 is-0.059
 doesn-0.053
 isn-0.053
 happens-0.052
 means-0.051
Token,
Token ID11
Feature activation-5.34e+00

Pos logit contributions
Unfortunately+0.174
Meanwhile+0.173
Finally+0.170
 sidelines+0.169
Eventually+0.167
Neg logit contributions
 is-0.041
 happens-0.037
 doesn-0.035
 isn-0.034
 guys-0.033
Token picking
Token ID10868
Feature activation-5.28e-01

Pos logit contributions
Days+0.253
Unfortunately+0.247
Finally+0.245
Eventually+0.245
Years+0.241
Neg logit contributions
,-0.186
 I-0.175
?"-0.165
 is-0.162
 brother-0.162
Token her
Token ID607
Feature activation+3.60e-02

Pos logit contributions
Unfortunately+0.025
Meanwhile+0.024
eyed+0.024
Just+0.023
 pounding+0.023
Neg logit contributions
 is-0.023
 happens-0.023
 doesn-0.023
 isn-0.022
 belongs-0.022
Token up
Token ID510
Feature activation-1.02e+00

Pos logit contributions
 happens+0.002
 is+0.002
 doesn+0.002
 belongs+0.002
 isn+0.002
Neg logit contributions
Unfortunately-0.002
Meanwhile-0.002
eyed-0.001
Just-0.001
 widening-0.001
Token and
Token ID290
Feature activation-2.46e+00

Pos logit contributions
Unfortunately+0.054
Meanwhile+0.054
eyed+0.052
Just+0.051
Finally+0.050
Neg logit contributions
 is-0.039
 doesn-0.038
 happens-0.037
 isn-0.037
 belongs-0.036
Token spinning
Token ID19493
Feature activation-9.95e-01

Pos logit contributions
Unfortunately+0.110
Days+0.109
Finally+0.106
Just+0.104
Meanwhile+0.102
Neg logit contributions
 is-0.113
 doesn-0.106
 isn-0.106
 happens-0.103
 needs-0.101
Token so
Token ID523
Feature activation-5.18e-01

Pos logit contributions
eyed+0.169
rolling+0.164
Finally+0.163
Days+0.161
har+0.159
Neg logit contributions
 doesn-0.108
 is-0.106
 isn-0.103
 can-0.090
 needs-0.089
Token he
Token ID339
Feature activation-6.23e-01

Pos logit contributions
Unfortunately+0.027
Meanwhile+0.027
eyed+0.027
 widening+0.026
Just+0.025
Neg logit contributions
 happens-0.020
 is-0.019
 doesn-0.019
 isn-0.018
 needs-0.018
Token stomp
Token ID32221
Feature activation-4.45e-01

Pos logit contributions
Unfortunately+0.027
Meanwhile+0.027
eyed+0.027
 widening+0.026
 sidelines+0.025
Neg logit contributions
 happens-0.029
 doesn-0.028
 is-0.028
 guys-0.028
 isn-0.028
Tokened
Token ID276
Feature activation-1.75e+00

Pos logit contributions
Unfortunately+0.028
Meanwhile+0.027
 widening+0.026
eyed+0.026
 sidelines+0.026
Neg logit contributions
 happens-0.013
 is-0.012
 guys-0.012
 doesn-0.012
 isn-0.012
Token his
Token ID465
Feature activation-1.04e+00

Pos logit contributions
Meanwhile+0.090
Unfortunately+0.088
Finally+0.086
 widening+0.085
rolling+0.083
Neg logit contributions
 is-0.074
 isn-0.071
 doesn-0.070
 happens-0.069
 guys-0.069
Token feet
Token ID3625
Feature activation-5.33e+00

Pos logit contributions
Unfortunately+0.057
Meanwhile+0.056
eyed+0.054
 widening+0.053
His+0.052
Neg logit contributions
 is-0.039
 belongs-0.036
 doesn-0.036
 needs-0.036
 isn-0.036
Token and
Token ID290
Feature activation-1.57e+00

Pos logit contributions
Finally+0.360
Unfortunately+0.352
Eventually+0.347
Meanwhile+0.347
har+0.339
Neg logit contributions
 is-0.105
,-0.101
 doesn-0.083
 can-0.083
 isn-0.065
Token shouted
Token ID17293
Feature activation-8.11e-01

Pos logit contributions
Unfortunately+0.078
eyed+0.077
Meanwhile+0.076
Finally+0.076
rolling+0.074
Neg logit contributions
 doesn-0.064
 happens-0.064
 is-0.063
 guys-0.061
 isn-0.060
Token.
Token ID13
Feature activation-8.06e-01

Pos logit contributions
Meanwhile+0.051
Unfortunately+0.051
eyed+0.049
 widening+0.048
Finally+0.048
Neg logit contributions
 happens-0.023
 is-0.023
 isn-0.022
 doesn-0.022
 guys-0.022
Token Everyone
Token ID11075
Feature activation-6.93e-01

Pos logit contributions
Meanwhile+0.038
Unfortunately+0.038
eyed+0.038
 pounding+0.036
 widening+0.036
Neg logit contributions
 is-0.033
 happens-0.033
 isn-0.032
 doesn-0.032
 belongs-0.031
Token in
Token ID287
Feature activation+1.64e-02

Pos logit contributions
Unfortunately+0.039
Meanwhile+0.038
 widening+0.037
Finally+0.036
eyed+0.036
Neg logit contributions
 happens-0.025
 is-0.024
 doesn-0.023
 isn-0.023
 belongs-0.022
Token I
Token ID314
Feature activation-6.13e-02

Pos logit contributions
unn+0.104
uffy+0.100
 belongs+0.097
ishes+0.096
ens+0.096
Neg logit contributions
His-0.154
Unfortunately-0.154
 impressed-0.151
 determined-0.149
 victorious-0.148
Token made
Token ID925
Feature activation+5.23e-01

Pos logit contributions
Unfortunately+0.003
Meanwhile+0.003
eyed+0.003
 widening+0.003
Just+0.003
Neg logit contributions
 happens-0.002
 is-0.002
 doesn-0.002
 belongs-0.002
 isn-0.002
Token!"
Token ID2474
Feature activation-9.58e-01

Pos logit contributions
 happens+0.017
 doesn+0.016
 belongs+0.016
 is+0.015
 guys+0.015
Neg logit contributions
Unfortunately-0.030
Meanwhile-0.029
eyed-0.029
Just-0.028
 widening-0.028
Token James
Token ID3700
Feature activation-2.24e+00

Pos logit contributions
Unfortunately+0.051
Meanwhile+0.050
eyed+0.049
 pounding+0.049
Days+0.048
Neg logit contributions
 happens-0.035
 is-0.035
 doesn-0.034
 isn-0.033
 belongs-0.032
Token said
Token ID531
Feature activation-3.20e+00

Pos logit contributions
 sidelines+0.121
Unfortunately+0.121
Days+0.120
Years+0.116
Meanwhile+0.115
Neg logit contributions
 is-0.081
 happens-0.074
 doesn-0.073
 isn-0.072
 needs-0.067
Token,
Token ID11
Feature activation-5.32e+00

Pos logit contributions
Meanwhile+0.217
 sidelines+0.217
Unfortunately+0.217
Finally+0.214
Days+0.212
Neg logit contributions
 is-0.065
,-0.062
 happens-0.061
 brother-0.058
 sister-0.055
Token folding
Token ID29909
Feature activation-1.47e+00

Pos logit contributions
Days+0.282
Unfortunately+0.269
Finally+0.266
Years+0.265
Eventually+0.263
Neg logit contributions
,-0.174
 I-0.172
 is-0.152
?"-0.150
 we-0.144
Token his
Token ID465
Feature activation-1.44e-01

Pos logit contributions
Meanwhile+0.080
Unfortunately+0.080
Just+0.076
eyed+0.076
rolling+0.075
Neg logit contributions
 is-0.059
 isn-0.055
 doesn-0.054
 happens-0.054
 belongs-0.052
Token arms
Token ID5101
Feature activation-3.98e+00

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.006
Just+0.006
 widening+0.006
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token in
Token ID287
Feature activation-2.30e+00

Pos logit contributions
Unfortunately+0.254
Days+0.244
Meanwhile+0.242
har+0.240
 sidelines+0.239
Neg logit contributions
 is-0.115
 doesn-0.102
 isn-0.101
 can-0.100
 happens-0.089
Token front
Token ID2166
Feature activation-2.42e+00

Pos logit contributions
rolling+0.121
Just+0.121
Meanwhile+0.121
ooting+0.120
Unfortunately+0.119
Neg logit contributions
 is-0.093
 isn-0.087
 can-0.080
 doesn-0.078
 needs-0.077
Token swinging
Token ID25635
Feature activation-2.80e+00

Pos logit contributions
Unfortunately+0.205
Finally+0.202
Days+0.196
Meanwhile+0.194
Eventually+0.193
Neg logit contributions
 is-0.091
 happens-0.075
 doesn-0.071
 isn-0.070
 things-0.069
Token.
Token ID13
Feature activation-1.26e+00

Pos logit contributions
Unfortunately+0.163
Meanwhile+0.162
eyed+0.156
Finally+0.156
rolling+0.155
Neg logit contributions
 is-0.104
 can-0.087
 isn-0.087
 doesn-0.086
 happens-0.085
Token He
Token ID679
Feature activation-1.14e+00

Pos logit contributions
Meanwhile+0.061
 pounding+0.061
Unfortunately+0.060
eyed+0.060
 widening+0.060
Neg logit contributions
 isn-0.050
 is-0.050
 doesn-0.048
 happens-0.046
 belongs-0.045
Token pumped
Token ID29104
Feature activation-2.77e+00

Pos logit contributions
Unfortunately+0.058
Meanwhile+0.056
eyed+0.055
 widening+0.054
 sidelines+0.053
Neg logit contributions
 is-0.048
 happens-0.047
 doesn-0.045
 isn-0.045
 belongs-0.043
Token his
Token ID465
Feature activation-1.08e+00

Pos logit contributions
Unfortunately+0.160
eyed+0.155
har+0.154
Meanwhile+0.153
Finally+0.152
Neg logit contributions
 is-0.102
 isn-0.088
 doesn-0.086
 guys-0.084
 happens-0.084
Token legs
Token ID7405
Feature activation-5.27e+00

Pos logit contributions
Unfortunately+0.055
Meanwhile+0.054
eyed+0.051
 widening+0.050
Finally+0.049
Neg logit contributions
 is-0.045
 happens-0.044
 doesn-0.044
 isn-0.043
 guys-0.043
Token higher
Token ID2440
Feature activation-2.21e+00

Pos logit contributions
har+0.353
 sidelines+0.350
Unfortunately+0.347
Days+0.337
Sadly+0.332
Neg logit contributions
,-0.123
 is-0.122
 can-0.107
 are-0.075
 doesn-0.072
Token and
Token ID290
Feature activation-1.76e+00

Pos logit contributions
Unfortunately+0.139
Meanwhile+0.133
 sidelines+0.133
eyed+0.132
rolling+0.131
Neg logit contributions
 is-0.069
 doesn-0.057
 isn-0.054
 happens-0.053
 guys-0.051
Token higher
Token ID2440
Feature activation-1.48e+00

Pos logit contributions
Unfortunately+0.052
eyed+0.052
Meanwhile+0.049
Days+0.047
Their+0.045
Neg logit contributions
 is-0.109
 happens-0.109
 doesn-0.107
 isn-0.105
 can-0.101
Token as
Token ID355
Feature activation-3.32e-01

Pos logit contributions
Unfortunately+0.085
Meanwhile+0.082
eyed+0.079
Finally+0.077
rolling+0.077
Neg logit contributions
 is-0.053
 doesn-0.049
 happens-0.049
 isn-0.048
 guys-0.046
Token he
Token ID339
Feature activation-6.03e-01

Pos logit contributions
Unfortunately+0.017
Meanwhile+0.017
eyed+0.016
Just+0.016
 widening+0.015
Neg logit contributions
 happens-0.013
 is-0.013
 doesn-0.013
 isn-0.012
 guys-0.012
Token,
Token ID11
Feature activation+9.17e-01

Pos logit contributions
 happens+0.053
 guys+0.050
 belongs+0.048
 doesn+0.047
 needs+0.045
Neg logit contributions
Unfortunately-0.102
eyed-0.099
Meanwhile-0.099
Just-0.096
 pounding-0.095
Token Mama
Token ID40084
Feature activation+1.93e+00

Pos logit contributions
 happens+0.036
 belongs+0.035
 guys+0.033
 is+0.033
 needs+0.032
Neg logit contributions
Unfortunately-0.046
Meanwhile-0.046
eyed-0.043
 pounding-0.043
Just-0.043
Token!"
Token ID2474
Feature activation-1.54e+00

Pos logit contributions
 happens+0.063
 belongs+0.058
 guys+0.056
 doesn+0.054
 isn+0.053
Neg logit contributions
eyed-0.108
Meanwhile-0.108
Unfortunately-0.105
 pounding-0.105
Just-0.101
Token Drake
Token ID18515
Feature activation-8.49e-01

Pos logit contributions
Days+0.085
 widening+0.085
eyed+0.085
Unfortunately+0.085
 sidelines+0.084
Neg logit contributions
 happens-0.050
 is-0.049
 doesn-0.047
 isn-0.046
 means-0.045
Token said
Token ID531
Feature activation-2.37e+00

Pos logit contributions
Unfortunately+0.044
Meanwhile+0.042
 sidelines+0.042
eyed+0.041
 widening+0.041
Neg logit contributions
 happens-0.033
 is-0.032
 doesn-0.032
 belongs-0.031
 isn-0.031
Token,
Token ID11
Feature activation-5.24e+00

Pos logit contributions
Unfortunately+0.148
 sidelines+0.144
Meanwhile+0.144
Finally+0.141
Days+0.140
Neg logit contributions
 happens-0.069
 is-0.067
 happened-0.061
 guys-0.059
 doesn-0.059
Token amazed
Token ID24562
Feature activation-5.67e-01

Pos logit contributions
Days+0.264
Unfortunately+0.262
Years+0.260
Finally+0.249
Eventually+0.248
Neg logit contributions
 I-0.178
,-0.176
?"-0.170
 is-0.170
 we-0.157
Token.
Token ID13
Feature activation-2.36e+00

Pos logit contributions
Unfortunately+0.034
Meanwhile+0.033
eyed+0.031
Finally+0.031
Just+0.031
Neg logit contributions
 happens-0.018
 is-0.017
 doesn-0.017
 isn-0.017
 guys-0.017
Token
Token ID198
Feature activation-2.30e+00

Pos logit contributions
 sidelines+0.129
 widening+0.128
har+0.127
Days+0.124
 pounding+0.123
Neg logit contributions
 is-0.085
 isn-0.082
 doesn-0.079
 happens-0.079
 can-0.076
Token
Token ID198
Feature activation-2.77e+00

Pos logit contributions
 widening+0.141
 sidelines+0.140
 pounding+0.129
side+0.129
 winding+0.126
Neg logit contributions
 is-0.077
 happens-0.067
?"-0.066
 can-0.065
 isn-0.063
TokenM
Token ID44
Feature activation-6.61e-01

Pos logit contributions
 widening+0.142
 sidelines+0.139
 contain+0.125
 ledge+0.124
side+0.123
Neg logit contributions
 is-0.111
 can-0.107
 happens-0.101
 isn-0.097
 doesn-0.096
Token Mom
Token ID11254
Feature activation+1.58e+00

Pos logit contributions
 happens+0.038
 guys+0.037
 belongs+0.037
 doesn+0.034
 needs+0.034
Neg logit contributions
Unfortunately-0.048
Meanwhile-0.046
Just-0.044
 pounding-0.043
However-0.043
Token,"
Token ID553
Feature activation+7.97e-02

Pos logit contributions
 happens+0.052
 guys+0.049
 belongs+0.048
 isn+0.046
 doesn+0.045
Neg logit contributions
eyed-0.088
Meanwhile-0.087
Unfortunately-0.086
 pounding-0.085
Just-0.082
Token she
Token ID673
Feature activation-1.53e+00

Pos logit contributions
 happens+0.003
 is+0.003
 doesn+0.003
 belongs+0.003
 isn+0.003
Neg logit contributions
Unfortunately-0.004
Meanwhile-0.004
eyed-0.004
Just-0.004
 widening-0.004
Token said
Token ID531
Feature activation-2.29e+00

Pos logit contributions
 sidelines+0.099
Unfortunately+0.095
eyed+0.095
side+0.094
Meanwhile+0.092
Neg logit contributions
 happens-0.043
 is-0.040
 doesn-0.040
 isn-0.037
 belongs-0.036
Token quietly
Token ID12703
Feature activation-3.25e+00

Pos logit contributions
Unfortunately+0.169
Meanwhile+0.168
Finally+0.166
 sidelines+0.165
Eventually+0.163
Neg logit contributions
 is-0.036
 happens-0.033
 doesn-0.032
 brother-0.029
 isn-0.027
Token,
Token ID11
Feature activation-5.14e+00

Pos logit contributions
Unfortunately+0.266
Finally+0.258
Eventually+0.255
Days+0.251
Meanwhile+0.251
Neg logit contributions
,-0.032
 is-0.029
 brother-0.028
 happens-0.026
 doesn-0.024
Token her
Token ID607
Feature activation-5.63e-01

Pos logit contributions
Finally+0.279
Days+0.278
Unfortunately+0.278
Years+0.275
Hours+0.271
Neg logit contributions
 doesn-0.147
,-0.146
 is-0.145
 I-0.141
 isn-0.135
Token eyes
Token ID2951
Feature activation-4.60e+00

Pos logit contributions
Unfortunately+0.035
Meanwhile+0.034
eyed+0.033
Just+0.033
Finally+0.032
Neg logit contributions
 is-0.017
 happens-0.016
 doesn-0.016
 isn-0.016
 needs-0.016
Token full
Token ID1336
Feature activation-1.65e+00

Pos logit contributions
Unfortunately+0.268
Meanwhile+0.254
 sidelines+0.253
Finally+0.246
Eventually+0.244
Neg logit contributions
 is-0.152
 happened-0.147
 can-0.145
 happens-0.141
 doesn-0.138
Token of
Token ID286
Feature activation-7.16e-02

Pos logit contributions
Unfortunately+0.103
Meanwhile+0.102
rolling+0.098
Finally+0.098
eyed+0.098
Neg logit contributions
 is-0.049
 happens-0.046
 isn-0.046
 doesn-0.045
 needs-0.042
Token tears
Token ID10953
Feature activation-1.60e+00

Pos logit contributions
Unfortunately+0.003
Meanwhile+0.003
eyed+0.003
Just+0.003
 widening+0.003
Neg logit contributions
 happens-0.003
 is-0.003
 doesn-0.003
 belongs-0.003
 isn-0.003
Token than
Token ID621
Feature activation+1.04e+00

Pos logit contributions
 happens+0.044
 belongs+0.042
 doesn+0.040
 needs+0.039
 isn+0.039
Neg logit contributions
Unfortunately-0.081
eyed-0.080
Meanwhile-0.079
Just-0.078
 pounding-0.078
Token yours
Token ID12431
Feature activation+1.78e+00

Pos logit contributions
 happens+0.031
 belongs+0.030
 doesn+0.029
 is+0.029
 isn+0.028
Neg logit contributions
Unfortunately-0.061
Meanwhile-0.060
eyed-0.058
Just-0.057
 sidelines-0.057
Token!"
Token ID2474
Feature activation+6.79e-01

Pos logit contributions
 happens+0.052
 doesn+0.048
 belongs+0.047
 guys+0.047
 isn+0.046
Neg logit contributions
eyed-0.101
Unfortunately-0.099
Meanwhile-0.097
 pounding-0.096
Just-0.096
Token Ben
Token ID3932
Feature activation-1.10e+00

Pos logit contributions
 belongs+0.024
 happens+0.024
 guys+0.024
 doesn+0.024
 isn+0.023
Neg logit contributions
Unfortunately-0.037
Meanwhile-0.036
eyed-0.035
Just-0.034
 widening-0.034
Token said
Token ID531
Feature activation-1.76e+00

Pos logit contributions
Unfortunately+0.062
Meanwhile+0.060
 sidelines+0.059
Days+0.058
Finally+0.058
Neg logit contributions
 is-0.038
 doesn-0.037
 happens-0.037
 isn-0.037
 belongs-0.035
Token,
Token ID11
Feature activation-5.12e+00

Pos logit contributions
Unfortunately+0.121
Meanwhile+0.120
Finally+0.117
Eventually+0.115
 sidelines+0.114
Neg logit contributions
 happens-0.038
 is-0.037
 guys-0.036
 doesn-0.035
 isn-0.034
Token z
Token ID1976
Feature activation-4.05e-01

Pos logit contributions
Unfortunately+0.271
Finally+0.266
Eventually+0.264
Days+0.258
Years+0.253
Neg logit contributions
,-0.163
 I-0.162
 is-0.153
 brother-0.145
?"-0.145
Tokenooming
Token ID30602
Feature activation-1.96e+00

Pos logit contributions
Unfortunately+0.018
Meanwhile+0.018
eyed+0.016
 widening+0.016
 pounding+0.016
Neg logit contributions
 happens-0.019
 is-0.018
 guys-0.018
 doesn-0.018
 belongs-0.018
Token his
Token ID465
Feature activation-1.06e+00

Pos logit contributions
Unfortunately+0.104
Finally+0.100
Meanwhile+0.099
Eventually+0.096
rolling+0.096
Neg logit contributions
 is-0.078
 guys-0.077
 happens-0.074
 isn-0.072
 doesn-0.071
Token red
Token ID2266
Feature activation-6.05e-01

Pos logit contributions
Unfortunately+0.061
Meanwhile+0.060
eyed+0.057
Finally+0.056
 widening+0.055
Neg logit contributions
 guys-0.038
 is-0.038
 doesn-0.036
 happens-0.036
 belongs-0.036
Token boat
Token ID8848
Feature activation-3.97e+00

Pos logit contributions
Unfortunately+0.031
Meanwhile+0.030
eyed+0.029
 widening+0.028
Just+0.028
Neg logit contributions
 is-0.025
 guys-0.024
 happens-0.024
 belongs-0.024
 doesn-0.024
Token star
Token ID3491
Feature activation+2.50e+00

Pos logit contributions
 happens+0.032
 belongs+0.032
 doesn+0.031
 is+0.030
 isn+0.030
Neg logit contributions
Unfortunately-0.034
Meanwhile-0.033
eyed-0.033
 pounding-0.032
 widening-0.032
Tokenfish
Token ID11084
Feature activation+2.26e+00

Pos logit contributions
 guys+0.080
 happens+0.079
 doesn+0.076
 belongs+0.070
 isn+0.070
Neg logit contributions
eyed-0.127
 pounding-0.123
Meanwhile-0.122
 widening-0.121
 crashing-0.121
Token!"
Token ID2474
Feature activation+5.17e-01

Pos logit contributions
 happens+0.075
 guys+0.072
 doesn+0.070
 isn+0.067
 belongs+0.065
Neg logit contributions
eyed-0.114
 widening-0.111
Meanwhile-0.110
 pounding-0.110
Unfortunately-0.110
Token Sam
Token ID3409
Feature activation-1.13e+00

Pos logit contributions
 happens+0.018
 isn+0.017
 doesn+0.017
 belongs+0.017
 is+0.017
Neg logit contributions
Unfortunately-0.029
Meanwhile-0.029
eyed-0.027
Just-0.027
 widening-0.027
Token said
Token ID531
Feature activation-7.65e-01

Pos logit contributions
Unfortunately+0.069
 sidelines+0.067
Meanwhile+0.067
Finally+0.066
Eventually+0.065
Neg logit contributions
 is-0.033
 happens-0.032
 doesn-0.032
 belongs-0.031
 isn-0.030
Token,
Token ID11
Feature activation-5.10e+00

Pos logit contributions
Unfortunately+0.049
Meanwhile+0.049
Finally+0.046
 sidelines+0.046
Eventually+0.045
Neg logit contributions
 happens-0.021
 is-0.021
 doesn-0.019
 belongs-0.019
 guys-0.019
Token pointing
Token ID10609
Feature activation-7.59e-01

Pos logit contributions
Unfortunately+0.271
Finally+0.267
Eventually+0.262
Days+0.255
Years+0.254
Neg logit contributions
,-0.166
 is-0.161
 I-0.159
 brother-0.150
?"-0.149
Token to
Token ID284
Feature activation-5.93e-01

Pos logit contributions
Unfortunately+0.044
Meanwhile+0.043
 sidelines+0.041
Finally+0.040
 widening+0.040
Neg logit contributions
 is-0.027
 happens-0.027
 doesn-0.026
 isn-0.026
 belongs-0.025
Token a
Token ID257
Feature activation-1.53e+00

Pos logit contributions
Unfortunately+0.032
Meanwhile+0.032
eyed+0.031
Just+0.030
 pounding+0.030
Neg logit contributions
 is-0.022
 happens-0.022
 guys-0.022
 doesn-0.021
 isn-0.021
Token red
Token ID2266
Feature activation-2.38e-01

Pos logit contributions
Unfortunately+0.081
Meanwhile+0.079
eyed+0.077
Just+0.076
Days+0.073
Neg logit contributions
 is-0.062
 isn-0.059
 happens-0.059
 can-0.057
 doesn-0.057
Token and
Token ID290
Feature activation-3.38e-01

Pos logit contributions
Unfortunately+0.012
Meanwhile+0.012
eyed+0.012
Just+0.011
 pounding+0.011
Neg logit contributions
 happens-0.010
 is-0.009
 doesn-0.009
 belongs-0.009
 guys-0.009
Token to
Token ID284
Feature activation-2.28e-01

Pos logit contributions
Unfortunately+0.089
 sidelines+0.089
Meanwhile+0.088
Finally+0.085
 widening+0.084
Neg logit contributions
 is-0.049
 doesn-0.049
 isn-0.045
 guys-0.044
 happens-0.044
Token the
Token ID262
Feature activation-3.67e-01

Pos logit contributions
Unfortunately+0.012
Meanwhile+0.012
eyed+0.011
Just+0.011
 widening+0.011
Neg logit contributions
 happens-0.009
 is-0.009
 doesn-0.009
 belongs-0.009
 guys-0.008
Token bird
Token ID6512
Feature activation-1.18e+00

Pos logit contributions
Unfortunately+0.022
Meanwhile+0.022
eyed+0.021
Just+0.021
 widening+0.021
Neg logit contributions
 happens-0.011
 is-0.011
 doesn-0.011
 guys-0.011
 belongs-0.011
Token and
Token ID290
Feature activation-6.50e-01

Pos logit contributions
Unfortunately+0.070
Meanwhile+0.069
 widening+0.066
Finally+0.065
 sidelines+0.065
Neg logit contributions
 is-0.039
 doesn-0.038
 belongs-0.036
 needs-0.036
 isn-0.035
Token whispered
Token ID25029
Feature activation-1.29e+00

Pos logit contributions
Unfortunately+0.031
Meanwhile+0.031
eyed+0.030
 widening+0.029
Just+0.029
Neg logit contributions
 happens-0.028
 is-0.028
 doesn-0.027
 belongs-0.027
 guys-0.026
Token,
Token ID11
Feature activation-5.08e+00

Pos logit contributions
Unfortunately+0.067
Meanwhile+0.066
 sidelines+0.062
Finally+0.061
eyed+0.061
Neg logit contributions
 happens-0.052
 is-0.051
 guys-0.049
 doesn-0.049
 isn-0.048
Token "
Token ID366
Feature activation-1.80e+00

Pos logit contributions
Days+0.341
har+0.340
amed+0.339
inge+0.335
 sidelines+0.333
Neg logit contributions
 I-0.092
 is-0.077
 doesn-0.075
 we-0.073
 isn-0.072
TokenI
Token ID40
Feature activation+2.75e-01

Pos logit contributions
rolling+0.076
 pounding+0.076
 sidelines+0.076
 widening+0.075
Unfortunately+0.075
Neg logit contributions
 doesn-0.077
 is-0.076
 isn-0.075
 happens-0.074
 belongs-0.071
Token will
Token ID481
Feature activation-1.33e+00

Pos logit contributions
 happens+0.008
 belongs+0.008
 doesn+0.008
 guys+0.008
 is+0.008
Neg logit contributions
Unfortunately-0.016
Meanwhile-0.016
eyed-0.016
Just-0.016
 widening-0.015
Token miss
Token ID2051
Feature activation+8.06e-01

Pos logit contributions
Meanwhile+0.065
Unfortunately+0.062
 widening+0.058
eyed+0.058
 sidelines+0.058
Neg logit contributions
 is-0.061
 doesn-0.058
 happens-0.056
 isn-0.056
 needs-0.056
Token you
Token ID345
Feature activation+5.82e-01

Pos logit contributions
 happens+0.019
 belongs+0.018
 doesn+0.017
 is+0.017
 isn+0.017
Neg logit contributions
Unfortunately-0.052
Meanwhile-0.051
eyed-0.051
Just-0.050
 pounding-0.050
Token it
Token ID340
Feature activation+2.81e+00

Pos logit contributions
unn+0.108
 guys+0.095
ishes+0.088
 happens+0.086
 cares+0.083
Neg logit contributions
Meanwhile-0.187
Unfortunately-0.187
 ledge-0.186
 pounding-0.184
The-0.183
Token is
Token ID318
Feature activation+2.00e+00

Pos logit contributions
unn+0.095
 guys+0.094
mm+0.088
ishes+0.083
 cares+0.080
Neg logit contributions
Meanwhile-0.137
Unfortunately-0.130
Just-0.130
 pounding-0.128
On-0.127
Token!"
Token ID2474
Feature activation+2.98e-03

Pos logit contributions
unn+0.092
 happens+0.089
 belongs+0.086
 guys+0.085
 doesn+0.085
Neg logit contributions
Unfortunately-0.079
Meanwhile-0.077
 pounding-0.075
On-0.073
Just-0.071
Token Lily
Token ID20037
Feature activation-1.18e+00

Pos logit contributions
 happens+0.000
 is+0.000
 doesn+0.000
 belongs+0.000
 isn+0.000
Neg logit contributions
Unfortunately-0.000
Meanwhile-0.000
eyed-0.000
Just-0.000
 widening-0.000
Token whispered
Token ID25029
Feature activation-1.77e+00

Pos logit contributions
 sidelines+0.063
Unfortunately+0.063
eyed+0.061
Meanwhile+0.061
Finally+0.061
Neg logit contributions
 is-0.042
 doesn-0.041
 happens-0.040
 isn-0.039
 belongs-0.037
Token,
Token ID11
Feature activation-5.06e+00

Pos logit contributions
Unfortunately+0.116
Meanwhile+0.113
 sidelines+0.109
Finally+0.108
Eventually+0.108
Neg logit contributions
 guys-0.045
 happens-0.042
 is-0.042
 doesn-0.039
 brother-0.036
Token pointing
Token ID10609
Feature activation-5.38e-01

Pos logit contributions
Unfortunately+0.271
Finally+0.269
Eventually+0.267
Years+0.257
tted+0.248
Neg logit contributions
,-0.163
 brother-0.145
 is-0.144
 I-0.144
?"-0.135
Token to
Token ID284
Feature activation-3.79e-01

Pos logit contributions
Unfortunately+0.028
Meanwhile+0.027
 sidelines+0.025
Finally+0.025
 widening+0.025
Neg logit contributions
 happens-0.022
 is-0.022
 doesn-0.021
 isn-0.021
 belongs-0.021
Token the
Token ID262
Feature activation-1.68e-01

Pos logit contributions
Unfortunately+0.020
Meanwhile+0.020
eyed+0.019
Just+0.019
 widening+0.019
Neg logit contributions
 is-0.015
 happens-0.014
 guys-0.014
 doesn-0.014
 isn-0.014
Token doll
Token ID3654
Feature activation-6.25e-01

Pos logit contributions
Unfortunately+0.009
Meanwhile+0.009
eyed+0.009
Just+0.009
 pounding+0.009
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token.
Token ID13
Feature activation-1.28e+00

Pos logit contributions
Unfortunately+0.036
Meanwhile+0.035
eyed+0.034
Just+0.033
 widening+0.032
Neg logit contributions
 is-0.022
 happens-0.021
 belongs-0.021
 doesn-0.021
 isn-0.020
Token this
Token ID428
Feature activation+4.54e-01

Pos logit contributions
 happens+0.034
 belongs+0.034
 doesn+0.034
 isn+0.033
 needs+0.033
Neg logit contributions
Unfortunately-0.036
eyed-0.035
Meanwhile-0.035
Just-0.034
Finally-0.032
Token one
Token ID530
Feature activation+5.91e-01

Pos logit contributions
 happens+0.021
 doesn+0.020
 belongs+0.020
 guys+0.020
 is+0.020
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.020
eyed-0.019
 pounding-0.018
Just-0.018
Token!"
Token ID2474
Feature activation-1.25e+00

Pos logit contributions
 happens+0.024
 doesn+0.022
 guys+0.022
 belongs+0.022
 isn+0.022
Neg logit contributions
Unfortunately-0.030
Meanwhile-0.029
eyed-0.029
Just-0.028
 pounding-0.027
Token she
Token ID673
Feature activation-1.80e+00

Pos logit contributions
Unfortunately+0.070
Meanwhile+0.070
Days+0.069
 pounding+0.069
 sidelines+0.068
Neg logit contributions
 is-0.041
 happens-0.040
 isn-0.038
 doesn-0.037
 belongs-0.036
Token said
Token ID531
Feature activation-2.55e+00

Pos logit contributions
 sidelines+0.111
Unfortunately+0.110
Meanwhile+0.105
 crashing+0.105
eyed+0.105
Neg logit contributions
 happens-0.052
 is-0.050
 doesn-0.048
 isn-0.046
 means-0.046
Token,
Token ID11
Feature activation-5.06e+00

Pos logit contributions
Unfortunately+0.168
Meanwhile+0.168
 sidelines+0.163
Finally+0.162
Days+0.162
Neg logit contributions
 is-0.058
 happens-0.054
 doesn-0.052
 brother-0.049
 happened-0.048
Token picking
Token ID10868
Feature activation-1.00e+00

Pos logit contributions
Days+0.272
Unfortunately+0.266
Finally+0.256
Years+0.256
Hours+0.253
Neg logit contributions
,-0.152
 I-0.149
 is-0.141
?"-0.134
 doesn-0.133
Token up
Token ID510
Feature activation-1.49e-01

Pos logit contributions
Unfortunately+0.052
Meanwhile+0.051
Just+0.048
eyed+0.048
 pounding+0.048
Neg logit contributions
 is-0.041
 happens-0.040
 doesn-0.038
 isn-0.038
 belongs-0.038
Token the
Token ID262
Feature activation+3.49e-01

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
Just+0.007
 widening+0.007
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token bunny
Token ID44915
Feature activation-1.46e+00

Pos logit contributions
 happens+0.015
 doesn+0.014
 belongs+0.014
 is+0.014
 guys+0.014
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.017
eyed-0.016
 widening-0.016
 pounding-0.016
Token.
Token ID13
Feature activation-1.50e+00

Pos logit contributions
Unfortunately+0.084
Meanwhile+0.082
Finally+0.078
 sidelines+0.076
 widening+0.076
Neg logit contributions
 is-0.052
 belongs-0.048
 doesn-0.048
 isn-0.047
 needs-0.046
Token to
Token ID284
Feature activation-7.48e-01

Pos logit contributions
Unfortunately+0.118
eyed+0.114
Meanwhile+0.112
Finally+0.112
Days+0.110
Neg logit contributions
 is-0.050
 happens-0.046
 guys-0.044
 needs-0.042
 can-0.041
Token sleep
Token ID3993
Feature activation-9.36e-01

Pos logit contributions
Unfortunately+0.037
Meanwhile+0.037
Just+0.035
eyed+0.035
 widening+0.034
Neg logit contributions
 is-0.032
 happens-0.031
 doesn-0.030
 needs-0.030
 belongs-0.030
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
eyed+0.068
Unfortunately+0.068
Meanwhile+0.067
Just+0.064
har+0.064
Neg logit contributions
 is-0.017
 happens-0.016
 guys-0.015
 doesn-0.014
 isn-0.014
Token she
Token ID673
Feature activation-9.20e-01

Pos logit contributions
eyed+0.064
Unfortunately+0.060
Meanwhile+0.060
har+0.057
 widening+0.057
Neg logit contributions
 is-0.034
 happens-0.034
 doesn-0.033
 guys-0.033
 isn-0.032
Token whispered
Token ID25029
Feature activation-1.47e+00

Pos logit contributions
Unfortunately+0.049
eyed+0.048
Meanwhile+0.046
 sidelines+0.046
 widening+0.045
Neg logit contributions
 is-0.035
 happens-0.035
 doesn-0.034
 isn-0.033
 needs-0.032
Token,
Token ID11
Feature activation-5.05e+00

Pos logit contributions
Unfortunately+0.078
Meanwhile+0.074
 sidelines+0.072
Finally+0.072
eyed+0.071
Neg logit contributions
 happens-0.055
 is-0.054
 guys-0.054
 doesn-0.052
 isn-0.051
Token "
Token ID366
Feature activation-1.87e+00

Pos logit contributions
Days+0.334
inge+0.330
har+0.328
 sidelines+0.328
Unfortunately+0.327
Neg logit contributions
 is-0.088
 doesn-0.086
 I-0.084
 isn-0.080
 can-0.072
TokenI
Token ID40
Feature activation+8.51e-01

Pos logit contributions
Unfortunately+0.077
 victorious+0.075
 widening+0.075
eyed+0.074
 sidelines+0.074
Neg logit contributions
 doesn-0.080
 isn-0.079
 is-0.078
 happens-0.077
 guys-0.076
Token love
Token ID1842
Feature activation+1.34e+00

Pos logit contributions
 happens+0.033
 guys+0.033
 belongs+0.032
 isn+0.031
 doesn+0.031
Neg logit contributions
Unfortunately-0.041
eyed-0.041
Meanwhile-0.041
Just-0.039
 pounding-0.039
Token you
Token ID345
Feature activation+3.74e-01

Pos logit contributions
 happens+0.043
 belongs+0.041
 guys+0.038
 doesn+0.037
 is+0.035
Neg logit contributions
Unfortunately-0.077
Meanwhile-0.075
 pounding-0.073
Just-0.073
 crashing-0.072
Token,
Token ID11
Feature activation+3.23e-01

Pos logit contributions
 happens+0.014
 belongs+0.013
 doesn+0.013
 is+0.013
 isn+0.013
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.019
eyed-0.019
Just-0.019
 pounding-0.018
Token is
Token ID318
Feature activation+2.17e-01

Pos logit contributions
 guys+0.057
 happens+0.054
unn+0.048
 doesn+0.042
 lives+0.040
Neg logit contributions
Unfortunately-0.168
Meanwhile-0.166
 pounding-0.163
eyed-0.162
Just-0.160
Token gone
Token ID3750
Feature activation+1.50e+00

Pos logit contributions
 happens+0.010
 is+0.010
 doesn+0.010
 belongs+0.010
 guys+0.010
Neg logit contributions
Unfortunately-0.009
Meanwhile-0.009
eyed-0.009
 pounding-0.008
Just-0.008
Token!"
Token ID2474
Feature activation-1.42e+00

Pos logit contributions
 happens+0.045
 belongs+0.041
 guys+0.040
 doesn+0.039
 isn+0.039
Neg logit contributions
Unfortunately-0.087
Meanwhile-0.086
eyed-0.085
 pounding-0.083
Just-0.082
Token he
Token ID339
Feature activation-1.55e+00

Pos logit contributions
Unfortunately+0.075
Meanwhile+0.075
Days+0.074
har+0.074
 pounding+0.074
Neg logit contributions
 happens-0.049
 is-0.049
 doesn-0.047
 isn-0.046
 belongs-0.044
Token said
Token ID531
Feature activation-2.60e+00

Pos logit contributions
 sidelines+0.092
Unfortunately+0.089
side+0.088
eyed+0.087
Meanwhile+0.086
Neg logit contributions
 happens-0.049
 is-0.049
 doesn-0.048
 isn-0.046
 means-0.043
Token,
Token ID11
Feature activation-5.05e+00

Pos logit contributions
Meanwhile+0.171
Unfortunately+0.169
 sidelines+0.165
Finally+0.165
Eventually+0.163
Neg logit contributions
 is-0.063
 doesn-0.058
 happens-0.057
 brother-0.055
 isn-0.054
Token between
Token ID1022
Feature activation-8.22e-01

Pos logit contributions
Finally+0.251
Eventually+0.249
Days+0.245
Unfortunately+0.244
Years+0.240
Neg logit contributions
 I-0.167
 is-0.162
,-0.158
 doesn-0.156
?"-0.155
Token so
Token ID523
Feature activation-1.20e+00

Pos logit contributions
Unfortunately+0.042
Meanwhile+0.041
eyed+0.041
Just+0.040
har+0.039
Neg logit contributions
 is-0.031
 happens-0.031
 guys-0.031
 isn-0.029
 doesn-0.029
Tokenbs
Token ID1443
Feature activation-1.40e+00

Pos logit contributions
Unfortunately+0.066
Meanwhile+0.064
eyed+0.064
 widening+0.062
rolling+0.062
Neg logit contributions
 happens-0.041
 is-0.039
 doesn-0.036
 needs-0.036
 guys-0.036
Token.
Token ID13
Feature activation-1.55e+00

Pos logit contributions
Unfortunately+0.081
Meanwhile+0.077
Finally+0.076
eyed+0.076
Just+0.075
Neg logit contributions
 happens-0.046
 is-0.046
 doesn-0.045
 guys-0.044
 isn-0.043
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
eyed+0.074
 pounding+0.074
Meanwhile+0.072
 widening+0.071
har+0.071
Neg logit contributions
 is-0.061
 isn-0.061
 happens-0.060
 doesn-0.059
 belongs-0.055
Token L
Token ID406
Feature activation+1.56e+00

Pos logit contributions
 happens+0.019
 belongs+0.018
 guys+0.017
 doesn+0.017
 is+0.017
Neg logit contributions
Unfortunately-0.027
Meanwhile-0.026
eyed-0.025
Just-0.025
 pounding-0.025
Tokenila
Token ID10102
Feature activation+1.01e+00

Pos logit contributions
 guys+0.067
 needs+0.065
 happens+0.065
 belongs+0.063
 lives+0.063
Neg logit contributions
Just-0.072
Meanwhile-0.071
Unfortunately-0.070
eyed-0.067
Her-0.064
Token?"
Token ID1701
Feature activation-7.43e-01

Pos logit contributions
 happens+0.014
 guys+0.013
 isn+0.012
 belongs+0.011
 doesn+0.010
Neg logit contributions
Unfortunately-0.074
Meanwhile-0.074
eyed-0.074
Just-0.072
 pounding-0.072
Token she
Token ID673
Feature activation-1.21e+00

Pos logit contributions
Unfortunately+0.042
Meanwhile+0.040
har+0.040
eyed+0.040
 widening+0.040
Neg logit contributions
 is-0.026
 happens-0.026
 doesn-0.024
 belongs-0.024
 needs-0.023
Token asked
Token ID1965
Feature activation-2.18e-01

Pos logit contributions
Unfortunately+0.060
eyed+0.059
 sidelines+0.057
har+0.057
Finally+0.056
Neg logit contributions
 happens-0.052
 is-0.050
 doesn-0.049
 isn-0.047
 guys-0.046
Token,
Token ID11
Feature activation-5.04e+00

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.013
eyed+0.013
Just+0.013
 widening+0.013
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token smiling
Token ID16755
Feature activation-1.27e-01

Pos logit contributions
Unfortunately+0.272
Finally+0.267
Eventually+0.264
Days+0.264
Years+0.256
Neg logit contributions
 brother-0.167
?"-0.158
,-0.151
 sister-0.149
 is-0.142
Token.
Token ID13
Feature activation-1.30e+00

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
Just+0.007
 widening+0.007
Neg logit contributions
 happens-0.004
 is-0.004
 doesn-0.004
 belongs-0.004
 guys-0.004
Token
Token ID198
Feature activation-7.81e-01

Pos logit contributions
 sidelines+0.066
eyed+0.065
Unfortunately+0.065
har+0.064
Meanwhile+0.064
Neg logit contributions
 is-0.053
 happens-0.050
 isn-0.048
 doesn-0.048
 can-0.047
Token
Token ID198
Feature activation-1.42e+00

Pos logit contributions
Unfortunately+0.035
Meanwhile+0.035
 widening+0.034
eyed+0.034
 pounding+0.034
Neg logit contributions
 is-0.035
 happens-0.034
 doesn-0.033
 isn-0.033
 belongs-0.032
TokenL
Token ID43
Feature activation+7.56e-01

Pos logit contributions
 widening+0.074
 sidelines+0.073
eyed+0.071
 pounding+0.071
 victorious+0.070
Neg logit contributions
 is-0.056
 happens-0.049
 belongs-0.048
 doesn-0.048
 isn-0.047
Token something
Token ID1223
Feature activation+7.99e-01

Pos logit contributions
 happens+0.016
 belongs+0.016
 doesn+0.016
 is+0.016
 isn+0.016
Neg logit contributions
Unfortunately-0.018
Meanwhile-0.017
eyed-0.017
Just-0.016
 pounding-0.016
Token together
Token ID1978
Feature activation+1.11e+00

Pos logit contributions
 happens+0.038
 guys+0.037
 doesn+0.037
 belongs+0.036
 is+0.036
Neg logit contributions
Unfortunately-0.033
Meanwhile-0.031
eyed-0.031
 pounding-0.030
Just-0.030
Token!"
Token ID2474
Feature activation-2.82e-01

Pos logit contributions
 happens+0.030
 guys+0.029
 belongs+0.029
 doesn+0.028
 is+0.027
Neg logit contributions
Unfortunately-0.067
Meanwhile-0.066
eyed-0.066
 pounding-0.064
 widening-0.063
Token said
Token ID531
Feature activation+6.52e-01

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.014
eyed+0.014
 pounding+0.013
 widening+0.013
Neg logit contributions
 happens-0.011
 is-0.011
 doesn-0.011
 belongs-0.011
 isn-0.011
Token Emma
Token ID18966
Feature activation-2.49e+00

Pos logit contributions
 happens+0.022
 belongs+0.022
 doesn+0.021
 is+0.021
 isn+0.021
Neg logit contributions
Unfortunately-0.036
Meanwhile-0.036
eyed-0.035
 pounding-0.034
 widening-0.034
Token,
Token ID11
Feature activation-5.03e+00

Pos logit contributions
Unfortunately+0.175
Finally+0.169
 sidelines+0.169
Meanwhile+0.169
Days+0.168
Neg logit contributions
 is-0.051
 doesn-0.046
 isn-0.043
 happens-0.042
 brother-0.040
Token adm
Token ID6178
Feature activation-1.55e+00

Pos logit contributions
Unfortunately+0.244
Days+0.242
Finally+0.234
Years+0.233
Eventually+0.230
Neg logit contributions
,-0.172
 I-0.166
 brother-0.162
?"-0.157
 is-0.147
Tokeniring
Token ID3428
Feature activation-1.24e+00

Pos logit contributions
Unfortunately+0.086
 sidelines+0.080
Meanwhile+0.079
Finally+0.077
shadow+0.077
Neg logit contributions
 happens-0.052
 is-0.052
 belongs-0.049
?"-0.048
 guys-0.047
Token their
Token ID511
Feature activation-1.13e+00

Pos logit contributions
Unfortunately+0.068
Meanwhile+0.068
eyed+0.066
Just+0.065
Finally+0.063
Neg logit contributions
 is-0.045
 happens-0.044
 doesn-0.043
 isn-0.043
 belongs-0.041
Token work
Token ID670
Feature activation-2.85e+00

Pos logit contributions
Unfortunately+0.060
Meanwhile+0.058
eyed+0.055
Just+0.054
However+0.054
Neg logit contributions
 is-0.047
 happens-0.045
 belongs-0.045
 isn-0.045
 lives-0.044
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
Unfortunately+0.179
Meanwhile+0.178
Just+0.169
Finally+0.169
Eventually+0.167
Neg logit contributions
 is-0.089
 happens-0.081
 doesn-0.078
 belongs-0.077
 isn-0.076
Token do
Token ID466
Feature activation+1.87e-02

Pos logit contributions
 happens+0.000
 is+0.000
 doesn+0.000
 belongs+0.000
 isn+0.000
Neg logit contributions
Unfortunately-0.000
Meanwhile-0.000
eyed-0.000
Just-0.000
 widening-0.000
Token it
Token ID340
Feature activation+1.29e+00

Pos logit contributions
 happens+0.001
 is+0.001
 doesn+0.001
 belongs+0.001
 isn+0.001
Neg logit contributions
Unfortunately-0.001
Meanwhile-0.001
eyed-0.001
 widening-0.001
Just-0.001
Token!"
Token ID2474
Feature activation-1.00e+00

Pos logit contributions
 happens+0.041
 belongs+0.038
 guys+0.038
 doesn+0.037
 isn+0.037
Neg logit contributions
Unfortunately-0.072
Meanwhile-0.070
eyed-0.070
Just-0.069
 pounding-0.068
Token Sarah
Token ID10490
Feature activation-1.77e+00

Pos logit contributions
Unfortunately+0.056
Days+0.056
Meanwhile+0.056
eyed+0.055
 widening+0.054
Neg logit contributions
 is-0.034
 happens-0.033
 doesn-0.033
 isn-0.032
 belongs-0.031
Token said
Token ID531
Feature activation-2.71e+00

Pos logit contributions
Unfortunately+0.097
 sidelines+0.095
Days+0.094
Meanwhile+0.094
Finally+0.093
Neg logit contributions
 is-0.062
 doesn-0.061
 isn-0.058
 happens-0.058
 belongs-0.054
Token,
Token ID11
Feature activation-5.03e+00

Pos logit contributions
Meanwhile+0.184
Unfortunately+0.183
Days+0.178
Finally+0.178
 sidelines+0.178
Neg logit contributions
 is-0.058
 doesn-0.053
 happens-0.051
 brother-0.048
,-0.047
Token laughing
Token ID14376
Feature activation-1.37e+00

Pos logit contributions
Days+0.252
Unfortunately+0.242
Finally+0.240
Years+0.238
Hours+0.237
Neg logit contributions
 I-0.178
,-0.168
 is-0.163
?"-0.162
 doesn-0.161
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
Unfortunately+0.078
Meanwhile+0.077
Finally+0.073
eyed+0.072
rolling+0.071
Neg logit contributions
 is-0.047
 doesn-0.046
 isn-0.046
 happens-0.045
 guys-0.045
Token
Token ID220
Feature activation-1.10e+00

Pos logit contributions
Meanwhile+0.043
Unfortunately+0.042
eyed+0.042
 pounding+0.040
 widening+0.040
Neg logit contributions
 is-0.052
 isn-0.052
 doesn-0.051
 happens-0.050
 belongs-0.049
Token
Token ID198
Feature activation-2.15e+00

Pos logit contributions
Unfortunately+0.050
Meanwhile+0.049
 widening+0.048
eyed+0.048
 sidelines+0.047
Neg logit contributions
 is-0.049
 happens-0.048
 doesn-0.047
 isn-0.047
 belongs-0.046
Token
Token ID198
Feature activation-2.56e+00

Pos logit contributions
 widening+0.113
 pounding+0.112
 ledge+0.109
Meanwhile+0.109
inge+0.108
Neg logit contributions
 is-0.077
 isn-0.068
 doesn-0.064
?"-0.064
 happens-0.063
Token you
Token ID345
Feature activation+4.21e-01

Pos logit contributions
 happens+0.079
unn+0.074
 guys+0.073
 belongs+0.072
 needs+0.069
Neg logit contributions
Unfortunately-0.140
Finally-0.134
Meanwhile-0.133
Just-0.132
Eventually-0.129
Token go
Token ID467
Feature activation+4.01e-01

Pos logit contributions
 happens+0.018
 doesn+0.017
 belongs+0.017
 is+0.017
 isn+0.017
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.019
eyed-0.019
Just-0.019
 widening-0.018
Token,"
Token ID553
Feature activation-1.04e+00

Pos logit contributions
 happens+0.015
 doesn+0.014
 belongs+0.014
 guys+0.014
 is+0.014
Neg logit contributions
Unfortunately-0.021
Meanwhile-0.021
eyed-0.020
Just-0.020
 pounding-0.020
Token she
Token ID673
Feature activation-1.48e+00

Pos logit contributions
Unfortunately+0.058
eyed+0.058
Meanwhile+0.057
rolling+0.055
 widening+0.055
Neg logit contributions
 is-0.035
 happens-0.035
 doesn-0.034
 isn-0.033
 belongs-0.032
Token said
Token ID531
Feature activation-2.60e+00

Pos logit contributions
 sidelines+0.088
Unfortunately+0.087
eyed+0.085
Meanwhile+0.085
 crashing+0.085
Neg logit contributions
 happens-0.047
 is-0.045
 doesn-0.044
 isn-0.042
 belongs-0.042
Token,
Token ID11
Feature activation-5.02e+00

Pos logit contributions
Meanwhile+0.178
Unfortunately+0.176
 sidelines+0.172
Finally+0.170
Eventually+0.168
Neg logit contributions
 is-0.054
 brother-0.049
 doesn-0.049
 happens-0.046
 sister-0.046
Token pat
Token ID1458
Feature activation-1.88e+00

Pos logit contributions
Days+0.255
Unfortunately+0.246
Finally+0.240
Years+0.240
Eventually+0.237
Neg logit contributions
 I-0.157
,-0.155
 is-0.155
 doesn-0.151
?"-0.145
Tokenting
Token ID889
Feature activation-2.67e+00

Pos logit contributions
Unfortunately+0.097
Meanwhile+0.093
Days+0.088
eyed+0.088
Just+0.086
Neg logit contributions
 is-0.073
 guys-0.072
 doesn-0.071
 happens-0.069
 isn-0.069
Token the
Token ID262
Feature activation-6.85e-01

Pos logit contributions
Meanwhile+0.159
Unfortunately+0.159
Just+0.153
Finally+0.153
Eventually+0.149
Neg logit contributions
 is-0.087
 doesn-0.080
 guys-0.078
 isn-0.076
 happens-0.076
Token little
Token ID1310
Feature activation+4.02e-01

Pos logit contributions
Unfortunately+0.035
eyed+0.035
Meanwhile+0.034
His+0.032
 pounding+0.032
Neg logit contributions
 is-0.027
 happens-0.026
 doesn-0.026
 isn-0.026
 needs-0.026
Token girl
Token ID2576
Feature activation-2.98e+00

Pos logit contributions
 happens+0.013
 belongs+0.012
 doesn+0.012
 is+0.012
 guys+0.012
Neg logit contributions
Unfortunately-0.023
Meanwhile-0.023
eyed-0.022
 widening-0.022
 pounding-0.022
Token the
Token ID262
Feature activation-4.90e-01

Pos logit contributions
 happens+0.011
 belongs+0.011
 doesn+0.010
 is+0.010
 guys+0.010
Neg logit contributions
Unfortunately-0.015
Meanwhile-0.015
eyed-0.014
Just-0.014
 widening-0.014
Token crane
Token ID41175
Feature activation-1.91e+00

Pos logit contributions
Unfortunately+0.025
Meanwhile+0.025
eyed+0.024
 pounding+0.024
Just+0.023
Neg logit contributions
 is-0.020
 happens-0.019
 belongs-0.019
 guys-0.019
 needs-0.018
Token fl
Token ID781
Feature activation-1.79e+00

Pos logit contributions
Unfortunately+0.100
 sidelines+0.099
Meanwhile+0.094
 widening+0.093
rolling+0.091
Neg logit contributions
 is-0.077
 happens-0.074
 doesn-0.072
 belongs-0.071
 needs-0.070
Tokenapped
Token ID6320
Feature activation-2.32e+00

Pos logit contributions
Unfortunately+0.101
 widening+0.098
 sidelines+0.098
Meanwhile+0.097
 winding+0.096
Neg logit contributions
 is-0.056
 belongs-0.055
 happens-0.054
 needs-0.051
 isn-0.050
Token his
Token ID465
Feature activation-7.25e-01

Pos logit contributions
Unfortunately+0.133
Meanwhile+0.130
rolling+0.130
Finally+0.128
 sidelines+0.127
Neg logit contributions
 is-0.087
 doesn-0.076
 happens-0.076
 isn-0.075
 guys-0.072
Token wings
Token ID12098
Feature activation-5.01e+00

Pos logit contributions
Unfortunately+0.040
Meanwhile+0.039
 widening+0.037
eyed+0.037
 sidelines+0.037
Neg logit contributions
 is-0.027
 happens-0.027
 doesn-0.026
 belongs-0.026
 needs-0.026
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
Unfortunately+0.350
 sidelines+0.344
Finally+0.341
har+0.336
Meanwhile+0.332
Neg logit contributions
,-0.102
 is-0.093
 can-0.075
 happens-0.065
 doesn-0.059
Token flew
Token ID13112
Feature activation-2.54e+00

Pos logit contributions
Unfortunately+0.065
eyed+0.063
Meanwhile+0.062
Finally+0.061
Days+0.061
Neg logit contributions
 happens-0.055
 is-0.053
 doesn-0.051
 isn-0.050
 belongs-0.049
Token from
Token ID422
Feature activation-1.06e+00

Pos logit contributions
Meanwhile+0.134
Unfortunately+0.134
 sidelines+0.130
inge+0.129
Days+0.127
Neg logit contributions
 is-0.096
 can-0.089
 isn-0.083
 guys-0.082
 happens-0.082
Token tree
Token ID5509
Feature activation-4.04e+00

Pos logit contributions
Unfortunately+0.056
Meanwhile+0.054
Just+0.052
rolling+0.052
eyed+0.052
Neg logit contributions
 is-0.042
 happens-0.042
 needs-0.039
 belongs-0.039
 lives-0.039
Token to
Token ID284
Feature activation-2.24e+00

Pos logit contributions
Unfortunately+0.284
Finally+0.271
Years+0.263
Meanwhile+0.262
Days+0.261
Neg logit contributions
,-0.083
 is-0.076
 lives-0.058
 brother-0.055
 things-0.055
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
 belongs+0.073
 doesn+0.073
 needs+0.071
 isn+0.070
 guys+0.069
Neg logit contributions
Her-0.090
His-0.088
eyed-0.087
Unfortunately-0.087
 widening-0.087
Token "
Token ID366
Feature activation-3.99e-01

Pos logit contributions
Unfortunately+0.078
eyed+0.077
Meanwhile+0.077
har+0.074
Days+0.071
Neg logit contributions
 is-0.053
 happens-0.051
 doesn-0.049
 isn-0.049
 can-0.048
TokenHello
Token ID15496
Feature activation+4.59e+00

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.014
eyed+0.013
 pounding+0.013
 widening+0.013
Neg logit contributions
 happens-0.022
 is-0.022
 doesn-0.021
 isn-0.021
 belongs-0.021
Token,
Token ID11
Feature activation+1.81e+00

Pos logit contributions
 belongs+0.222
 guys+0.218
ishes+0.214
eer+0.213
 happens+0.211
Neg logit contributions
Her-0.140
On-0.132
 louder-0.130
 gently-0.128
 faster-0.124
Token Elsa
Token ID19226
Feature activation+3.72e+00

Pos logit contributions
 happens+0.066
 belongs+0.065
 guys+0.063
ishes+0.061
 doesn+0.059
Neg logit contributions
Unfortunately-0.090
Meanwhile-0.089
However-0.085
Her-0.084
On-0.084
Token.
Token ID13
Feature activation+3.84e+00

Pos logit contributions
 guys+0.222
 happens+0.220
 belongs+0.214
mm+0.211
unn+0.208
Neg logit contributions
eyed-0.089
But-0.084
Just-0.074
On-0.069
 pounding-0.069
Token I
Token ID314
Feature activation+1.30e+00

Pos logit contributions
ishes+0.144
 happens+0.144
 guys+0.144
iles+0.135
 happened+0.131
Neg logit contributions
Her-0.173
eyed-0.170
Unfortunately-0.168
Just-0.165
His-0.161
Token am
Token ID716
Feature activation+1.29e+00

Pos logit contributions
 happens+0.049
 guys+0.046
 doesn+0.045
 belongs+0.045
 isn+0.044
Neg logit contributions
eyed-0.065
Unfortunately-0.063
On-0.061
Meanwhile-0.061
Just-0.061
Token happy
Token ID3772
Feature activation+2.07e+00

Pos logit contributions
 happens+0.048
 belongs+0.045
 doesn+0.045
 guys+0.044
 isn+0.043
Neg logit contributions
Unfortunately-0.066
Meanwhile-0.065
eyed-0.065
 victorious-0.063
 widening-0.063
Token to
Token ID284
Feature activation+3.61e-01

Pos logit contributions
 belongs+0.116
 happens+0.114
 guys+0.114
 isn+0.110
 doesn+0.109
Neg logit contributions
Just-0.066
But-0.062
Meanwhile-0.061
Unfortunately-0.061
Her-0.059
Token meet
Token ID1826
Feature activation+2.86e+00

Pos logit contributions
 happens+0.018
 doesn+0.018
 belongs+0.017
 isn+0.017
 is+0.017
Neg logit contributions
Unfortunately-0.014
Meanwhile-0.014
eyed-0.014
Just-0.013
 widening-0.013
Token can
Token ID460
Feature activation-1.46e+00

Pos logit contributions
 happens+0.040
 isn+0.036
 belongs+0.036
mm+0.034
 doesn+0.034
Neg logit contributions
eyed-0.108
Unfortunately-0.105
On-0.101
Meanwhile-0.100
Finally-0.100
Token give
Token ID1577
Feature activation+1.96e+00

Pos logit contributions
Unfortunately+0.072
Meanwhile+0.072
 pounding+0.067
 widening+0.066
Just+0.065
Neg logit contributions
 is-0.065
 guys-0.059
?"-0.059
 can-0.058
 doesn-0.058
Token him
Token ID683
Feature activation+2.28e+00

Pos logit contributions
 happens+0.087
 belongs+0.082
 isn+0.079
 doesn+0.079
 needs+0.078
Neg logit contributions
eyed-0.084
Unfortunately-0.082
His-0.080
Meanwhile-0.079
Just-0.078
Token to
Token ID284
Feature activation+6.31e-01

Pos logit contributions
 happens+0.123
 belongs+0.115
 isn+0.115
 doesn+0.115
 needs+0.112
Neg logit contributions
His-0.074
eyed-0.073
Unfortunately-0.071
Meanwhile-0.070
 victorious-0.068
Token someone
Token ID2130
Feature activation+3.03e+00

Pos logit contributions
 happens+0.024
 belongs+0.023
 doesn+0.023
 is+0.023
 isn+0.022
Neg logit contributions
Unfortunately-0.032
Meanwhile-0.032
eyed-0.031
Just-0.030
 pounding-0.030
Token who
Token ID508
Feature activation+3.29e+00

Pos logit contributions
 happens+0.144
 guys+0.135
 isn+0.132
mm+0.127
 belongs+0.127
Neg logit contributions
eyed-0.110
His-0.103
Just-0.101
On-0.099
But-0.098
Token's
Token ID338
Feature activation+1.20e+00

Pos logit contributions
 happens+0.076
 guys+0.075
mm+0.069
 isn+0.065
unn+0.061
Neg logit contributions
eyed-0.197
Meanwhile-0.178
 lower-0.176
 victorious-0.176
His-0.175
Token lonely
Token ID21757
Feature activation+3.16e+00

Pos logit contributions
 happens+0.050
 guys+0.045
 belongs+0.045
 doesn+0.045
 isn+0.045
Neg logit contributions
eyed-0.056
Unfortunately-0.055
Meanwhile-0.054
 pounding-0.053
Just-0.051
Token,
Token ID11
Feature activation+5.95e-01

Pos logit contributions
 happens+0.117
mm+0.112
 belongs+0.110
 isn+0.108
unn+0.108
Neg logit contributions
eyed-0.137
His-0.128
 pounding-0.126
Meanwhile-0.123
Just-0.122
Token like
Token ID588
Feature activation+1.61e+00

Pos logit contributions
 happens+0.025
 belongs+0.024
 is+0.023
 doesn+0.023
 guys+0.023
Neg logit contributions
Unfortunately-0.029
Meanwhile-0.028
eyed-0.027
Just-0.026
 pounding-0.026
Token me
Token ID502
Feature activation+6.48e-01

Pos logit contributions
 happens+0.056
 belongs+0.053
 doesn+0.051
 isn+0.050
 needs+0.049
Neg logit contributions
Unfortunately-0.085
Meanwhile-0.084
eyed-0.081
Just-0.080
His-0.080
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
 doesn+0.121
 belongs+0.116
 isn+0.116
ishes+0.114
 cares+0.114
Neg logit contributions
Just-0.110
Meanwhile-0.109
His-0.109
Their-0.107
On-0.107
Token a
Token ID257
Feature activation+1.31e+00

Pos logit contributions
 happens+0.080
 guys+0.078
 doesn+0.078
 isn+0.076
 belongs+0.075
Neg logit contributions
On-0.047
Meanwhile-0.047
Unfortunately-0.046
eyed-0.046
Just-0.045
Token little
Token ID1310
Feature activation+2.04e+00

Pos logit contributions
 happens+0.061
 belongs+0.060
 doesn+0.059
 isn+0.058
 is+0.056
Neg logit contributions
Unfortunately-0.054
Meanwhile-0.054
Just-0.053
eyed-0.052
His-0.052
Token girl
Token ID2576
Feature activation+3.43e+00

Pos logit contributions
 happens+0.080
 doesn+0.079
 belongs+0.078
 isn+0.077
 tastes+0.068
Neg logit contributions
Meanwhile-0.098
eyed-0.098
 crashing-0.096
 sidelines-0.095
Unfortunately-0.095
Token named
Token ID3706
Feature activation+2.06e+00

Pos logit contributions
 doesn+0.213
 guys+0.213
 isn+0.206
mm+0.204
 happens+0.204
Neg logit contributions
eyed-0.087
Her-0.071
 pat-0.065
Just-0.064
But-0.064
Token Lucy
Token ID22162
Feature activation+3.41e+00

Pos logit contributions
 doesn+0.081
 happens+0.080
 isn+0.075
 belongs+0.075
 guys+0.075
Neg logit contributions
Her-0.100
Unfortunately-0.099
eyed-0.095
Meanwhile-0.093
Finally-0.091
Token wanted
Token ID2227
Feature activation+4.63e-01

Pos logit contributions
mm+0.192
 guys+0.189
unn+0.186
 isn+0.184
 doesn+0.183
Neg logit contributions
eyed-0.112
On-0.086
Just-0.082
 swept-0.082
 pounding-0.079
Token to
Token ID284
Feature activation+2.72e-02

Pos logit contributions
 happens+0.023
 doesn+0.023
 belongs+0.023
 isn+0.023
 is+0.023
Neg logit contributions
Unfortunately-0.018
Meanwhile-0.018
eyed-0.017
Just-0.017
 pounding-0.017
Token play
Token ID711
Feature activation-2.48e-01

Pos logit contributions
 happens+0.001
 is+0.001
 doesn+0.001
 belongs+0.001
 isn+0.001
Neg logit contributions
Unfortunately-0.001
Meanwhile-0.001
eyed-0.001
Just-0.001
 widening-0.001
Token.
Token ID13
Feature activation+1.65e+00

Pos logit contributions
Unfortunately+0.011
Meanwhile+0.011
eyed+0.010
 pounding+0.010
 widening+0.010
Neg logit contributions
 happens-0.012
 is-0.011
 guys-0.011
 doesn-0.011
 belongs-0.011
Token She
Token ID1375
Feature activation+1.21e+00

Pos logit contributions
 happens+0.096
 guys+0.091
 doesn+0.091
 belongs+0.090
 needs+0.087
Neg logit contributions
Unfortunately-0.053
eyed-0.050
Her-0.049
 widening-0.049
Meanwhile-0.049
Token was
Token ID373
Feature activation-2.82e+00

Pos logit contributions
Unfortunately+0.022
Meanwhile+0.022
eyed+0.021
Just+0.021
 widening+0.021
Neg logit contributions
 happens-0.014
 is-0.014
 belongs-0.013
 doesn-0.013
 isn-0.013
Token so
Token ID523
Feature activation-1.55e+00

Pos logit contributions
 sidelines+0.129
Unfortunately+0.127
Meanwhile+0.126
Years+0.126
Finally+0.125
Neg logit contributions
 is-0.121
?"-0.112
 isn-0.107
 happened-0.105
 happens-0.104
Token impressed
Token ID12617
Feature activation+1.37e+00

Pos logit contributions
Unfortunately+0.061
Meanwhile+0.061
 sidelines+0.059
Just+0.057
side+0.056
Neg logit contributions
 is-0.080
 happens-0.078
 isn-0.074
 belongs-0.073
 wants-0.073
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
 guys+0.066
 happens+0.066
 needs+0.064
 belongs+0.062
 doesn+0.061
Neg logit contributions
eyed-0.055
Unfortunately-0.054
Just-0.053
Meanwhile-0.053
On-0.050
Token "
Token ID366
Feature activation-1.75e+00

Pos logit contributions
 happens+0.005
 is+0.005
 doesn+0.005
 belongs+0.005
 isn+0.005
Neg logit contributions
Unfortunately-0.005
Meanwhile-0.005
eyed-0.005
Just-0.005
 widening-0.005
TokenWow
Token ID22017
Feature activation+3.45e+00

Pos logit contributions
 pounding+0.081
rolling+0.078
 widening+0.077
Meanwhile+0.076
 sidelines+0.075
Neg logit contributions
 isn-0.070
 is-0.070
 happens-0.070
 doesn-0.067
 guys-0.066
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
 belongs+0.137
 needs+0.136
 happens+0.132
 doesn+0.128
 guy+0.125
Neg logit contributions
Unfortunately-0.137
Suddenly-0.136
 free-0.134
Just-0.134
 pounding-0.134
Token that
Token ID326
Feature activation+1.36e+00

Pos logit contributions
 happens+0.047
 belongs+0.045
 doesn+0.044
 needs+0.043
 guys+0.042
Neg logit contributions
Unfortunately-0.051
Meanwhile-0.049
eyed-0.048
 pounding-0.046
However-0.046
Token's
Token ID338
Feature activation+9.72e-01

Pos logit contributions
 happens+0.042
 guys+0.041
unn+0.039
 belongs+0.038
 needs+0.037
Neg logit contributions
Unfortunately-0.074
 pounding-0.073
Meanwhile-0.073
Just-0.069
eyed-0.069
Token perfect
Token ID2818
Feature activation+9.08e-01

Pos logit contributions
 happens+0.052
 guys+0.049
 belongs+0.048
unn+0.048
 needs+0.048
Neg logit contributions
Unfortunately-0.036
Meanwhile-0.033
 pounding-0.032
eyed-0.031
On-0.031
Token!"
Token ID2474
Feature activation-8.13e-01

Pos logit contributions
 happens+0.030
 doesn+0.028
 belongs+0.028
 guys+0.027
 needs+0.026
Neg logit contributions
Unfortunately-0.050
Meanwhile-0.049
eyed-0.049
 pounding-0.049
 widening-0.047
Token on
Token ID319
Feature activation+4.84e-01

Pos logit contributions
 happens+0.005
 doesn+0.005
 is+0.005
 belongs+0.005
 isn+0.005
Neg logit contributions
Unfortunately-0.005
Meanwhile-0.005
eyed-0.005
Just-0.005
 widening-0.005
Token the
Token ID262
Feature activation+2.32e-01

Pos logit contributions
 happens+0.021
 belongs+0.020
 doesn+0.020
 isn+0.020
 needs+0.020
Neg logit contributions
Unfortunately-0.022
Meanwhile-0.022
eyed-0.021
 pounding-0.021
 widening-0.021
Token mattress
Token ID33388
Feature activation-5.79e-01

Pos logit contributions
 happens+0.010
 doesn+0.009
 belongs+0.009
 is+0.009
 isn+0.009
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.011
 widening-0.011
Just-0.011
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
Unfortunately+0.034
Meanwhile+0.033
eyed+0.032
Just+0.031
 pounding+0.031
Neg logit contributions
 is-0.019
 happens-0.019
 belongs-0.019
 doesn-0.018
 guys-0.018
Token But
Token ID887
Feature activation+1.27e+00

Pos logit contributions
 happens+0.017
 guys+0.016
 belongs+0.016
 doesn+0.016
 is+0.016
Neg logit contributions
Unfortunately-0.018
Meanwhile-0.018
eyed-0.017
Just-0.017
 widening-0.016
Token sometimes
Token ID3360
Feature activation+3.34e+00

Pos logit contributions
 happens+0.061
 guys+0.059
 belongs+0.059
 doesn+0.058
 isn+0.058
Neg logit contributions
Meanwhile-0.052
Unfortunately-0.050
However-0.047
Just-0.046
His-0.046
Token they
Token ID484
Feature activation+2.91e-01

Pos logit contributions
unn+0.178
 belongs+0.160
elling+0.159
mm+0.157
ishes+0.155
Neg logit contributions
 pounding-0.098
Meanwhile-0.089
On-0.088
 determined-0.087
 beating-0.086
Token make
Token ID787
Feature activation+5.63e-01

Pos logit contributions
 happens+0.014
 belongs+0.013
 doesn+0.013
 is+0.013
 isn+0.013
Neg logit contributions
Unfortunately-0.012
Meanwhile-0.012
eyed-0.012
 pounding-0.012
 widening-0.011
Token too
Token ID1165
Feature activation+9.38e-01

Pos logit contributions
 happens+0.025
 belongs+0.025
 doesn+0.024
 isn+0.024
 needs+0.024
Neg logit contributions
Unfortunately-0.025
Meanwhile-0.024
 pounding-0.023
eyed-0.023
Just-0.023
Token much
Token ID881
Feature activation+6.71e-01

Pos logit contributions
 isn+0.054
 belongs+0.054
 doesn+0.054
 happens+0.054
 guys+0.053
Neg logit contributions
Unfortunately-0.028
Meanwhile-0.028
eyed-0.027
 pounding-0.026
On-0.026
Token noise
Token ID7838
Feature activation+1.65e+00

Pos logit contributions
 belongs+0.034
 happens+0.033
 doesn+0.033
 isn+0.033
 guys+0.032
Neg logit contributions
Unfortunately-0.025
Meanwhile-0.025
 widening-0.024
 pounding-0.024
eyed-0.024
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
 happens+0.009
 belongs+0.009
 doesn+0.009
 is+0.009
 guys+0.009
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.011
Just-0.011
 widening-0.011
Token
Token ID198
Feature activation-1.88e+00

Pos logit contributions
 widening+0.057
Unfortunately+0.057
Meanwhile+0.057
har+0.057
 pounding+0.056
Neg logit contributions
 is-0.054
 happens-0.051
 doesn-0.048
 belongs-0.047
 isn-0.047
TokenWhen
Token ID2215
Feature activation+6.72e-01

Pos logit contributions
rolling+0.108
 widening+0.106
har+0.105
 pounding+0.104
 ledge+0.103
Neg logit contributions
 is-0.063
 happens-0.052
?"-0.050
 belongs-0.050
 doesn-0.049
Token they
Token ID484
Feature activation-2.83e-01

Pos logit contributions
 belongs+0.026
 happens+0.026
 doesn+0.025
 isn+0.025
 is+0.025
Neg logit contributions
Unfortunately-0.034
Meanwhile-0.033
 pounding-0.031
His-0.031
On-0.031
Token get
Token ID651
Feature activation+6.87e-01

Pos logit contributions
Unfortunately+0.013
Meanwhile+0.013
eyed+0.012
Just+0.012
 pounding+0.012
Neg logit contributions
 happens-0.013
 is-0.013
 doesn-0.012
 belongs-0.012
 guys-0.012
Token home
Token ID1363
Feature activation+7.72e-01

Pos logit contributions
 happens+0.039
 belongs+0.038
 doesn+0.038
 isn+0.038
 is+0.037
Neg logit contributions
Unfortunately-0.022
eyed-0.022
Meanwhile-0.022
 pounding-0.020
rolling-0.020
Token,
Token ID11
Feature activation+6.15e-01

Pos logit contributions
 happens+0.024
 doesn+0.022
 belongs+0.022
 guys+0.022
 isn+0.022
Neg logit contributions
Meanwhile-0.045
Unfortunately-0.045
eyed-0.044
 pounding-0.043
 widening-0.043
Token Tom
Token ID4186
Feature activation+2.27e+00

Pos logit contributions
 happens+0.020
 belongs+0.019
 doesn+0.019
 is+0.018
 isn+0.018
Neg logit contributions
Unfortunately-0.035
Meanwhile-0.035
eyed-0.033
 pounding-0.033
His-0.033
Token goes
Token ID2925
Feature activation-1.48e+00

Pos logit contributions
 guys+0.084
 happens+0.076
mm+0.074
 isn+0.074
 belongs+0.071
Neg logit contributions
Meanwhile-0.110
eyed-0.109
Unfortunately-0.106
Just-0.104
On-0.103
Token to
Token ID284
Feature activation-9.55e-01

Pos logit contributions
Unfortunately+0.085
 widening+0.082
Meanwhile+0.082
Days+0.081
Finally+0.080
Neg logit contributions
 is-0.052
?"-0.047
 needs-0.044
 belongs-0.044
 happens-0.043
Token his
Token ID465
Feature activation+5.33e-01

Pos logit contributions
Unfortunately+0.052
Meanwhile+0.051
Just+0.050
eyed+0.049
Days+0.048
Neg logit contributions
 is-0.037
 guys-0.035
 happens-0.034
 doesn-0.034
 needs-0.033
Token felt
Token ID2936
Feature activation-7.75e-01

Pos logit contributions
Unfortunately+0.054
Meanwhile+0.053
eyed+0.052
 sidelines+0.052
 widening+0.051
Neg logit contributions
 is-0.037
 doesn-0.037
 happens-0.037
 isn-0.036
 belongs-0.035
Token relieved
Token ID22598
Feature activation-1.04e+00

Pos logit contributions
Meanwhile+0.035
Unfortunately+0.034
rolling+0.033
eyed+0.033
har+0.033
Neg logit contributions
 happens-0.036
 is-0.036
 doesn-0.034
 isn-0.034
 belongs-0.033
Token.
Token ID13
Feature activation-8.43e-02

Pos logit contributions
Unfortunately+0.062
Meanwhile+0.061
rolling+0.060
eyed+0.060
Finally+0.059
Neg logit contributions
 is-0.034
 doesn-0.033
 isn-0.032
 happens-0.032
 guys-0.029
Token She
Token ID1375
Feature activation-1.15e+00

Pos logit contributions
Unfortunately+0.004
Meanwhile+0.004
eyed+0.004
 pounding+0.003
 widening+0.003
Neg logit contributions
 happens-0.004
 is-0.004
 doesn-0.004
 isn-0.004
 belongs-0.004
Token realised
Token ID19169
Feature activation-1.57e-01

Pos logit contributions
Unfortunately+0.059
Meanwhile+0.059
 sidelines+0.058
eyed+0.058
side+0.057
Neg logit contributions
 is-0.045
 doesn-0.044
 happens-0.043
 isn-0.043
 belongs-0.041
Token the
Token ID262
Feature activation+3.27e-01

Pos logit contributions
Unfortunately+0.008
Meanwhile+0.008
eyed+0.008
 widening+0.008
Just+0.008
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 isn-0.006
 belongs-0.006
Token monster
Token ID9234
Feature activation+1.62e+00

Pos logit contributions
 happens+0.011
 belongs+0.011
 doesn+0.011
 is+0.011
 isn+0.011
Neg logit contributions
Unfortunately-0.018
Meanwhile-0.018
eyed-0.017
 widening-0.017
 pounding-0.017
Token was
Token ID373
Feature activation-1.34e+00

Pos logit contributions
 guys+0.058
 happens+0.058
 belongs+0.052
mm+0.052
 doesn+0.051
Neg logit contributions
eyed-0.081
 pounding-0.081
Meanwhile-0.080
Unfortunately-0.080
Just-0.078
Token not
Token ID407
Feature activation-2.35e-01

Pos logit contributions
Unfortunately+0.065
Meanwhile+0.063
rolling+0.063
Finally+0.063
 sidelines+0.061
Neg logit contributions
 is-0.058
 happens-0.057
 doesn-0.055
 belongs-0.055
 isn-0.054
Token real
Token ID1103
Feature activation+1.84e+00

Pos logit contributions
Unfortunately+0.010
Meanwhile+0.010
eyed+0.010
Just+0.010
 widening+0.009
Neg logit contributions
 happens-0.011
 is-0.011
 doesn-0.011
 belongs-0.011
 guys-0.011
Token and
Token ID290
Feature activation+1.12e+00

Pos logit contributions
mm+0.079
 belongs+0.079
 happens+0.076
 doesn+0.076
unn+0.074
Neg logit contributions
 pounding-0.074
eyed-0.073
 realizing-0.072
 crashing-0.072
Unfortunately-0.070
Token upon
Token ID2402
Feature activation+1.63e-01

Pos logit contributions
 guys+0.109
 happens+0.109
 doesn+0.104
 belongs+0.103
 isn+0.103
Neg logit contributions
Meanwhile-0.067
Unfortunately-0.064
eyed-0.063
His-0.061
On-0.061
Token a
Token ID257
Feature activation+8.50e-01

Pos logit contributions
 happens+0.007
 doesn+0.007
 belongs+0.007
 is+0.007
 isn+0.007
Neg logit contributions
Unfortunately-0.007
Meanwhile-0.007
eyed-0.007
Just-0.007
 widening-0.007
Token time
Token ID640
Feature activation+2.73e+00

Pos logit contributions
 happens+0.031
 belongs+0.030
 guys+0.029
 doesn+0.029
 isn+0.029
Neg logit contributions
Unfortunately-0.046
Meanwhile-0.045
Just-0.044
eyed-0.043
Finally-0.043
Token,
Token ID11
Feature activation+1.37e+00

Pos logit contributions
 happens+0.128
 guys+0.123
ishes+0.122
 needs+0.121
 doesn+0.120
Neg logit contributions
His-0.108
On-0.107
Unfortunately-0.106
rolling-0.105
Meanwhile-0.104
Token there
Token ID612
Feature activation+2.49e+00

Pos logit contributions
 happens+0.065
 guys+0.064
 doesn+0.062
 isn+0.060
 belongs+0.060
Neg logit contributions
Meanwhile-0.058
Unfortunately-0.057
On-0.057
His-0.056
eyed-0.055
Token was
Token ID373
Feature activation+8.68e-01

Pos logit contributions
 guys+0.125
unn+0.121
 happens+0.120
ishes+0.119
 cares+0.114
Neg logit contributions
His-0.094
Meanwhile-0.090
Unfortunately-0.090
On-0.089
 pounding-0.088
Token a
Token ID257
Feature activation+5.22e-01

Pos logit contributions
 happens+0.046
 doesn+0.045
 belongs+0.045
 isn+0.044
 needs+0.043
Neg logit contributions
Unfortunately-0.034
Meanwhile-0.033
Just-0.031
eyed-0.031
 widening-0.030
Token little
Token ID1310
Feature activation+2.30e+00

Pos logit contributions
 happens+0.023
 belongs+0.022
 doesn+0.022
 isn+0.021
 is+0.021
Neg logit contributions
Unfortunately-0.024
Meanwhile-0.024
eyed-0.023
Just-0.023
 widening-0.023
Token girl
Token ID2576
Feature activation+9.09e-01

Pos logit contributions
 happens+0.100
 belongs+0.096
 doesn+0.096
 isn+0.094
 is+0.084
Neg logit contributions
Meanwhile-0.098
 crashing-0.098
 sidelines-0.098
 lower-0.097
 winding-0.097
Token named
Token ID3706
Feature activation+1.18e+00

Pos logit contributions
 happens+0.047
 guys+0.044
 doesn+0.044
 isn+0.044
 belongs+0.044
Neg logit contributions
eyed-0.037
Meanwhile-0.035
Unfortunately-0.035
Just-0.034
 pounding-0.033
Token Lily
Token ID20037
Feature activation+6.85e-01

Pos logit contributions
 happens+0.044
 doesn+0.042
 guys+0.040
 belongs+0.040
 isn+0.040
Neg logit contributions
Unfortunately-0.063
Meanwhile-0.062
Her-0.061
Just-0.060
On-0.059
Token of
Token ID286
Feature activation-1.05e-03

Pos logit contributions
 happens+0.005
 is+0.005
 doesn+0.005
 belongs+0.005
 isn+0.005
Neg logit contributions
Unfortunately-0.006
Meanwhile-0.006
eyed-0.006
Just-0.006
 widening-0.006
Token the
Token ID262
Feature activation+6.70e-01

Pos logit contributions
Unfortunately+0.000
Meanwhile+0.000
eyed+0.000
Just+0.000
 widening+0.000
Neg logit contributions
 happens-0.000
 is-0.000
 doesn-0.000
 belongs-0.000
 isn-0.000
Token ham
Token ID8891
Feature activation+6.18e-01

Pos logit contributions
 happens+0.023
 belongs+0.021
 doesn+0.021
 isn+0.020
 guys+0.020
Neg logit contributions
Unfortunately-0.037
Meanwhile-0.037
eyed-0.036
 widening-0.035
Just-0.035
Token sandwich
Token ID20433
Feature activation-2.26e-01

Pos logit contributions
 happens+0.025
 doesn+0.023
 belongs+0.023
 isn+0.023
 guys+0.023
Neg logit contributions
Unfortunately-0.030
Meanwhile-0.030
eyed-0.030
Just-0.029
 widening-0.029
Token.
Token ID13
Feature activation+2.55e-01

Pos logit contributions
Unfortunately+0.012
Meanwhile+0.012
eyed+0.012
Just+0.011
 pounding+0.011
Neg logit contributions
 happens-0.008
 is-0.008
 doesn-0.008
 belongs-0.008
 isn-0.008
Token She
Token ID1375
Feature activation+1.04e+00

Pos logit contributions
 happens+0.011
 belongs+0.011
 guys+0.011
 doesn+0.011
 is+0.011
Neg logit contributions
Unfortunately-0.012
Meanwhile-0.012
eyed-0.011
Just-0.011
 widening-0.011
Token did
Token ID750
Feature activation-6.21e-01

Pos logit contributions
 guys+0.047
 happens+0.046
 belongs+0.044
 isn+0.044
 doesn+0.044
Neg logit contributions
Unfortunately-0.045
Meanwhile-0.045
eyed-0.043
Just-0.042
 widening-0.042
Token the
Token ID262
Feature activation+3.27e-01

Pos logit contributions
Meanwhile+0.025
Unfortunately+0.024
eyed+0.024
rolling+0.023
 pounding+0.023
Neg logit contributions
 is-0.032
 happens-0.032
 doesn-0.031
 isn-0.031
 belongs-0.031
Token same
Token ID976
Feature activation-1.41e-01

Pos logit contributions
 happens+0.013
 doesn+0.012
 belongs+0.012
 is+0.012
 isn+0.012
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.016
eyed-0.016
Just-0.015
 widening-0.015
Token for
Token ID329
Feature activation-4.39e-01

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
Just+0.007
 widening+0.007
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.005
Token Ben
Token ID3932
Feature activation+6.49e-01

Pos logit contributions
Unfortunately+0.024
eyed+0.024
Meanwhile+0.024
Just+0.023
 widening+0.023
Neg logit contributions
 happens-0.015
 is-0.015
 guys-0.015
 doesn-0.015
 isn-0.014
Token a
Token ID257
Feature activation+6.56e-01

Pos logit contributions
 happens+0.070
 doesn+0.069
 belongs+0.069
 isn+0.068
 needs+0.067
Neg logit contributions
Unfortunately-0.043
Meanwhile-0.042
On-0.040
Just-0.039
His-0.039
Token little
Token ID1310
Feature activation+2.48e+00

Pos logit contributions
 happens+0.030
 belongs+0.029
 doesn+0.029
 isn+0.028
 is+0.028
Neg logit contributions
Unfortunately-0.029
Meanwhile-0.029
eyed-0.028
 widening-0.027
Just-0.027
Token bunny
Token ID44915
Feature activation+5.34e-01

Pos logit contributions
 happens+0.109
 doesn+0.104
 isn+0.104
 belongs+0.103
 is+0.090
Neg logit contributions
 sidelines-0.105
Meanwhile-0.105
 crashing-0.104
 lower-0.103
 low-0.103
Token named
Token ID3706
Feature activation+1.70e+00

Pos logit contributions
 happens+0.025
 doesn+0.023
 isn+0.023
 guys+0.023
 belongs+0.023
Neg logit contributions
Unfortunately-0.024
eyed-0.023
Meanwhile-0.023
Just-0.022
 pounding-0.022
Token Betsy
Token ID45775
Feature activation+6.55e-01

Pos logit contributions
 happens+0.081
 belongs+0.074
 doesn+0.072
 isn+0.071
 cares+0.071
Neg logit contributions
Unfortunately-0.076
Meanwhile-0.073
His-0.073
On-0.072
However-0.071
Token.
Token ID13
Feature activation+9.99e-01

Pos logit contributions
 happens+0.028
 isn+0.026
 doesn+0.026
 guys+0.026
 belongs+0.026
Neg logit contributions
eyed-0.031
Unfortunately-0.030
Meanwhile-0.030
Just-0.029
 pounding-0.029
Token Betsy
Token ID45775
Feature activation+2.38e+00

Pos logit contributions
 happens+0.045
 belongs+0.043
 doesn+0.042
 is+0.041
 isn+0.041
Neg logit contributions
Unfortunately-0.047
Meanwhile-0.045
 widening-0.044
On-0.043
Just-0.043
Token loved
Token ID6151
Feature activation+5.31e-01

Pos logit contributions
 happens+0.113
 guys+0.112
mm+0.100
 isn+0.100
 guy+0.097
Neg logit contributions
eyed-0.100
Just-0.094
Meanwhile-0.091
His-0.091
Unfortunately-0.090
Token to
Token ID284
Feature activation-1.38e-01

Pos logit contributions
 happens+0.026
 belongs+0.026
 doesn+0.026
 isn+0.025
 is+0.025
Neg logit contributions
Unfortunately-0.021
Meanwhile-0.021
eyed-0.020
 pounding-0.020
Just-0.019
Token hop
Token ID1725
Feature activation-2.79e-02

Pos logit contributions
Unfortunately+0.006
Meanwhile+0.006
eyed+0.005
Just+0.005
 widening+0.005
Neg logit contributions
 happens-0.007
 is-0.007
 doesn-0.006
 guys-0.006
 belongs-0.006
Token around
Token ID1088
Feature activation+5.17e-01

Pos logit contributions
Unfortunately+0.001
Meanwhile+0.001
eyed+0.001
 widening+0.001
Just+0.001
Neg logit contributions
 happens-0.001
 is-0.001
 doesn-0.001
 belongs-0.001
 isn-0.001
Token room
Token ID2119
Feature activation-1.91e+00

Pos logit contributions
 happens+0.030
 doesn+0.029
 isn+0.028
 belongs+0.028
 guys+0.028
Neg logit contributions
Unfortunately-0.032
Meanwhile-0.032
eyed-0.030
 pounding-0.030
Just-0.029
Token and
Token ID290
Feature activation-4.96e-01

Pos logit contributions
Unfortunately+0.121
Meanwhile+0.119
 sidelines+0.115
Finally+0.114
rolling+0.114
Neg logit contributions
 is-0.058
 doesn-0.050
 needs-0.047
 happens-0.046
 belongs-0.046
Token played
Token ID2826
Feature activation-1.04e+00

Pos logit contributions
Unfortunately+0.024
Meanwhile+0.023
eyed+0.022
Just+0.022
 widening+0.022
Neg logit contributions
 happens-0.021
 is-0.021
 doesn-0.021
 belongs-0.021
 needs-0.020
Token with
Token ID351
Feature activation+1.45e+00

Pos logit contributions
Meanwhile+0.054
Unfortunately+0.053
eyed+0.051
rolling+0.050
 pounding+0.050
Neg logit contributions
 is-0.043
 happens-0.041
 guys-0.041
 doesn-0.039
 belongs-0.038
Token their
Token ID511
Feature activation+1.38e+00

Pos logit contributions
 belongs+0.080
 happens+0.079
 doesn+0.078
 isn+0.078
 needs+0.076
Neg logit contributions
Their-0.044
Unfortunately-0.043
Meanwhile-0.042
eyed-0.041
 lower-0.041
Token dolls
Token ID36062
Feature activation-9.05e-01

Pos logit contributions
 happens+0.059
 doesn+0.054
 belongs+0.054
 isn+0.054
 guys+0.053
Neg logit contributions
Meanwhile-0.062
Unfortunately-0.062
 pounding-0.060
 sidelines-0.060
 widening-0.059
Token.
Token ID13
Feature activation+4.76e-01

Pos logit contributions
Unfortunately+0.055
Meanwhile+0.055
eyed+0.052
Just+0.051
Finally+0.051
Neg logit contributions
 is-0.028
 happens-0.027
 guys-0.027
 doesn-0.026
 belongs-0.026
Token They
Token ID1119
Feature activation-5.47e-02

Pos logit contributions
 happens+0.020
 belongs+0.020
 guys+0.020
 doesn+0.020
 is+0.019
Neg logit contributions
Unfortunately-0.023
Meanwhile-0.022
eyed-0.021
Just-0.021
 widening-0.021
Token waited
Token ID13488
Feature activation-1.47e+00

Pos logit contributions
Unfortunately+0.003
Meanwhile+0.003
eyed+0.003
Just+0.003
 widening+0.003
Neg logit contributions
 happens-0.002
 is-0.002
 doesn-0.002
 belongs-0.002
 guys-0.002
Token for
Token ID329
Feature activation+3.66e-01

Pos logit contributions
Unfortunately+0.086
Meanwhile+0.085
eyed+0.084
har+0.082
His+0.078
Neg logit contributions
 is-0.049
 happens-0.046
 doesn-0.046
 guys-0.046
 isn-0.044
Token the
Token ID262
Feature activation+3.99e-01

Pos logit contributions
 happens+0.016
 belongs+0.016
 doesn+0.016
 is+0.016
 isn+0.016
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.016
eyed-0.016
 widening-0.015
 pounding-0.015
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
 belongs+0.108
 doesn+0.108
 needs+0.103
 isn+0.098
 tastes+0.097
Neg logit contributions
His-0.102
Their-0.102
Meanwhile-0.100
On-0.097
Unfortunately-0.097
Token they
Token ID484
Feature activation+9.74e-01

Pos logit contributions
 happens+0.048
 belongs+0.047
 doesn+0.046
 needs+0.045
 isn+0.045
Neg logit contributions
Unfortunately-0.048
Meanwhile-0.047
On-0.044
His-0.044
 widening-0.044
Token decided
Token ID3066
Feature activation+1.29e-01

Pos logit contributions
 happens+0.045
 belongs+0.044
 doesn+0.044
 isn+0.044
 needs+0.042
Neg logit contributions
Meanwhile-0.041
Unfortunately-0.040
eyed-0.040
On-0.038
 pounding-0.037
Token to
Token ID284
Feature activation+8.78e-02

Pos logit contributions
 happens+0.006
 is+0.006
 doesn+0.006
 belongs+0.006
 isn+0.006
Neg logit contributions
Unfortunately-0.006
Meanwhile-0.006
eyed-0.005
Just-0.005
 widening-0.005
Token play
Token ID711
Feature activation-4.68e-01

Pos logit contributions
 happens+0.004
 is+0.004
 doesn+0.004
 belongs+0.004
 isn+0.004
Neg logit contributions
Unfortunately-0.004
Meanwhile-0.004
eyed-0.003
Just-0.003
 widening-0.003
Token a
Token ID257
Feature activation-7.90e-01

Pos logit contributions
Unfortunately+0.023
Meanwhile+0.023
eyed+0.022
 widening+0.021
 pounding+0.021
Neg logit contributions
 is-0.020
 happens-0.020
 guys-0.019
 belongs-0.019
 doesn-0.019
Token prank
Token ID33401
Feature activation+1.21e+00

Pos logit contributions
Unfortunately+0.046
Meanwhile+0.046
eyed+0.046
 widening+0.044
Just+0.043
Neg logit contributions
 guys-0.025
 is-0.025
 happens-0.025
 belongs-0.024
 doesn-0.024
Token on
Token ID319
Feature activation+7.76e-01

Pos logit contributions
 happens+0.052
 doesn+0.051
 belongs+0.051
 needs+0.050
 isn+0.050
Neg logit contributions
Unfortunately-0.052
Meanwhile-0.052
eyed-0.051
 pounding-0.050
His-0.049
Token Lily
Token ID20037
Feature activation+1.28e+00

Pos logit contributions
 happens+0.036
 belongs+0.035
 doesn+0.034
 isn+0.034
 needs+0.034
Neg logit contributions
Unfortunately-0.034
Meanwhile-0.033
eyed-0.031
 pounding-0.031
His-0.031
Token's
Token ID338
Feature activation+1.49e-01

Pos logit contributions
 happens+0.049
 isn+0.045
 belongs+0.044
 doesn+0.044
 guys+0.044
Neg logit contributions
eyed-0.063
Meanwhile-0.063
Unfortunately-0.063
 pounding-0.062
 widening-0.061
Token big
Token ID1263
Feature activation+1.55e+00

Pos logit contributions
 happens+0.007
 is+0.007
 doesn+0.007
 belongs+0.007
 isn+0.006
Neg logit contributions
Unfortunately-0.007
Meanwhile-0.007
eyed-0.006
Just-0.006
 widening-0.006
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
Unfortunately+0.027
Meanwhile+0.027
eyed+0.026
 widening+0.026
 pounding+0.026
Neg logit contributions
 is-0.015
 happens-0.015
 doesn-0.015
 isn-0.015
 belongs-0.014
Token They
Token ID1119
Feature activation-6.66e-01

Pos logit contributions
 happens+0.001
 is+0.001
 doesn+0.001
 belongs+0.001
 isn+0.001
Neg logit contributions
Unfortunately-0.001
Meanwhile-0.001
eyed-0.001
 widening-0.001
Just-0.001
Token are
Token ID389
Feature activation-1.05e+00

Pos logit contributions
Unfortunately+0.031
Meanwhile+0.031
Just+0.029
eyed+0.029
 pounding+0.028
Neg logit contributions
 is-0.030
 happens-0.030
 doesn-0.029
 belongs-0.029
 guys-0.028
Token happy
Token ID3772
Feature activation+7.78e-01

Pos logit contributions
Unfortunately+0.044
Meanwhile+0.043
Just+0.041
 widening+0.040
Finally+0.040
Neg logit contributions
 is-0.052
 happens-0.050
 isn-0.049
 doesn-0.049
 lives-0.048
Token.
Token ID13
Feature activation+9.98e-01

Pos logit contributions
 belongs+0.038
 happens+0.038
 guys+0.036
 doesn+0.036
 isn+0.036
Neg logit contributions
Unfortunately-0.032
Meanwhile-0.032
eyed-0.031
Just-0.031
 pounding-0.029
Token They
Token ID1119
Feature activation-2.74e-01

Pos logit contributions
 guys+0.053
 happens+0.052
 belongs+0.051
 doesn+0.050
 needs+0.049
Neg logit contributions
Unfortunately-0.039
Meanwhile-0.037
eyed-0.036
Just-0.036
On-0.035
Token like
Token ID588
Feature activation+4.96e-01

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.014
eyed+0.013
Just+0.013
 pounding+0.013
Neg logit contributions
 happens-0.011
 is-0.011
 doesn-0.011
 belongs-0.011
 isn-0.011
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
 happens+0.024
 belongs+0.024
 doesn+0.023
 isn+0.023
 is+0.023
Neg logit contributions
Unfortunately-0.020
Meanwhile-0.020
eyed-0.020
 pounding-0.019
Just-0.018
Token play
Token ID711
Feature activation+1.98e-01

Pos logit contributions
Meanwhile+0.085
Unfortunately+0.084
shadow+0.076
Just+0.076
Eventually+0.075
Neg logit contributions
 is-0.061
 guys-0.056
?"-0.056
 happens-0.055
 lives-0.054
Token with
Token ID351
Feature activation+1.96e+00

Pos logit contributions
 happens+0.010
 doesn+0.009
 belongs+0.009
 is+0.009
 isn+0.009
Neg logit contributions
Unfortunately-0.008
Meanwhile-0.008
eyed-0.008
Just-0.007
 widening-0.007
Token the
Token ID262
Feature activation+7.05e-01

Pos logit contributions
 happens+0.108
 belongs+0.106
 doesn+0.102
 needs+0.102
 isn+0.102
Neg logit contributions
Their-0.064
His-0.056
eyed-0.056
Her-0.055
Unfortunately-0.055
Token the
Token ID262
Feature activation-4.01e-01

Pos logit contributions
Unfortunately+0.002
Meanwhile+0.002
eyed+0.002
Just+0.002
 widening+0.002
Neg logit contributions
 happens-0.002
 is-0.002
 doesn-0.002
 belongs-0.002
 isn-0.002
Token car
Token ID1097
Feature activation-2.15e-01

Pos logit contributions
Unfortunately+0.019
eyed+0.019
Meanwhile+0.019
Just+0.018
 widening+0.018
Neg logit contributions
 is-0.017
 happens-0.016
 belongs-0.016
 guys-0.016
 isn-0.016
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
Unfortunately+0.014
Meanwhile+0.013
eyed+0.013
Just+0.013
 widening+0.013
Neg logit contributions
 is-0.006
 happens-0.006
 doesn-0.005
 belongs-0.005
 isn-0.005
Token mom
Token ID1995
Feature activation+3.14e-01

Pos logit contributions
 happens+0.046
 belongs+0.044
 needs+0.043
 doesn+0.043
 is+0.042
Neg logit contributions
Unfortunately-0.052
Meanwhile-0.051
eyed-0.049
 pounding-0.048
On-0.048
Tokenmy
Token ID1820
Feature activation+2.41e-01

Pos logit contributions
 happens+0.011
 belongs+0.011
 doesn+0.011
 guys+0.011
 is+0.011
Neg logit contributions
Unfortunately-0.017
Meanwhile-0.017
eyed-0.016
 pounding-0.016
Just-0.016
Token turned
Token ID2900
Feature activation-9.17e-01

Pos logit contributions
 happens+0.011
 doesn+0.010
 belongs+0.010
 is+0.010
 guys+0.010
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.011
Just-0.010
 pounding-0.010
Token on
Token ID319
Feature activation-1.05e+00

Pos logit contributions
Unfortunately+0.046
Meanwhile+0.045
Just+0.044
Finally+0.043
 widening+0.042
Neg logit contributions
 happens-0.039
 is-0.038
 doesn-0.037
 isn-0.036
 guys-0.036
Token the
Token ID262
Feature activation-6.27e-01

Pos logit contributions
Meanwhile+0.059
Unfortunately+0.058
eyed+0.057
Just+0.056
rolling+0.055
Neg logit contributions
 is-0.038
 isn-0.036
 doesn-0.035
 guys-0.035
 happens-0.034
Token radio
Token ID5243
Feature activation-1.91e+00

Pos logit contributions
Unfortunately+0.031
Meanwhile+0.031
eyed+0.030
Just+0.029
 widening+0.029
Neg logit contributions
 is-0.026
 happens-0.026
 guys-0.025
 isn-0.025
 belongs-0.025
Token and
Token ID290
Feature activation-1.69e-01

Pos logit contributions
Unfortunately+0.117
Meanwhile+0.113
Finally+0.110
Just+0.109
Eventually+0.109
Neg logit contributions
 is-0.064
 doesn-0.060
 happens-0.058
 belongs-0.058
 isn-0.057
Token everyone
Token ID2506
Feature activation+3.33e-01

Pos logit contributions
Unfortunately+0.008
Meanwhile+0.008
eyed+0.008
Just+0.008
 widening+0.008
Neg logit contributions
 happens-0.007
 is-0.007
 doesn-0.007
 belongs-0.007
 isn-0.007
Token looked
Token ID3114
Feature activation-1.17e+00

Pos logit contributions
Unfortunately+0.063
 sidelines+0.062
eyed+0.062
Meanwhile+0.061
rolling+0.057
Neg logit contributions
 is-0.049
 happens-0.047
 isn-0.045
 doesn-0.045
 belongs-0.043
Token around
Token ID1088
Feature activation-4.82e-01

Pos logit contributions
Unfortunately+0.053
Meanwhile+0.051
eyed+0.050
 pounding+0.049
har+0.049
Neg logit contributions
 happens-0.054
 is-0.053
 doesn-0.051
 isn-0.050
 belongs-0.050
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
Unfortunately+0.032
Meanwhile+0.031
eyed+0.031
Just+0.030
 pounding+0.030
Neg logit contributions
 is-0.012
 happens-0.012
 doesn-0.011
 isn-0.011
 belongs-0.011
Token she
Token ID673
Feature activation-1.88e+00

Pos logit contributions
Unfortunately+0.008
Meanwhile+0.008
eyed+0.008
Just+0.008
 widening+0.008
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token felt
Token ID2936
Feature activation-1.84e+00

Pos logit contributions
eyed+0.106
Unfortunately+0.105
 sidelines+0.103
Their+0.101
 crashing+0.099
Neg logit contributions
 is-0.065
 doesn-0.062
 isn-0.060
 happens-0.058
 can-0.057
Token so
Token ID523
Feature activation-1.57e+00

Pos logit contributions
Meanwhile+0.093
har+0.093
Unfortunately+0.093
rolling+0.091
eyed+0.090
Neg logit contributions
 is-0.071
 happens-0.070
 isn-0.067
 doesn-0.067
 can-0.063
Token happy
Token ID3772
Feature activation-5.33e-01

Pos logit contributions
Meanwhile+0.054
Unfortunately+0.053
side+0.050
 pounding+0.049
 sidelines+0.049
Neg logit contributions
 is-0.090
 happens-0.087
 doesn-0.085
 isn-0.085
 belongs-0.084
Token and
Token ID290
Feature activation-1.96e+00

Pos logit contributions
Unfortunately+0.029
Meanwhile+0.029
eyed+0.028
Finally+0.027
 widening+0.027
Neg logit contributions
 is-0.019
 happens-0.019
 doesn-0.019
 isn-0.018
 belongs-0.018
Token proud
Token ID6613
Feature activation-7.94e-02

Pos logit contributions
Unfortunately+0.067
Meanwhile+0.066
 stret+0.064
Days+0.064
Their+0.063
Neg logit contributions
 is-0.109
 doesn-0.108
 isn-0.106
 happens-0.105
 belongs-0.105
Token of
Token ID286
Feature activation-9.20e-01

Pos logit contributions
Unfortunately+0.004
Meanwhile+0.004
eyed+0.004
Just+0.004
 widening+0.004
Neg logit contributions
 happens-0.003
 is-0.003
 doesn-0.003
 isn-0.003
 belongs-0.003
Token herself
Token ID5223
Feature activation-9.38e-01

Pos logit contributions
Meanwhile+0.040
Unfortunately+0.039
rolling+0.038
eyed+0.037
Just+0.037
Neg logit contributions
 is-0.046
 happens-0.044
 isn-0.043
 doesn-0.042
 belongs-0.042
Token caught
Token ID4978
Feature activation+1.23e-01

Pos logit contributions
eyed+0.054
Unfortunately+0.053
Meanwhile+0.053
 sidelines+0.052
rolling+0.051
Neg logit contributions
 is-0.047
 happens-0.047
 doesn-0.046
 isn-0.045
 belongs-0.043
Token it
Token ID340
Feature activation-8.94e-01

Pos logit contributions
 happens+0.005
 is+0.005
 doesn+0.005
 belongs+0.005
 isn+0.005
Neg logit contributions
Unfortunately-0.006
Meanwhile-0.006
eyed-0.006
Just-0.006
 widening-0.006
Token on
Token ID319
Feature activation-4.75e-01

Pos logit contributions
Unfortunately+0.049
Meanwhile+0.048
eyed+0.047
 sidelines+0.045
Just+0.045
Neg logit contributions
 is-0.032
 doesn-0.031
 belongs-0.031
 happens-0.031
 isn-0.030
Token a
Token ID257
Feature activation-2.02e+00

Pos logit contributions
Unfortunately+0.024
Meanwhile+0.024
eyed+0.023
Just+0.022
 widening+0.022
Neg logit contributions
 is-0.019
 happens-0.019
 doesn-0.018
 isn-0.018
 guys-0.018
Token tw
Token ID665
Feature activation-1.25e+00

Pos logit contributions
eyed+0.108
Meanwhile+0.108
Unfortunately+0.106
rolling+0.102
amed+0.101
Neg logit contributions
 is-0.078
 guys-0.074
 isn-0.074
 can-0.072
 needs-0.069
Tokenig
Token ID328
Feature activation-2.71e+00

Pos logit contributions
Unfortunately+0.079
Meanwhile+0.078
eyed+0.077
 widening+0.075
 sidelines+0.073
Neg logit contributions
 is-0.033
 belongs-0.032
 doesn-0.031
 happens-0.031
 isn-0.031
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
Unfortunately+0.157
Meanwhile+0.150
 sidelines+0.147
Finally+0.146
Eventually+0.144
Neg logit contributions
 is-0.094
 belongs-0.085
 doesn-0.085
 isn-0.081
 guys-0.079
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
Unfortunately+0.005
Meanwhile+0.005
eyed+0.005
 pounding+0.005
 widening+0.005
Neg logit contributions
 happens-0.005
 is-0.005
 doesn-0.005
 isn-0.005
 belongs-0.005
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
 widening+0.088
 sidelines+0.087
 pounding+0.085
 crashing+0.082
king+0.082
Neg logit contributions
 is-0.064
 isn-0.057
 happens-0.057
?"-0.056
 doesn-0.055
Token"
Token ID1
Feature activation-8.92e-01

Pos logit contributions
 widening+0.077
 sidelines+0.071
 pounding+0.070
rolling+0.069
 crashing+0.068
Neg logit contributions
 is-0.101
 isn-0.098
 doesn-0.093
 happens-0.092
 can-0.091
TokenOh
Token ID5812
Feature activation+2.47e+00

Pos logit contributions
rolling+0.040
eyed+0.039
 pounding+0.039
Unfortunately+0.038
Meanwhile+0.037
Neg logit contributions
 happens-0.040
 isn-0.038
 is-0.038
 doesn-0.038
 guys-0.037
Token beef
Token ID12023
Feature activation+3.03e+00

Pos logit contributions
 happens+0.067
 belongs+0.065
 doesn+0.061
 guys+0.060
 isn+0.060
Neg logit contributions
Unfortunately-0.085
Meanwhile-0.083
eyed-0.080
Just-0.079
 pounding-0.079
Token!
Token ID0
Feature activation+5.67e-01

Pos logit contributions
 happens+0.119
 belongs+0.107
 doesn+0.104
 isn+0.101
 guys+0.101
Neg logit contributions
eyed-0.136
Unfortunately-0.133
Meanwhile-0.132
 pounding-0.128
 crashing-0.126
Token Please
Token ID4222
Feature activation+1.81e-01

Pos logit contributions
 happens+0.017
 belongs+0.016
 doesn+0.016
 is+0.016
 guys+0.016
Neg logit contributions
Unfortunately-0.034
Meanwhile-0.033
eyed-0.033
Just-0.032
 widening-0.031
Token!"
Token ID2474
Feature activation-2.16e+00

Pos logit contributions
 happens+0.008
 belongs+0.008
 is+0.008
 doesn+0.008
 isn+0.008
Neg logit contributions
Unfortunately-0.008
Meanwhile-0.008
eyed-0.008
Just-0.007
 widening-0.007
Token
Token ID198
Feature activation-2.47e+00

Pos logit contributions
har+0.111
eyed+0.108
 sidelines+0.107
 winding+0.107
shadow+0.106
Neg logit contributions
 is-0.080
 doesn-0.077
 isn-0.072
 means-0.072
 guys-0.072
Token
Token ID198
Feature activation-2.71e+00

Pos logit contributions
 sidelines+0.150
 widening+0.149
 winding+0.142
har+0.140
 crashing+0.139
Neg logit contributions
 is-0.074
?"-0.070
 happens-0.062
 means-0.056
 isn-0.056
TokenHis
Token ID6653
Feature activation+2.99e-01

Pos logit contributions
 widening+0.080
 sidelines+0.078
 crashing+0.073
ooting+0.071
 victorious+0.070
Neg logit contributions
 is-0.151
 guys-0.145
 happens-0.143
?"-0.142
 means-0.137
Token mom
Token ID1995
Feature activation-7.03e-01

Pos logit contributions
 happens+0.012
 belongs+0.011
 doesn+0.011
 is+0.011
 isn+0.011
Neg logit contributions
Unfortunately-0.015
Meanwhile-0.015
eyed-0.015
 pounding-0.014
Just-0.014
Token replied
Token ID8712
Feature activation-9.04e-01

Pos logit contributions
Unfortunately+0.036
Meanwhile+0.035
eyed+0.034
 sidelines+0.033
 widening+0.033
Neg logit contributions
 is-0.028
 happens-0.028
 doesn-0.027
 isn-0.027
 belongs-0.026
Token,
Token ID11
Feature activation-2.16e+00

Pos logit contributions
Unfortunately+0.066
Meanwhile+0.065
eyed+0.064
har+0.063
 sidelines+0.063
Neg logit contributions
 is-0.016
 happens-0.015
 doesn-0.014
 isn-0.014
 guys-0.013
Token "
Token ID366
Feature activation-1.89e+00

Pos logit contributions
har+0.129
eyed+0.128
Unfortunately+0.127
 sidelines+0.126
Meanwhile+0.124
Neg logit contributions
 is-0.065
 isn-0.060
 doesn-0.058
 happens-0.056
 can-0.055
Token see
Token ID766
Feature activation+2.09e+00

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
 widening+0.006
 pounding+0.006
Neg logit contributions
 happens-0.008
 is-0.007
 doesn-0.007
 belongs-0.007
 isn-0.007
Token?
Token ID30
Feature activation+2.03e-01

Pos logit contributions
 happens+0.090
 belongs+0.086
 needs+0.084
 guys+0.083
 lives+0.080
Neg logit contributions
Unfortunately-0.090
Meanwhile-0.088
His-0.088
Just-0.087
However-0.086
Tokenâ
Token ID22940
Feature activation-3.09e-02

Pos logit contributions
 happens+0.007
 is+0.007
 belongs+0.007
 doesn+0.007
 guys+0.006
Neg logit contributions
Unfortunately-0.011
Meanwhile-0.011
eyed-0.011
Just-0.011
 widening-0.011
Token
Token ID26391
Feature activation+2.09e+00

Pos logit contributions
Unfortunately+0.001
Meanwhile+0.001
eyed+0.001
Just+0.001
 widening+0.001
Neg logit contributions
 happens-0.001
 is-0.001
 doesn-0.001
 belongs-0.001
 isn-0.001
Token
Token ID198
Feature activation-2.41e+00

Pos logit contributions
 happens+0.089
 belongs+0.086
 guys+0.084
 needs+0.082
 lives+0.078
Neg logit contributions
Unfortunately-0.098
Just-0.096
rolling-0.095
Meanwhile-0.092
 pounding-0.091
Token
Token ID198
Feature activation-2.68e+00

Pos logit contributions
 widening+0.130
 sidelines+0.125
 pounding+0.124
king+0.119
 ledge+0.118
Neg logit contributions
 is-0.084
?"-0.080
 isn-0.078
 I-0.073
 can-0.072
TokenHis
Token ID6653
Feature activation-8.03e-02

Pos logit contributions
 widening+0.113
 sidelines+0.104
 victorious+0.103
 pounding+0.100
 ledge+0.099
Neg logit contributions
 is-0.119
 isn-0.115
 I-0.113
?"-0.111
 can-0.109
Token mom
Token ID1995
Feature activation-1.08e-01

Pos logit contributions
Unfortunately+0.004
Meanwhile+0.004
eyed+0.004
 widening+0.004
Just+0.004
Neg logit contributions
 happens-0.003
 is-0.003
 doesn-0.003
 belongs-0.003
 isn-0.003
Token answered
Token ID9373
Feature activation-5.10e-01

Pos logit contributions
Unfortunately+0.005
Meanwhile+0.005
eyed+0.005
 widening+0.005
Just+0.005
Neg logit contributions
 happens-0.004
 is-0.004
 doesn-0.004
 belongs-0.004
 isn-0.004
Token,
Token ID11
Feature activation-2.98e+00

Pos logit contributions
Unfortunately+0.034
Meanwhile+0.034
eyed+0.033
 widening+0.032
Just+0.032
Neg logit contributions
 happens-0.012
 is-0.012
 doesn-0.011
 isn-0.011
 guys-0.011
Token
Token ID6184
Feature activation-3.58e-01

Pos logit contributions
Unfortunately+0.170
eyed+0.169
Days+0.168
har+0.167
Meanwhile+0.166
Neg logit contributions
 isn-0.094
 is-0.094
 doesn-0.090
 I-0.084
 can-0.082
Token.
Token ID13
Feature activation-6.91e-01

Pos logit contributions
Unfortunately+0.097
Meanwhile+0.094
Finally+0.091
eyed+0.090
Days+0.089
Neg logit contributions
 is-0.051
 doesn-0.050
 isn-0.048
 belongs-0.047
 happens-0.046
Token
Token ID198
Feature activation-1.86e+00

Pos logit contributions
eyed+0.035
Meanwhile+0.035
Unfortunately+0.035
 pounding+0.034
 widening+0.034
Neg logit contributions
 isn-0.025
 is-0.025
 happens-0.025
 doesn-0.025
 belongs-0.024
Token
Token ID198
Feature activation-1.98e+00

Pos logit contributions
 widening+0.098
 sidelines+0.097
 pounding+0.095
 crashing+0.093
king+0.092
Neg logit contributions
 is-0.066
 isn-0.060
?"-0.060
 happens-0.059
 can-0.056
Tokenâ
Token ID22940
Feature activation-7.39e-01

Pos logit contributions
 widening+0.088
 crashing+0.085
 sidelines+0.084
 victorious+0.084
 pounding+0.084
Neg logit contributions
 is-0.080
 isn-0.076
 happens-0.074
 I-0.072
?"-0.072
Token
Token ID26391
Feature activation+3.05e-01

Pos logit contributions
Unfortunately+0.034
Meanwhile+0.033
 pounding+0.031
 widening+0.031
rolling+0.031
Neg logit contributions
 belongs-0.032
 doesn-0.032
 happens-0.032
 is-0.032
 isn-0.031
Token
Token ID129
Feature activation-2.73e+00

Pos logit contributions
 happens+0.014
 belongs+0.013
 is+0.013
 doesn+0.013
 guys+0.013
Neg logit contributions
Unfortunately-0.014
Meanwhile-0.014
eyed-0.013
Just-0.013
 pounding-0.013
Token
Token ID241
Feature activation-1.70e+00

Pos logit contributions
Meanwhile+0.112
Unfortunately+0.111
 distance+0.107
 widening+0.107
 crashing+0.105
Neg logit contributions
 belongs-0.126
 is-0.124
 doesn-0.120
 isn-0.117
 lives-0.116
TokenHello
Token ID15496
Feature activation+2.97e+00

Pos logit contributions
Meanwhile+0.067
Unfortunately+0.066
 sidelines+0.066
 widening+0.066
 victorious+0.065
Neg logit contributions
 is-0.082
 isn-0.079
 doesn-0.079
 happens-0.078
 needs-0.075
Token!
Token ID0
Feature activation+2.27e-01

Pos logit contributions
 belongs+0.119
 happens+0.117
 guys+0.114
 needs+0.110
 cares+0.110
Neg logit contributions
 pounding-0.130
Meanwhile-0.127
On-0.127
shadow-0.126
Suddenly-0.126
Tokenâ
Token ID22940
Feature activation-1.49e-01

Pos logit contributions
 happens+0.007
 is+0.007
 doesn+0.007
 belongs+0.007
 guys+0.007
Neg logit contributions
Unfortunately-0.013
Meanwhile-0.013
eyed-0.013
Just-0.012
 widening-0.012
Token
Token ID26391
Feature activation+1.98e+00

Pos logit contributions
Unfortunately+0.007
Meanwhile+0.007
eyed+0.007
 pounding+0.006
 widening+0.006
Neg logit contributions
 happens-0.006
 is-0.006
 doesn-0.006
 belongs-0.006
 isn-0.006
Token."
Token ID526
Feature activation-8.22e-01

Pos logit contributions
 happens+0.081
 belongs+0.079
 lives+0.077
 doesn+0.076
 guys+0.074
Neg logit contributions
eyed-0.088
 pounding-0.087
Unfortunately-0.086
Meanwhile-0.084
Just-0.083
Token Lily
Token ID20037
Feature activation-8.08e-01

Pos logit contributions
eyed+0.054
Unfortunately+0.053
Meanwhile+0.053
 pounding+0.053
 widening+0.052
Neg logit contributions
 is-0.019
 doesn-0.019
 happens-0.019
 isn-0.018
 belongs-0.017
Token smiled
Token ID13541
Feature activation-1.46e+00

Pos logit contributions
Unfortunately+0.042
Meanwhile+0.041
eyed+0.041
 sidelines+0.040
 widening+0.039
Neg logit contributions
 is-0.032
 doesn-0.031
 happens-0.030
 isn-0.030
 belongs-0.029
Token and
Token ID290
Feature activation-6.78e-01

Pos logit contributions
Unfortunately+0.092
 sidelines+0.089
Meanwhile+0.089
Finally+0.087
har+0.085
Neg logit contributions
 is-0.044
 doesn-0.041
 happens-0.039
 isn-0.038
 guys-0.037
Token said
Token ID531
Feature activation+8.43e-01

Pos logit contributions
Unfortunately+0.037
Meanwhile+0.036
eyed+0.036
 widening+0.035
Finally+0.035
Neg logit contributions
 happens-0.025
 doesn-0.024
 is-0.024
 belongs-0.023
 isn-0.022
Token,
Token ID11
Feature activation-3.26e+00

Pos logit contributions
 belongs+0.025
 doesn+0.024
 happens+0.024
 guys+0.024
 needs+0.024
Neg logit contributions
Unfortunately-0.049
eyed-0.048
Meanwhile-0.048
Just-0.047
His-0.047
Token "
Token ID366
Feature activation-1.53e+00

Pos logit contributions
har+0.215
eyed+0.210
Unfortunately+0.210
Meanwhile+0.207
 distance+0.202
Neg logit contributions
 is-0.077
 doesn-0.072
 I-0.069
 isn-0.069
 can-0.067
TokenThank
Token ID10449
Feature activation+1.97e+00

Pos logit contributions
rolling+0.069
Meanwhile+0.066
 pounding+0.066
Unfortunately+0.066
 sidelines+0.064
Neg logit contributions
 doesn-0.064
 is-0.064
 isn-0.064
 happens-0.063
 belongs-0.058
Token you
Token ID345
Feature activation+1.22e+00

Pos logit contributions
 happens+0.064
 belongs+0.062
 guys+0.060
 doesn+0.060
 isn+0.059
Neg logit contributions
Just-0.111
Her-0.110
Unfortunately-0.109
His-0.106
eyed-0.105
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
 happens+0.047
 belongs+0.044
 doesn+0.041
 lives+0.041
 needs+0.040
Neg logit contributions
Unfortunately-0.065
Meanwhile-0.062
eyed-0.060
Just-0.060
 victorious-0.060
Token Do
Token ID2141
Feature activation+2.25e+00

Pos logit contributions
 happens+0.062
 guys+0.062
 belongs+0.056
 happened+0.052
 doesn+0.051
Neg logit contributions
Unfortunately-0.120
Just-0.115
Meanwhile-0.115
eyed-0.114
However-0.112