TOP ACTIVATIONS
MAX = 0.094

the most beautiful purse she had ever seen . It was
dad said . L yl a smiled , and
and tie her sho el aces tight , just in case
" Okay , L yl a , if you
wanted . One day , N yl a wanted a chain
as he realised that the par rot had managed to find
singing about jail ?" Sy lves ter asked .
ily pad to l ily pad . Suddenly , she noticed
wanted a chain . Everywhere N yl a looked , she
the most beautiful thing she had ever seen ! She wanted
quietly hopping from l ily pad to l ily pad .
said " I 'm sorry " and they became friends .
was grateful for her own sc ooter and shared it with
happy and calm . The par rot kept shining until the
was the biggest mailbox he had ever seen and it looked
the most beautiful thing she had ever seen ! She put
it was not safe to play with chains and took it
neck l aces , grape brace lets , and grape crown
. He knew that the ac orn was a special gift
the most fancy frame he had ever seen ! He wanted

MIN ACTIVATIONS
MIN = -0.095

. Polly happily got a big bucket full of popcorn .
dad . They have a big TV in the living room
yes and gave him a big bowl of beautiful , y
the store and bought a big bag of popcorn . When
and quickly ran to get a bowl for the popcorn .
bowl of beautiful , y ummy popcorn . Tim my was
served it with a y ummy sauce .
named Amelia put on her special wrapping hat . She took
They both put on their favorite clothes and headed outside .
poured the popcorn into a big bowl and they sat down
my made her some y ummy w affles for breakfast .
mom . They had a big ball of dough to roll
Mum and dad had a big surprise for Tommy . They
and turn it on . Water fills the bath tub .
Mom and Dad have a big surprise for them . They
! They put on their cheerful clothes and hopped in the
He quickly put the DVD in the player and
milk and watching the fire work . <|endoftext|> E dd ie
bite and makes a y ummy sound . "
Ben and squee zes . Water shoots out and hits him

INTERVAL 0.047 - 0.094
CONTAINS 0.143%

. I should have shared with you . Sharing is caring
first ! It had been worth the delay ! <|endoftext|> Sus
bird loved to sing and play with his friends . One
to hop around the me adow all day long . One
generous and shared whatever she had with people in need .

INTERVAL -0.000 - 0.047
CONTAINS 51.315%

satisfaction as she looked at her beautiful castle .
a beautiful , graceful necklace to wear to a party .
Bob started to feel very sleepy . He tried his best
rock and Cathy found a stick . Then , they worked
very sad and scared . They wished they had never played

INTERVAL -0.048 - -0.000
CONTAINS 48.376%

inside and got some bread and cheese . They ran back
a 3 year old kid who lived with her mom and
! What are you doing ? â € The
and your dad fix it . And I promise , I
on the coat and went outside to play . The sun

INTERVAL -0.095 - -0.048
CONTAINS 0.166%

play in the big park . There were many things to
, with black spots . It has a long tail and
toys !" he said with a big smile .
up their room and made the beds look nice .
She was scared of the bright colors and shapes that moved
Token the
Token ID262
Feature activation+2.90e-02

Pos logit contributions
ross+0.015
umper+0.015
inger+0.014
Bet+0.014
Nut+0.014
Neg logit contributions
 sip-0.008
 dip-0.008
 popcorn-0.008
 swim-0.008
 look-0.007
Token most
Token ID749
Feature activation+3.66e-02

Pos logit contributions
ross+0.058
umper+0.056
Bet+0.054
inger+0.053
Nut+0.052
Neg logit contributions
 dip-0.035
 look-0.033
 sip-0.033
 popcorn-0.032
 picnic-0.032
Token beautiful
Token ID4950
Feature activation+3.62e-02

Pos logit contributions
ross+0.068
Bet+0.065
umper+0.065
inger+0.064
Nut+0.063
Neg logit contributions
 sip-0.046
 dip-0.046
 swim-0.044
 splash-0.042
 popcorn-0.042
Token purse
Token ID27517
Feature activation+5.08e-02

Pos logit contributions
ross+0.060
umper+0.057
Bet+0.057
inger+0.056
Nut+0.055
Neg logit contributions
 sip-0.053
 dip-0.053
 swim-0.051
 splash-0.049
 popcorn-0.049
Token she
Token ID673
Feature activation+4.20e-02

Pos logit contributions
ross+0.083
umper+0.082
Bet+0.081
inger+0.080
Nut+0.079
Neg logit contributions
 dip-0.074
 sip-0.073
 look-0.070
 swim-0.070
 movie-0.068
Token had
Token ID550
Feature activation+8.12e-02

Pos logit contributions
Bet+0.087
inger+0.086
ross+0.086
Nut+0.084
umper+0.084
Neg logit contributions
 look-0.050
 looks-0.047
 dip-0.047
 search-0.045
 swim-0.044
Token ever
Token ID1683
Feature activation+1.77e-02

Pos logit contributions
Bet+0.159
umper+0.157
Mic+0.156
Nut+0.155
ross+0.144
Neg logit contributions
 look-0.102
 dip-0.097
 search-0.096
 walk-0.093
 wait-0.092
Token seen
Token ID1775
Feature activation+4.62e-02

Pos logit contributions
ross+0.019
umper+0.017
Bet+0.017
inger+0.017
Nut+0.016
Neg logit contributions
 sip-0.036
 dip-0.036
 swim-0.035
 splash-0.035
 popcorn-0.034
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
Bet+0.096
umper+0.094
Nut+0.093
ross+0.093
inger+0.093
Neg logit contributions
 popcorn-0.046
 dip-0.045
 sip-0.044
 movie-0.043
 look-0.042
Token It
Token ID632
Feature activation+3.98e-03

Pos logit contributions
ross+0.036
umper+0.035
inger+0.033
Bet+0.032
Nut+0.032
Neg logit contributions
 sip-0.036
 dip-0.036
 swim-0.034
 splash-0.034
 look-0.034
Token was
Token ID373
Feature activation+1.34e-02

Pos logit contributions
ross+0.006
umper+0.006
inger+0.006
Bet+0.006
Nut+0.006
Neg logit contributions
 sip-0.006
 dip-0.006
 swim-0.006
 splash-0.006
 popcorn-0.006
Token dad
Token ID9955
Feature activation+6.88e-03

Pos logit contributions
Bet+0.082
ross+0.080
Nut+0.078
orns+0.076
umper+0.076
Neg logit contributions
 dip-0.041
 look-0.041
 swim-0.040
 sigh-0.040
 splash-0.038
Token said
Token ID531
Feature activation+1.07e-03

Pos logit contributions
ross+0.009
umper+0.008
enna+0.008
ppa+0.008
Bet+0.008
Neg logit contributions
 sip-0.012
 dip-0.012
 splash-0.011
 movie-0.011
 swim-0.011
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
ross+0.002
inger+0.001
amed+0.001
but+0.001
umper+0.001
Neg logit contributions
 dip-0.002
 sip-0.002
 picnic-0.002
 movie-0.002
 popcorn-0.002
Token
Token ID198
Feature activation+1.38e-02

Pos logit contributions
ross+0.060
umper+0.055
inger+0.054
Bet+0.054
eh+0.053
Neg logit contributions
 swim-0.037
 splash-0.037
 dip-0.036
 look-0.035
 sip-0.035
Token
Token ID198
Feature activation+1.36e-02

Pos logit contributions
ross+0.028
umper+0.025
inger+0.024
Bet+0.024
Mic+0.024
Neg logit contributions
 swim-0.017
 sip-0.017
 splash-0.017
 dip-0.016
 look-0.015
TokenL
Token ID43
Feature activation+8.07e-02

Pos logit contributions
ross+0.016
umper+0.015
inger+0.014
Bet+0.014
Nut+0.014
Neg logit contributions
 dip-0.026
 sip-0.026
 swim-0.026
 splash-0.025
 drive-0.024
Tokenyl
Token ID2645
Feature activation+5.49e-02

Pos logit contributions
Mic+0.132
Nut+0.122
Bet+0.120
ross+0.117
umper+0.108
Neg logit contributions
 look-0.122
 looks-0.110
 tickets-0.106
 sip-0.106
 dip-0.105
Tokena
Token ID64
Feature activation+1.07e-02

Pos logit contributions
ross+0.096
Bet+0.095
Nut+0.095
Mic+0.093
orns+0.091
Neg logit contributions
 looks-0.065
 swim-0.063
 movie-0.061
 sip-0.060
 sigh-0.059
Token smiled
Token ID13541
Feature activation+5.45e-03

Pos logit contributions
ross+0.018
Bet+0.017
umper+0.017
inger+0.017
Nut+0.017
Neg logit contributions
 sip-0.015
 dip-0.015
 swim-0.015
 splash-0.015
 popcorn-0.014
Token,
Token ID11
Feature activation+2.06e-02

Pos logit contributions
ross+0.007
Bet+0.007
umper+0.007
inger+0.007
Nut+0.006
Neg logit contributions
 sip-0.010
 dip-0.010
 swim-0.009
 splash-0.009
 popcorn-0.009
Token and
Token ID290
Feature activation+6.59e-03

Pos logit contributions
ross+0.036
inger+0.035
umper+0.035
orns+0.035
Bet+0.034
Neg logit contributions
 sigh-0.029
 dip-0.029
 sip-0.029
 splash-0.028
 swim-0.028
Token and
Token ID290
Feature activation+2.72e-02

Pos logit contributions
Bet+0.108
umper+0.105
Wal+0.104
Jud+0.102
Mic+0.101
Neg logit contributions
 look-0.065
 walk-0.057
 dip-0.057
 nap-0.054
 looks-0.054
Token tie
Token ID9839
Feature activation+4.41e-02

Pos logit contributions
umper+0.048
ross+0.047
Bet+0.046
inger+0.045
ase+0.043
Neg logit contributions
 dip-0.038
 swim-0.037
 look-0.036
 sip-0.035
 splash-0.035
Token her
Token ID607
Feature activation+3.33e-02

Pos logit contributions
ross+0.079
Bet+0.076
umper+0.074
ich+0.074
inger+0.072
Neg logit contributions
 dip-0.062
 look-0.060
 sip-0.058
 swim-0.057
 popcorn-0.057
Token sho
Token ID7354
Feature activation+3.95e-02

Pos logit contributions
ross+0.069
Bet+0.067
umper+0.065
inger+0.063
Nut+0.062
Neg logit contributions
 dip-0.038
 swim-0.036
 sip-0.036
 look-0.035
 popcorn-0.034
Tokenel
Token ID417
Feature activation+3.30e-02

Pos logit contributions
Bet+0.061
ross+0.058
 known+0.057
Wal+0.056
eh+0.056
Neg logit contributions
 sip-0.052
 dip-0.049
 search-0.045
 looks-0.044
 nap-0.043
Tokenaces
Token ID2114
Feature activation+8.03e-02

Pos logit contributions
Bet+0.040
ross+0.038
umper+0.034
Kelly+0.034
ydia+0.033
Neg logit contributions
 dip-0.063
 swim-0.062
 look-0.060
 sip-0.060
 nap-0.060
Token tight
Token ID5381
Feature activation+2.37e-02

Pos logit contributions
Bet+0.170
Nut+0.159
Mic+0.155
umper+0.155
ross+0.154
Neg logit contributions
 look-0.090
 dip-0.088
 nap-0.082
 walk-0.080
 sip-0.077
Token,
Token ID11
Feature activation+5.65e-02

Pos logit contributions
Bet+0.049
ross+0.046
umper+0.046
Nut+0.045
inger+0.044
Neg logit contributions
 dip-0.027
 sip-0.026
 swim-0.025
 look-0.024
 popcorn-0.024
Token just
Token ID655
Feature activation+2.48e-02

Pos logit contributions
umper+0.113
ross+0.112
inger+0.111
illian+0.104
Bet+0.102
Neg logit contributions
 dip-0.072
 look-0.071
 splash-0.065
 swim-0.065
 sip-0.063
Token in
Token ID287
Feature activation+1.67e-02

Pos logit contributions
ross+0.039
Bet+0.038
umper+0.037
inger+0.037
Nut+0.036
Neg logit contributions
 dip-0.038
 sip-0.038
 swim-0.037
 splash-0.036
 popcorn-0.035
Token case
Token ID1339
Feature activation+4.15e-02

Pos logit contributions
ross+0.033
umper+0.031
inger+0.031
Bet+0.031
Nut+0.030
Neg logit contributions
 sip-0.021
 dip-0.020
 search-0.020
 look-0.019
 popcorn-0.019
Token
Token ID198
Feature activation+1.88e-03

Pos logit contributions
ross+0.034
inger+0.032
Bet+0.032
umper+0.032
Nut+0.031
Neg logit contributions
 dip-0.025
 swim-0.025
 splash-0.025
 sip-0.025
 look-0.023
Token
Token ID198
Feature activation+6.71e-03

Pos logit contributions
ross+0.003
umper+0.003
Bet+0.003
inger+0.003
Nut+0.003
Neg logit contributions
 sip-0.003
 swim-0.003
 dip-0.003
 splash-0.003
 sigh-0.002
Token"
Token ID1
Feature activation+2.12e-04

Pos logit contributions
ross+0.008
umper+0.008
Bet+0.008
inger+0.008
Nut+0.007
Neg logit contributions
 sip-0.012
 dip-0.012
 swim-0.012
 splash-0.012
 movie-0.012
TokenOkay
Token ID16454
Feature activation-4.19e-03

Pos logit contributions
ross+0.000
inger+0.000
umper+0.000
Bet+0.000
Nut+0.000
Neg logit contributions
 dip-0.000
 sip-0.000
 swim-0.000
 popcorn-0.000
 splash-0.000
Token,
Token ID11
Feature activation+3.83e-02

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.006
 popcorn+0.005
 movie+0.005
Neg logit contributions
ross-0.007
Bet-0.006
inger-0.006
umper-0.006
Nut-0.006
Token L
Token ID406
Feature activation+7.99e-02

Pos logit contributions
ross+0.062
Bet+0.060
umper+0.059
inger+0.059
Nut+0.057
Neg logit contributions
 dip-0.057
 sip-0.056
 swim-0.055
 splash-0.054
 popcorn-0.052
Tokenyl
Token ID2645
Feature activation+4.23e-02

Pos logit contributions
Mic+0.146
Bet+0.132
Nut+0.132
ross+0.130
umper+0.123
Neg logit contributions
 look-0.104
 looks-0.093
 tickets-0.091
 wait-0.086
 dip-0.085
Tokena
Token ID64
Feature activation+1.07e-02

Pos logit contributions
Bet+0.079
Mic+0.078
Nut+0.075
umper+0.070
ross+0.069
Neg logit contributions
 looks-0.048
 swim-0.048
 look-0.046
 movie-0.044
 drive-0.043
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
ross+0.022
Bet+0.022
umper+0.022
inger+0.021
Nut+0.021
Neg logit contributions
 sip-0.011
 dip-0.010
 swim-0.010
 splash-0.010
 popcorn-0.009
Token if
Token ID611
Feature activation-1.44e-03

Pos logit contributions
ross+0.018
umper+0.017
Bet+0.017
Nut+0.017
ydia+0.017
Neg logit contributions
 sip-0.017
 dip-0.016
 swim-0.016
 movie-0.016
 popcorn-0.016
Token you
Token ID345
Feature activation+2.74e-03

Pos logit contributions
 sip+0.002
 dip+0.002
 splash+0.002
 swim+0.002
 movie+0.002
Neg logit contributions
ross-0.002
Nut-0.002
Bet-0.002
umper-0.002
inger-0.002
Token wanted
Token ID2227
Feature activation+1.99e-02

Pos logit contributions
ross+0.038
Bet+0.036
inger+0.036
Nut+0.034
umper+0.034
Neg logit contributions
 sip-0.033
 dip-0.032
 swim-0.031
 looks-0.030
 look-0.030
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
Bet+0.043
Nut+0.043
inger+0.042
Mic+0.042
umper+0.042
Neg logit contributions
 look-0.020
 dip-0.020
 swim-0.019
 sip-0.019
 nap-0.018
Token One
Token ID1881
Feature activation+3.34e-03

Pos logit contributions
 sip+0.021
 dip+0.021
 swim+0.020
 splash+0.020
 popcorn+0.020
Neg logit contributions
ross-0.017
umper-0.017
Bet-0.016
inger-0.016
Nut-0.016
Token day
Token ID1110
Feature activation-1.34e-02

Pos logit contributions
ross+0.005
Bet+0.005
eh+0.004
umper+0.004
inger+0.004
Neg logit contributions
 dip-0.005
 argue-0.005
 sip-0.005
 swim-0.005
 sigh-0.005
Token,
Token ID11
Feature activation-6.72e-03

Pos logit contributions
 sip+0.019
 dip+0.018
 swim+0.018
 splash+0.017
 movie+0.017
Neg logit contributions
ross-0.022
umper-0.020
Bet-0.020
inger-0.020
Op-0.020
Token N
Token ID399
Feature activation+7.96e-02

Pos logit contributions
 dip+0.010
 sip+0.010
 swim+0.009
 splash+0.009
 popcorn+0.009
Neg logit contributions
ross-0.011
Bet-0.011
umper-0.011
inger-0.011
Nut-0.011
Tokenyl
Token ID2645
Feature activation+3.77e-02

Pos logit contributions
Mic+0.130
Nut+0.122
Bet+0.121
ross+0.121
umper+0.115
Neg logit contributions
 look-0.112
 dip-0.106
 looks-0.103
 sip-0.100
 Today-0.099
Tokena
Token ID64
Feature activation+8.25e-03

Pos logit contributions
Nut+0.074
Bet+0.074
ross+0.074
Mic+0.070
orns+0.067
Neg logit contributions
 swim-0.036
's-0.036
 looks-0.034
 movie-0.033
 look-0.031
Token wanted
Token ID2227
Feature activation-4.23e-03

Pos logit contributions
ross+0.017
inger+0.016
Nut+0.016
umper+0.016
Bet+0.016
Neg logit contributions
 swim-0.010
 sip-0.009
 looks-0.009
 walk-0.009
 splash-0.009
Token a
Token ID257
Feature activation-9.28e-03

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.006
 popcorn+0.006
 splash+0.006
Neg logit contributions
ross-0.007
Bet-0.006
umper-0.006
inger-0.006
Nut-0.006
Token chain
Token ID6333
Feature activation+2.25e-02

Pos logit contributions
 dip+0.010
 anticipation+0.009
 sip+0.009
 swim+0.009
 splash+0.009
Neg logit contributions
Bet-0.015
Nut-0.015
Op-0.014
ydia-0.014
ich-0.014
Token as
Token ID355
Feature activation+2.19e-03

Pos logit contributions
 dip+0.006
 sip+0.006
 swim+0.006
 splash+0.006
 popcorn+0.006
Neg logit contributions
ross-0.010
Bet-0.010
umper-0.010
inger-0.010
Nut-0.009
Token he
Token ID339
Feature activation+1.01e-02

Pos logit contributions
umper+0.004
ross+0.004
inger+0.004
Bet+0.004
Nut+0.004
Neg logit contributions
 swim-0.003
 dip-0.003
 sip-0.003
 splash-0.003
 popcorn-0.003
Token realised
Token ID19169
Feature activation+1.12e-02

Pos logit contributions
ross+0.019
Bet+0.018
inger+0.018
umper+0.018
Nut+0.018
Neg logit contributions
 swim-0.014
 dip-0.014
 sip-0.013
 splash-0.013
 walk-0.013
Token that
Token ID326
Feature activation-1.39e-02

Pos logit contributions
ross+0.021
inger+0.021
Bet+0.021
umper+0.021
Mic+0.020
Neg logit contributions
 dip-0.014
 swim-0.014
 popcorn-0.014
 sip-0.013
 splash-0.013
Token the
Token ID262
Feature activation+1.26e-02

Pos logit contributions
 sip+0.020
 dip+0.020
 swim+0.019
 splash+0.019
 popcorn+0.019
Neg logit contributions
ross-0.023
Bet-0.022
umper-0.022
inger-0.021
Nut-0.021
Token par
Token ID1582
Feature activation+7.90e-02

Pos logit contributions
ross+0.022
Bet+0.021
umper+0.021
inger+0.021
Nut+0.020
Neg logit contributions
 sip-0.017
 dip-0.017
 swim-0.016
 splash-0.015
 popcorn-0.015
Tokenrot
Token ID10599
Feature activation+2.32e-02

Pos logit contributions
ross+0.098
Bet+0.097
ydia+0.087
illian+0.086
umper+0.085
Neg logit contributions
 swim-0.125
 drive-0.120
 movie-0.119
 dip-0.117
 picnic-0.114
Token had
Token ID550
Feature activation+3.61e-02

Pos logit contributions
ross+0.041
Bet+0.039
inger+0.039
umper+0.039
Nut+0.038
Neg logit contributions
 swim-0.033
 sip-0.033
 dip-0.032
 looks-0.031
 splash-0.031
Token managed
Token ID5257
Feature activation+2.08e-02

Pos logit contributions
ross+0.058
umper+0.057
Bet+0.057
Mic+0.055
inger+0.054
Neg logit contributions
 dip-0.055
 swim-0.054
 look-0.053
 sip-0.053
 splash-0.050
Token to
Token ID284
Feature activation+1.56e-02

Pos logit contributions
Bet+0.041
ross+0.041
umper+0.041
Mic+0.041
ase+0.040
Neg logit contributions
 look-0.024
 dip-0.023
 swim-0.023
 sigh-0.022
 sip-0.022
Token find
Token ID1064
Feature activation+2.31e-02

Pos logit contributions
ross+0.035
umper+0.033
Bet+0.033
inger+0.033
Nut+0.032
Neg logit contributions
 dip-0.015
 swim-0.015
 sip-0.015
 splash-0.014
 look-0.013
Token singing
Token ID13777
Feature activation+1.89e-02

Pos logit contributions
ross+0.023
Bet+0.022
umper+0.022
inger+0.021
Nut+0.021
Neg logit contributions
 sip-0.018
 dip-0.018
 swim-0.018
 splash-0.017
 look-0.017
Token about
Token ID546
Feature activation+1.89e-02

Pos logit contributions
ross+0.033
umper+0.031
inger+0.031
Bet+0.031
Nut+0.030
Neg logit contributions
 sip-0.027
 swim-0.026
 dip-0.026
 splash-0.026
 movie-0.026
Token jail
Token ID7356
Feature activation+1.63e-02

Pos logit contributions
ross+0.031
inger+0.029
umper+0.029
Bet+0.029
ydia+0.028
Neg logit contributions
 swim-0.029
 dip-0.028
 sip-0.028
 popcorn-0.027
 movie-0.027
Token?"
Token ID1701
Feature activation+4.48e-02

Pos logit contributions
ross+0.027
Bet+0.026
umper+0.026
inger+0.026
Nut+0.025
Neg logit contributions
 sip-0.023
 dip-0.023
 swim-0.022
 splash-0.022
 popcorn-0.021
Token Sy
Token ID1632
Feature activation+5.27e-02

Pos logit contributions
ross+0.055
Bet+0.051
umper+0.051
inger+0.050
Nut+0.048
Neg logit contributions
 sip-0.085
 dip-0.084
 swim-0.082
 splash-0.080
 popcorn-0.079
Tokenlves
Token ID31018
Feature activation+7.89e-02

Pos logit contributions
ross+0.069
Bet+0.057
inger+0.054
umper+0.053
Mic+0.052
Neg logit contributions
 sip-0.097
 dip-0.097
 swim-0.096
 look-0.092
 splash-0.092
Tokenter
Token ID353
Feature activation+2.90e-02

Pos logit contributions
Kelly+0.123
Mic+0.112
odi+0.110
Bet+0.109
enna+0.108
Neg logit contributions
 swim-0.121
 splash-0.113
 look-0.110
 dive-0.109
 closer-0.108
Token asked
Token ID1965
Feature activation+2.79e-02

Pos logit contributions
ross+0.045
Bet+0.043
umper+0.043
inger+0.042
Nut+0.041
Neg logit contributions
 sip-0.045
 dip-0.045
 swim-0.043
 popcorn-0.042
 movie-0.042
Token.
Token ID13
Feature activation+3.02e-02

Pos logit contributions
ross+0.061
inger+0.059
Bet+0.059
umper+0.058
ydia+0.057
Neg logit contributions
 swim-0.025
 sip-0.025
 dip-0.024
 look-0.023
 splash-0.022
Token
Token ID220
Feature activation+5.09e-02

Pos logit contributions
ross+0.047
umper+0.043
inger+0.043
Bet+0.041
ydia+0.040
Neg logit contributions
 swim-0.048
 dip-0.048
 sip-0.048
 splash-0.047
 look-0.046
Token
Token ID198
Feature activation+2.82e-02

Pos logit contributions
ross+0.112
umper+0.100
Bet+0.100
ydia+0.099
inger+0.096
Neg logit contributions
 swim-0.044
 sip-0.044
 Today-0.042
 dip-0.042
 search-0.040
Tokenily
Token ID813
Feature activation+9.33e-04

Pos logit contributions
Bet+0.047
Nut+0.045
ross+0.045
Mic+0.044
Kelly+0.043
Neg logit contributions
 sip-0.085
 dip-0.083
 swim-0.080
 splash-0.079
 nap-0.079
Token pad
Token ID14841
Feature activation+7.75e-02

Pos logit contributions
ross+0.002
Bet+0.002
umper+0.002
inger+0.002
Nut+0.002
Neg logit contributions
 dip-0.001
 sip-0.001
 swim-0.001
 popcorn-0.001
 splash-0.001
Token to
Token ID284
Feature activation+2.47e-02

Pos logit contributions
umper+0.151
Bet+0.148
ross+0.146
ydia+0.146
Nut+0.144
Neg logit contributions
 swim-0.079
 dip-0.079
 walk-0.076
 sip-0.075
 look-0.074
Token l
Token ID300
Feature activation+4.36e-02

Pos logit contributions
ross+0.049
umper+0.046
inger+0.046
Bet+0.045
Nut+0.044
Neg logit contributions
 dip-0.030
 sip-0.030
 swim-0.029
 splash-0.028
 look-0.027
Tokenily
Token ID813
Feature activation-2.70e-03

Pos logit contributions
Bet+0.040
ross+0.040
ich+0.037
Nut+0.037
ully+0.035
Neg logit contributions
 sip-0.091
 dip-0.089
 swim-0.086
 nap-0.083
 splash-0.083
Token pad
Token ID14841
Feature activation+7.87e-02

Pos logit contributions
 sip+0.003
 dip+0.003
 swim+0.003
 splash+0.003
 popcorn+0.003
Neg logit contributions
ross-0.005
Bet-0.005
umper-0.005
inger-0.005
Nut-0.005
Token.
Token ID13
Feature activation-5.83e-03

Pos logit contributions
umper+0.169
Bet+0.167
ydia+0.164
ross+0.164
Nut+0.162
Neg logit contributions
 swim-0.063
 dip-0.062
 look-0.060
 sip-0.059
 walk-0.059
Token Suddenly
Token ID24975
Feature activation-3.14e-03

Pos logit contributions
 sip+0.009
 dip+0.008
 swim+0.008
 splash+0.008
 popcorn+0.008
Neg logit contributions
ross-0.010
umper-0.009
inger-0.009
Bet-0.009
Nut-0.009
Token,
Token ID11
Feature activation-7.85e-03

Pos logit contributions
 sip+0.004
 dip+0.004
 swim+0.003
 splash+0.003
 popcorn+0.003
Neg logit contributions
ross-0.006
umper-0.006
Bet-0.006
inger-0.006
Nut-0.006
Token she
Token ID673
Feature activation+2.70e-02

Pos logit contributions
 sip+0.013
 dip+0.012
 swim+0.012
 popcorn+0.012
 look+0.012
Neg logit contributions
ross-0.013
inger-0.012
umper-0.012
Bet-0.012
ully-0.012
Token noticed
Token ID6810
Feature activation+2.19e-02

Pos logit contributions
ross+0.051
inger+0.048
ydia+0.047
umper+0.046
ooks+0.045
Neg logit contributions
 swim-0.034
 sip-0.034
 dip-0.034
 nap-0.033
 walk-0.032
Token wanted
Token ID2227
Feature activation-4.23e-03

Pos logit contributions
ross+0.017
inger+0.016
Nut+0.016
umper+0.016
Bet+0.016
Neg logit contributions
 swim-0.010
 sip-0.009
 looks-0.009
 walk-0.009
 splash-0.009
Token a
Token ID257
Feature activation-9.28e-03

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.006
 popcorn+0.006
 splash+0.006
Neg logit contributions
ross-0.007
Bet-0.006
umper-0.006
inger-0.006
Nut-0.006
Token chain
Token ID6333
Feature activation+2.25e-02

Pos logit contributions
 dip+0.010
 anticipation+0.009
 sip+0.009
 swim+0.009
 splash+0.009
Neg logit contributions
Bet-0.015
Nut-0.015
Op-0.014
ydia-0.014
ich-0.014
Token.
Token ID13
Feature activation-7.67e-03

Pos logit contributions
ross+0.042
Bet+0.041
umper+0.040
inger+0.039
Nut+0.039
Neg logit contributions
 dip-0.029
 look-0.029
 sip-0.029
 swim-0.028
 walk-0.027
Token Everywhere
Token ID48201
Feature activation-7.50e-03

Pos logit contributions
 sip+0.015
 dip+0.015
 swim+0.015
 splash+0.014
 popcorn+0.014
Neg logit contributions
ross-0.009
umper-0.008
Bet-0.008
inger-0.008
Nut-0.008
Token N
Token ID399
Feature activation+7.86e-02

Pos logit contributions
 dip+0.013
 sip+0.013
 swim+0.013
 splash+0.013
 popcorn+0.013
Neg logit contributions
ross-0.010
Bet-0.009
umper-0.009
inger-0.009
Nut-0.009
Tokenyl
Token ID2645
Feature activation+4.12e-02

Pos logit contributions
Mic+0.131
Nut+0.126
Bet+0.122
ross+0.120
umper+0.115
Neg logit contributions
 look-0.114
 looks-0.107
 dip-0.105
 sip-0.103
 swim-0.102
Tokena
Token ID64
Feature activation+3.45e-02

Pos logit contributions
ross+0.078
Nut+0.077
Bet+0.075
Mic+0.070
ooks+0.068
Neg logit contributions
 looks-0.049
 swim-0.048
 dip-0.047
 sip-0.047
 look-0.047
Token looked
Token ID3114
Feature activation+9.89e-03

Pos logit contributions
ross+0.073
Bet+0.067
umper+0.067
Nut+0.066
inger+0.066
Neg logit contributions
 dip-0.042
 swim-0.041
 walk-0.041
 sip-0.040
 looks-0.039
Token,
Token ID11
Feature activation+1.89e-02

Pos logit contributions
ross+0.020
Bet+0.019
inger+0.019
umper+0.019
Nut+0.019
Neg logit contributions
 dip-0.012
 sip-0.011
 swim-0.011
 popcorn-0.010
 splash-0.010
Token she
Token ID673
Feature activation+1.90e-02

Pos logit contributions
ross+0.027
Bet+0.025
umper+0.025
inger+0.025
Nut+0.024
Neg logit contributions
 dip-0.033
 sip-0.032
 swim-0.031
 splash-0.031
 popcorn-0.031
Token the
Token ID262
Feature activation+4.23e-02

Pos logit contributions
ross+0.047
umper+0.046
Bet+0.044
inger+0.044
Mic+0.043
Neg logit contributions
 dip-0.021
 look-0.020
 sip-0.019
 swim-0.019
 popcorn-0.019
Token most
Token ID749
Feature activation+4.74e-02

Pos logit contributions
ross+0.091
Bet+0.084
umper+0.084
inger+0.080
Nut+0.079
Neg logit contributions
 dip-0.050
 look-0.048
 swim-0.046
 picnic-0.044
 sip-0.044
Token beautiful
Token ID4950
Feature activation+4.43e-02

Pos logit contributions
ross+0.094
Bet+0.091
umper+0.090
inger+0.088
Nut+0.087
Neg logit contributions
 dip-0.056
 sip-0.054
 swim-0.053
 splash-0.050
 popcorn-0.050
Token thing
Token ID1517
Feature activation+2.95e-02

Pos logit contributions
ross+0.077
Bet+0.074
umper+0.074
inger+0.071
Nut+0.071
Neg logit contributions
 dip-0.062
 sip-0.062
 swim-0.060
 splash-0.058
 look-0.057
Token she
Token ID673
Feature activation+5.09e-02

Pos logit contributions
ross+0.046
umper+0.045
Bet+0.044
inger+0.044
Nut+0.043
Neg logit contributions
 sip-0.046
 dip-0.046
 swim-0.045
 splash-0.043
 popcorn-0.043
Token had
Token ID550
Feature activation+7.77e-02

Pos logit contributions
ross+0.105
Bet+0.104
inger+0.102
ooks+0.098
Nut+0.098
Neg logit contributions
 look-0.062
 search-0.057
 looks-0.057
 dip-0.057
 swim-0.057
Token ever
Token ID1683
Feature activation+2.50e-02

Pos logit contributions
Bet+0.156
Mic+0.155
Nut+0.155
umper+0.151
ross+0.144
Neg logit contributions
 look-0.089
 search-0.087
 swim-0.086
 dip-0.085
 wait-0.084
Token seen
Token ID1775
Feature activation+4.88e-02

Pos logit contributions
ross+0.028
Bet+0.026
umper+0.026
inger+0.026
Nut+0.025
Neg logit contributions
 sip-0.049
 dip-0.049
 swim-0.048
 splash-0.047
 popcorn-0.047
Token!
Token ID0
Feature activation+1.57e-02

Pos logit contributions
Bet+0.109
Nut+0.106
ross+0.105
inger+0.105
umper+0.104
Neg logit contributions
 popcorn-0.041
 dip-0.041
 sip-0.040
 look-0.038
 nap-0.038
Token She
Token ID1375
Feature activation+3.73e-02

Pos logit contributions
ross+0.030
umper+0.027
inger+0.027
Bet+0.026
Mic+0.026
Neg logit contributions
 sip-0.021
 dip-0.020
 look-0.020
 splash-0.020
 swim-0.019
Token wanted
Token ID2227
Feature activation+1.99e-02

Pos logit contributions
ross+0.075
inger+0.070
umper+0.070
Bet+0.070
orns+0.067
Neg logit contributions
 swim-0.050
 dip-0.049
 sip-0.047
 splash-0.046
 looks-0.045
Token quietly
Token ID12703
Feature activation+3.95e-03

Pos logit contributions
ross+0.061
umper+0.059
inger+0.058
ydia+0.056
Nut+0.055
Neg logit contributions
 dip-0.039
 swim-0.038
 sip-0.038
 splash-0.037
 look-0.037
Token hopping
Token ID47153
Feature activation+3.56e-02

Pos logit contributions
ross+0.005
Bet+0.005
inger+0.005
umper+0.005
ich+0.005
Neg logit contributions
 sip-0.007
 movie-0.007
 dip-0.007
 popcorn-0.007
 swim-0.006
Token from
Token ID422
Feature activation+8.83e-03

Pos logit contributions
ross+0.065
umper+0.064
illian+0.062
anya+0.061
Kelly+0.060
Neg logit contributions
 swim-0.049
 sip-0.048
 dip-0.047
 splash-0.047
 look-0.045
Token l
Token ID300
Feature activation+4.54e-02

Pos logit contributions
ross+0.017
inger+0.016
umper+0.016
Bet+0.015
Nut+0.015
Neg logit contributions
 sip-0.012
 dip-0.012
 swim-0.012
 splash-0.011
 popcorn-0.011
Tokenily
Token ID813
Feature activation+9.33e-04

Pos logit contributions
Bet+0.047
Nut+0.045
ross+0.045
Mic+0.044
Kelly+0.043
Neg logit contributions
 sip-0.085
 dip-0.083
 swim-0.080
 splash-0.079
 nap-0.079
Token pad
Token ID14841
Feature activation+7.75e-02

Pos logit contributions
ross+0.002
Bet+0.002
umper+0.002
inger+0.002
Nut+0.002
Neg logit contributions
 dip-0.001
 sip-0.001
 swim-0.001
 popcorn-0.001
 splash-0.001
Token to
Token ID284
Feature activation+2.47e-02

Pos logit contributions
umper+0.151
Bet+0.148
ross+0.146
ydia+0.146
Nut+0.144
Neg logit contributions
 swim-0.079
 dip-0.079
 walk-0.076
 sip-0.075
 look-0.074
Token l
Token ID300
Feature activation+4.36e-02

Pos logit contributions
ross+0.049
umper+0.046
inger+0.046
Bet+0.045
Nut+0.044
Neg logit contributions
 dip-0.030
 sip-0.030
 swim-0.029
 splash-0.028
 look-0.027
Tokenily
Token ID813
Feature activation-2.70e-03

Pos logit contributions
Bet+0.040
ross+0.040
ich+0.037
Nut+0.037
ully+0.035
Neg logit contributions
 sip-0.091
 dip-0.089
 swim-0.086
 nap-0.083
 splash-0.083
Token pad
Token ID14841
Feature activation+7.87e-02

Pos logit contributions
 sip+0.003
 dip+0.003
 swim+0.003
 splash+0.003
 popcorn+0.003
Neg logit contributions
ross-0.005
Bet-0.005
umper-0.005
inger-0.005
Nut-0.005
Token.
Token ID13
Feature activation-5.83e-03

Pos logit contributions
umper+0.169
Bet+0.167
ydia+0.164
ross+0.164
Nut+0.162
Neg logit contributions
 swim-0.063
 dip-0.062
 look-0.060
 sip-0.059
 walk-0.059
Token said
Token ID531
Feature activation+1.37e-02

Pos logit contributions
ross+0.045
inger+0.043
ooks+0.041
Bet+0.041
ydia+0.041
Neg logit contributions
 swim-0.036
 splash-0.033
 sip-0.033
 sigh-0.033
 look-0.032
Token "
Token ID366
Feature activation+3.70e-02

Pos logit contributions
ross+0.026
umper+0.025
inger+0.025
Bet+0.025
Nut+0.024
Neg logit contributions
 sip-0.016
 swim-0.016
 dip-0.016
 splash-0.015
 popcorn-0.015
TokenI
Token ID40
Feature activation+2.32e-02

Pos logit contributions
ross+0.055
ooks+0.051
inger+0.050
ydia+0.050
illian+0.049
Neg logit contributions
 dip-0.062
 swim-0.061
 sip-0.057
 splash-0.057
 walk-0.056
Token'm
Token ID1101
Feature activation+1.70e-02

Pos logit contributions
ross+0.039
Bet+0.037
umper+0.037
inger+0.037
Nut+0.036
Neg logit contributions
 sip-0.034
 dip-0.034
 swim-0.033
 splash-0.032
 movie-0.031
Token sorry
Token ID7926
Feature activation+2.05e-02

Pos logit contributions
ross+0.034
inger+0.033
Bet+0.033
umper+0.032
ydia+0.031
Neg logit contributions
 swim-0.020
 dip-0.019
 sip-0.019
 splash-0.019
 popcorn-0.018
Token"
Token ID1
Feature activation+7.74e-02

Pos logit contributions
ross+0.040
Bet+0.038
umper+0.038
inger+0.038
Nut+0.037
Neg logit contributions
 sip-0.024
 dip-0.024
 swim-0.023
 splash-0.022
 popcorn-0.022
Token and
Token ID290
Feature activation+2.51e-02

Pos logit contributions
ross+0.180
ooks+0.177
inger+0.163
Bet+0.160
eh+0.159
Neg logit contributions
 look-0.067
 swim-0.061
 closer-0.058
 one-0.056
 popcorn-0.055
Token they
Token ID484
Feature activation+5.45e-03

Pos logit contributions
ross+0.053
inger+0.052
umper+0.050
orns+0.049
Bet+0.049
Neg logit contributions
 swim-0.030
 splash-0.028
 dip-0.026
 look-0.026
 sip-0.025
Token became
Token ID2627
Feature activation-3.00e-03

Pos logit contributions
ross+0.008
inger+0.008
umper+0.008
Bet+0.008
Nut+0.007
Neg logit contributions
 sip-0.009
 dip-0.009
 swim-0.009
 splash-0.008
 popcorn-0.008
Token friends
Token ID2460
Feature activation+1.74e-02

Pos logit contributions
 swim+0.005
 dip+0.005
 sip+0.005
 splash+0.005
 popcorn+0.004
Neg logit contributions
ross-0.005
Bet-0.004
inger-0.004
umper-0.004
Nut-0.004
Token.
Token ID13
Feature activation+2.95e-02

Pos logit contributions
ross+0.032
Bet+0.031
umper+0.031
inger+0.030
Nut+0.030
Neg logit contributions
 sip-0.022
 dip-0.022
 swim-0.021
 splash-0.020
 popcorn-0.020
Token was
Token ID373
Feature activation+9.52e-03

Pos logit contributions
Bet+0.038
ross+0.037
eh+0.036
inger+0.036
Nut+0.036
Neg logit contributions
 looks-0.031
 swim-0.028
's-0.027
 look-0.027
 turns-0.025
Token grateful
Token ID14066
Feature activation+2.82e-02

Pos logit contributions
ross+0.017
umper+0.016
inger+0.016
Bet+0.016
Nut+0.016
Neg logit contributions
 dip-0.012
 swim-0.012
 sip-0.012
 popcorn-0.012
 splash-0.012
Token for
Token ID329
Feature activation+3.98e-02

Pos logit contributions
Bet+0.066
Mic+0.065
umper+0.064
Nut+0.062
inger+0.062
Neg logit contributions
 dip-0.025
 look-0.024
 sip-0.023
 swim-0.023
 nap-0.023
Token her
Token ID607
Feature activation+4.55e-02

Pos logit contributions
inger+0.077
ross+0.070
ase+0.070
umbled+0.070
igi+0.069
Neg logit contributions
 look-0.049
 sip-0.049
 dip-0.045
 swim-0.045
 movie-0.044
Token own
Token ID898
Feature activation+3.92e-02

Pos logit contributions
ross+0.090
Bet+0.086
umper+0.085
inger+0.083
Nut+0.080
Neg logit contributions
 swim-0.054
 dip-0.054
 sip-0.052
 splash-0.051
 movie-0.049
Token sc
Token ID629
Feature activation+7.71e-02

Pos logit contributions
ross+0.076
Bet+0.073
umper+0.072
inger+0.071
Nut+0.069
Neg logit contributions
 dip-0.047
 swim-0.046
 sip-0.045
 splash-0.044
 movie-0.043
Tokenooter
Token ID25141
Feature activation+4.49e-02

Pos logit contributions
ross+0.127
Bet+0.126
umper+0.117
Nut+0.113
Da+0.113
Neg logit contributions
 dip-0.107
 swim-0.105
 drive-0.103
 splash-0.101
 look-0.100
Token and
Token ID290
Feature activation+1.18e-02

Pos logit contributions
ross+0.081
Bet+0.081
umper+0.080
inger+0.078
Nut+0.077
Neg logit contributions
 look-0.058
 dip-0.054
 movie-0.054
 sip-0.054
 swim-0.054
Token shared
Token ID4888
Feature activation+4.19e-02

Pos logit contributions
umper+0.021
inger+0.021
Bet+0.020
ross+0.020
eh+0.020
Neg logit contributions
 look-0.018
 swim-0.017
 looks-0.017
 dip-0.016
 splash-0.016
Token it
Token ID340
Feature activation+1.31e-02

Pos logit contributions
ross+0.083
umper+0.079
inger+0.079
Bet+0.077
ich+0.075
Neg logit contributions
 sip-0.054
 look-0.053
 dip-0.050
 popcorn-0.050
 swim-0.047
Token with
Token ID351
Feature activation+2.92e-02

Pos logit contributions
ross+0.022
Bet+0.022
umper+0.022
inger+0.021
Nut+0.021
Neg logit contributions
 sip-0.018
 dip-0.018
 swim-0.018
 splash-0.017
 popcorn-0.017
Token happy
Token ID3772
Feature activation-1.84e-04

Pos logit contributions
 sip+0.001
 dip+0.001
 swim+0.001
 popcorn+0.001
 movie+0.001
Neg logit contributions
ross-0.001
Bet-0.001
umper-0.001
inger-0.001
Nut-0.001
Token and
Token ID290
Feature activation+4.87e-03

Pos logit contributions
 dip+0.000
 sip+0.000
 swim+0.000
 splash+0.000
 popcorn+0.000
Neg logit contributions
ross-0.000
Bet-0.000
umper-0.000
inger-0.000
Nut-0.000
Token calm
Token ID9480
Feature activation-2.02e-02

Pos logit contributions
ross+0.008
umper+0.008
Bet+0.008
inger+0.008
Nut+0.007
Neg logit contributions
 dip-0.007
 swim-0.007
 sip-0.007
 splash-0.007
 popcorn-0.007
Token.
Token ID13
Feature activation-1.11e-03

Pos logit contributions
 sip+0.032
 dip+0.031
 swim+0.029
 movie+0.029
 popcorn+0.029
Neg logit contributions
ross-0.030
umper-0.028
Bet-0.028
inger-0.027
Nut-0.027
Token The
Token ID383
Feature activation+4.69e-02

Pos logit contributions
 sip+0.001
 swim+0.001
 dip+0.001
 splash+0.001
 looks+0.001
Neg logit contributions
ross-0.002
inger-0.002
umper-0.002
Bet-0.002
ppa-0.002
Token par
Token ID1582
Feature activation+7.71e-02

Pos logit contributions
ross+0.076
Bet+0.071
umper+0.071
inger+0.069
Nut+0.067
Neg logit contributions
 dip-0.072
 sip-0.071
 swim-0.071
 splash-0.067
 movie-0.067
Tokenrot
Token ID10599
Feature activation+1.32e-02

Pos logit contributions
ross+0.105
ydia+0.095
Bet+0.093
 Jade+0.092
ooks+0.092
Neg logit contributions
 swim-0.111
 movie-0.107
 drive-0.102
 bite-0.099
 dip-0.097
Token kept
Token ID4030
Feature activation-7.97e-04

Pos logit contributions
ross+0.025
Bet+0.024
inger+0.024
umper+0.024
Nut+0.024
Neg logit contributions
 swim-0.018
 dip-0.017
 looks-0.017
 splash-0.017
 sip-0.017
Token shining
Token ID22751
Feature activation+4.71e-03

Pos logit contributions
 sip+0.001
 dip+0.001
 swim+0.001
 splash+0.001
 movie+0.001
Neg logit contributions
ross-0.001
umper-0.001
Bet-0.001
inger-0.001
Nut-0.001
Token until
Token ID1566
Feature activation-6.59e-04

Pos logit contributions
ross+0.006
Bet+0.006
umper+0.006
inger+0.006
Nut+0.006
Neg logit contributions
 sip-0.008
 dip-0.008
 swim-0.008
 splash-0.008
 movie-0.008
Token the
Token ID262
Feature activation+3.25e-02

Pos logit contributions
 dip+0.001
 sip+0.001
 swim+0.001
 splash+0.001
 popcorn+0.001
Neg logit contributions
ross-0.001
umper-0.001
Bet-0.001
inger-0.001
Nut-0.001
Token was
Token ID373
Feature activation+6.03e-03

Pos logit contributions
 sip+0.011
 dip+0.011
 swim+0.011
 splash+0.011
 popcorn+0.011
Neg logit contributions
ross-0.011
umper-0.010
Bet-0.010
inger-0.010
Nut-0.010
Token the
Token ID262
Feature activation+2.56e-02

Pos logit contributions
ross+0.012
umper+0.012
inger+0.011
Bet+0.011
Nut+0.011
Neg logit contributions
 dip-0.007
 popcorn-0.007
 sip-0.007
 swim-0.007
 look-0.007
Token biggest
Token ID4094
Feature activation+2.43e-02

Pos logit contributions
ross+0.049
umper+0.048
inger+0.045
Bet+0.045
ydia+0.044
Neg logit contributions
 dip-0.032
 look-0.031
 popcorn-0.030
 picnic-0.030
 swim-0.030
Token mailbox
Token ID37282
Feature activation+2.71e-02

Pos logit contributions
ross+0.036
Bet+0.035
inger+0.034
Nut+0.033
umper+0.033
Neg logit contributions
 sip-0.038
 dip-0.038
 swim-0.037
 splash-0.036
 popcorn-0.036
Token he
Token ID339
Feature activation+4.20e-02

Pos logit contributions
ross+0.051
umper+0.050
Bet+0.049
inger+0.049
Nut+0.048
Neg logit contributions
 dip-0.033
 swim-0.033
 sip-0.032
 splash-0.031
 popcorn-0.031
Token had
Token ID550
Feature activation+7.69e-02

Pos logit contributions
ross+0.088
Bet+0.088
inger+0.087
umper+0.083
ooks+0.082
Neg logit contributions
 look-0.047
 swim-0.046
 looks-0.045
 search-0.044
 drive-0.044
Token ever
Token ID1683
Feature activation+2.42e-02

Pos logit contributions
Mic+0.153
Bet+0.152
umper+0.151
Nut+0.150
ross+0.140
Neg logit contributions
 look-0.092
 swim-0.089
 search-0.087
 drive-0.085
 walk-0.085
Token seen
Token ID1775
Feature activation+3.81e-02

Pos logit contributions
ross+0.028
Bet+0.026
umper+0.026
inger+0.026
Nut+0.025
Neg logit contributions
 dip-0.047
 sip-0.047
 swim-0.046
 splash-0.044
 popcorn-0.044
Token and
Token ID290
Feature activation+7.47e-03

Pos logit contributions
Bet+0.077
inger+0.076
Nut+0.074
ross+0.074
umper+0.073
Neg logit contributions
 popcorn-0.041
 movie-0.039
 dip-0.039
 swim-0.038
 sip-0.037
Token it
Token ID340
Feature activation-3.77e-04

Pos logit contributions
ross+0.013
umper+0.012
inger+0.012
Bet+0.012
Nut+0.012
Neg logit contributions
 dip-0.011
 sip-0.011
 swim-0.011
 splash-0.010
 popcorn-0.010
Token looked
Token ID3114
Feature activation+6.33e-03

Pos logit contributions
 dip+0.001
 sip+0.001
 swim+0.001
 splash+0.000
 movie+0.000
Neg logit contributions
ross-0.001
umper-0.001
inger-0.001
Bet-0.001
Nut-0.001
Token the
Token ID262
Feature activation+3.43e-02

Pos logit contributions
ross+0.028
umper+0.028
inger+0.027
Bet+0.026
enna+0.026
Neg logit contributions
 dip-0.013
 sip-0.013
 swim-0.013
 look-0.013
 popcorn-0.012
Token most
Token ID749
Feature activation+3.48e-02

Pos logit contributions
ross+0.072
Bet+0.067
umper+0.066
inger+0.066
ydia+0.064
Neg logit contributions
 dip-0.041
 swim-0.038
 look-0.038
 sip-0.036
 nap-0.036
Token beautiful
Token ID4950
Feature activation+2.65e-02

Pos logit contributions
ross+0.063
Bet+0.060
umper+0.060
inger+0.059
Nut+0.059
Neg logit contributions
 sip-0.045
 dip-0.045
 swim-0.043
 splash-0.042
 popcorn-0.041
Token thing
Token ID1517
Feature activation+2.14e-02

Pos logit contributions
ross+0.043
Bet+0.041
umper+0.041
inger+0.040
Nut+0.039
Neg logit contributions
 sip-0.040
 dip-0.039
 swim-0.038
 splash-0.037
 popcorn-0.037
Token she
Token ID673
Feature activation+4.30e-02

Pos logit contributions
ross+0.033
umper+0.033
inger+0.032
Bet+0.031
Nut+0.031
Neg logit contributions
 sip-0.034
 dip-0.034
 swim-0.033
 splash-0.032
 popcorn-0.032
Token had
Token ID550
Feature activation+7.68e-02

Pos logit contributions
ross+0.084
Bet+0.083
inger+0.082
Nut+0.077
ooks+0.074
Neg logit contributions
 look-0.058
 dip-0.054
 swim-0.054
 looks-0.054
 search-0.053
Token ever
Token ID1683
Feature activation+2.73e-02

Pos logit contributions
Bet+0.152
Nut+0.148
Mic+0.146
umper+0.145
ross+0.141
Neg logit contributions
 look-0.094
 search-0.094
 swim-0.090
 dip-0.089
 wait-0.085
Token seen
Token ID1775
Feature activation+5.00e-02

Pos logit contributions
ross+0.030
Bet+0.028
umper+0.028
inger+0.027
Nut+0.026
Neg logit contributions
 sip-0.055
 dip-0.055
 swim-0.053
 splash-0.052
 popcorn-0.052
Token!
Token ID0
Feature activation+2.18e-03

Pos logit contributions
Bet+0.112
inger+0.110
Nut+0.109
ross+0.109
umper+0.107
Neg logit contributions
 popcorn-0.041
 dip-0.040
 sip-0.040
 nap-0.038
 look-0.038
Token She
Token ID1375
Feature activation+2.63e-02

Pos logit contributions
ross+0.004
umper+0.004
inger+0.004
Bet+0.004
ich+0.004
Neg logit contributions
 sip-0.003
 dip-0.003
 look-0.003
 splash-0.003
 swim-0.003
Token put
Token ID1234
Feature activation+1.56e-02

Pos logit contributions
ross+0.052
inger+0.050
Bet+0.049
umper+0.048
Nut+0.046
Neg logit contributions
 swim-0.036
 dip-0.034
 sip-0.033
 splash-0.033
 looks-0.032
Token it
Token ID340
Feature activation+6.99e-03

Pos logit contributions
ross+0.022
inger+0.022
umper+0.022
Bet+0.021
Nut+0.021
Neg logit contributions
 sip-0.011
 dip-0.010
 swim-0.010
 look-0.010
 splash-0.010
Token was
Token ID373
Feature activation+1.65e-02

Pos logit contributions
ross+0.011
umper+0.011
Bet+0.010
inger+0.010
Nut+0.010
Neg logit contributions
 sip-0.011
 dip-0.011
 swim-0.010
 splash-0.010
 movie-0.010
Token not
Token ID407
Feature activation+2.86e-02

Pos logit contributions
umper+0.038
ross+0.038
ase+0.037
emaker+0.036
rows+0.036
Neg logit contributions
 look-0.016
 dip-0.015
 swim-0.014
 sip-0.014
 ice-0.014
Token safe
Token ID3338
Feature activation+3.30e-02

Pos logit contributions
ross+0.057
Bet+0.055
umper+0.054
inger+0.053
Nut+0.052
Neg logit contributions
 dip-0.033
 look-0.032
 swim-0.032
 sip-0.031
 popcorn-0.030
Token to
Token ID284
Feature activation+2.46e-02

Pos logit contributions
ross+0.057
umper+0.055
Bet+0.055
inger+0.054
Nut+0.053
Neg logit contributions
 sip-0.046
 dip-0.045
 swim-0.044
 splash-0.043
 look-0.042
Token play
Token ID711
Feature activation+7.66e-02

Pos logit contributions
ross+0.053
Bet+0.051
umper+0.051
inger+0.050
Nut+0.049
Neg logit contributions
 sip-0.024
 dip-0.024
 swim-0.023
 splash-0.022
 popcorn-0.021
Token with
Token ID351
Feature activation+4.06e-02

Pos logit contributions
ross+0.153
inger+0.149
umper+0.148
Bet+0.147
enna+0.144
Neg logit contributions
 swim-0.092
 sip-0.089
 look-0.089
 dip-0.087
 splash-0.086
Token chains
Token ID14659
Feature activation+6.56e-02

Pos logit contributions
ross+0.090
inger+0.085
Bet+0.084
umper+0.084
amed+0.080
Neg logit contributions
 sip-0.043
 dip-0.042
 swim-0.042
 look-0.041
 popcorn-0.039
Token and
Token ID290
Feature activation+2.37e-02

Pos logit contributions
ross+0.143
Bet+0.142
inger+0.139
umper+0.137
Wal+0.135
Neg logit contributions
 dip-0.060
 sip-0.059
 swim-0.058
 look-0.057
 popcorn-0.054
Token took
Token ID1718
Feature activation+9.09e-03

Pos logit contributions
ross+0.043
umper+0.042
inger+0.041
Bet+0.041
Nut+0.039
Neg logit contributions
 dip-0.033
 sip-0.032
 swim-0.032
 splash-0.031
 look-0.030
Token it
Token ID340
Feature activation+2.82e-03

Pos logit contributions
ross+0.017
Bet+0.016
umper+0.016
inger+0.016
Nut+0.016
Neg logit contributions
 sip-0.011
 dip-0.011
 swim-0.011
 splash-0.011
 popcorn-0.010
Token neck
Token ID7393
Feature activation+6.47e-02

Pos logit contributions
 dip+0.025
 sip+0.025
 movie+0.024
 popcorn+0.023
 swim+0.023
Neg logit contributions
ross-0.059
Bet-0.057
umper-0.056
Nut-0.055
inger-0.054
Tokenl
Token ID75
Feature activation+5.15e-02

Pos logit contributions
Bet+0.128
ross+0.127
umper+0.125
ydia+0.123
Mic+0.122
Neg logit contributions
 dip-0.077
 swim-0.075
 sip-0.071
 look-0.069
 popcorn-0.068
Tokenaces
Token ID2114
Feature activation+8.84e-02

Pos logit contributions
Bet+0.096
ross+0.090
Nut+0.088
ydia+0.088
illian+0.087
Neg logit contributions
 swim-0.066
 dip-0.064
 sip-0.060
 popcorn-0.059
 look-0.059
Token,
Token ID11
Feature activation+3.62e-02

Pos logit contributions
Bet+0.181
ross+0.176
ydia+0.168
umper+0.167
Kelly+0.167
Neg logit contributions
 dip-0.100
 look-0.094
 swim-0.094
 sip-0.086
 drive-0.084
Token grape
Token ID30777
Feature activation+1.46e-02

Pos logit contributions
ross+0.067
inger+0.064
umper+0.063
Bet+0.061
ydia+0.060
Neg logit contributions
 dip-0.052
 swim-0.051
 sip-0.050
 splash-0.049
 look-0.048
Token brace
Token ID22581
Feature activation+7.65e-02

Pos logit contributions
ross+0.029
umper+0.028
inger+0.028
Bet+0.027
Nut+0.027
Neg logit contributions
 sip-0.018
 swim-0.017
 dip-0.017
 popcorn-0.016
 splash-0.016
Tokenlets
Token ID5289
Feature activation+4.28e-02

Pos logit contributions
ross+0.138
Bet+0.135
umper+0.131
Kelly+0.129
illian+0.128
Neg logit contributions
 dip-0.095
 swim-0.089
 sip-0.089
 look-0.087
 splash-0.082
Token,
Token ID11
Feature activation+5.11e-02

Pos logit contributions
Bet+0.088
ross+0.087
umper+0.087
Nut+0.086
Mic+0.085
Neg logit contributions
 dip-0.047
 swim-0.045
 sip-0.044
 look-0.043
 popcorn-0.042
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
ross+0.122
umper+0.114
inger+0.113
Bet+0.111
illian+0.108
Neg logit contributions
 dip-0.050
 swim-0.046
 sip-0.045
 look-0.044
 popcorn-0.043
Token grape
Token ID30777
Feature activation+1.79e-02

Pos logit contributions
ross+0.029
umper+0.028
inger+0.028
Bet+0.028
Nut+0.027
Neg logit contributions
 dip-0.020
 sip-0.020
 swim-0.020
 splash-0.019
 popcorn-0.018
Token crown
Token ID12389
Feature activation+4.05e-02

Pos logit contributions
ross+0.035
umper+0.033
Bet+0.033
inger+0.033
Nut+0.032
Neg logit contributions
 sip-0.022
 dip-0.022
 swim-0.022
 popcorn-0.020
 splash-0.020
Token.
Token ID13
Feature activation+3.18e-02

Pos logit contributions
ross+0.057
Bet+0.056
inger+0.055
umper+0.054
ydia+0.053
Neg logit contributions
 swim-0.034
 sip-0.032
 dip-0.032
 popcorn-0.031
 splash-0.031
Token He
Token ID679
Feature activation+2.34e-02

Pos logit contributions
ross+0.067
inger+0.062
ydia+0.059
umper+0.059
enna+0.058
Neg logit contributions
 swim-0.032
 drive-0.032
 search-0.032
 dip-0.032
 Today-0.031
Token knew
Token ID2993
Feature activation+4.26e-02

Pos logit contributions
ross+0.042
inger+0.040
Bet+0.039
ooks+0.039
umper+0.039
Neg logit contributions
 swim-0.034
 sip-0.033
 tug-0.032
 dip-0.031
 sigh-0.031
Token that
Token ID326
Feature activation+1.55e-02

Pos logit contributions
inger+0.096
amed+0.093
Bet+0.092
ross+0.091
ase+0.090
Neg logit contributions
 swim-0.041
 drive-0.037
 ice-0.037
 popcorn-0.037
 dip-0.036
Token the
Token ID262
Feature activation+5.00e-02

Pos logit contributions
ross+0.028
inger+0.028
Bet+0.026
umper+0.026
amed+0.026
Neg logit contributions
 swim-0.021
 dip-0.020
 sip-0.020
 popcorn-0.020
 splash-0.019
Token ac
Token ID936
Feature activation+7.63e-02

Pos logit contributions
ross+0.091
Bet+0.085
umper+0.083
inger+0.083
enna+0.081
Neg logit contributions
 dip-0.066
 swim-0.065
 sip-0.064
 popcorn-0.061
 look-0.061
Tokenorn
Token ID1211
Feature activation+3.59e-02

Pos logit contributions
ross+0.104
ooks+0.104
enna+0.097
Kelly+0.095
Jud+0.092
Neg logit contributions
 treat-0.117
 looks-0.111
 snack-0.110
 bite-0.109
 ice-0.107
Token was
Token ID373
Feature activation+1.71e-02

Pos logit contributions
ross+0.064
Bet+0.064
umper+0.061
ooks+0.061
inger+0.060
Neg logit contributions
 swim-0.051
 looks-0.048
 dip-0.047
 sip-0.047
 look-0.046
Token a
Token ID257
Feature activation+3.35e-02

Pos logit contributions
ross+0.029
Bet+0.029
umper+0.029
inger+0.028
Nut+0.027
Neg logit contributions
 dip-0.023
 sip-0.023
 swim-0.023
 popcorn-0.022
 splash-0.021
Token special
Token ID2041
Feature activation+3.21e-02

Pos logit contributions
ross+0.067
umper+0.065
inger+0.064
Bet+0.063
ydia+0.061
Neg logit contributions
 sip-0.039
 dip-0.039
 swim-0.038
 splash-0.036
 movie-0.036
Token gift
Token ID6979
Feature activation+4.39e-02

Pos logit contributions
ross+0.059
Bet+0.056
umper+0.056
inger+0.055
Nut+0.054
Neg logit contributions
 sip-0.041
 dip-0.041
 swim-0.039
 splash-0.038
 popcorn-0.037
Token the
Token ID262
Feature activation+2.81e-02

Pos logit contributions
umper+0.021
ross+0.020
Bet+0.020
inger+0.020
orns+0.019
Neg logit contributions
 dip-0.010
 look-0.010
 swim-0.009
 popcorn-0.009
 sip-0.009
Token most
Token ID749
Feature activation+3.16e-02

Pos logit contributions
ross+0.061
umper+0.059
Bet+0.057
inger+0.055
Nut+0.054
Neg logit contributions
 dip-0.032
 look-0.031
 swim-0.029
 picnic-0.029
 popcorn-0.028
Token fancy
Token ID14996
Feature activation+3.56e-02

Pos logit contributions
ross+0.058
Bet+0.055
umper+0.055
inger+0.054
Nut+0.053
Neg logit contributions
 sip-0.041
 dip-0.041
 swim-0.039
 splash-0.038
 popcorn-0.037
Token frame
Token ID5739
Feature activation+3.96e-02

Pos logit contributions
ross+0.047
umper+0.046
Bet+0.045
Nut+0.044
inger+0.043
Neg logit contributions
 sip-0.066
 dip-0.065
 swim-0.063
 movie-0.062
 splash-0.062
Token he
Token ID339
Feature activation+3.80e-02

Pos logit contributions
ross+0.071
Bet+0.070
umper+0.069
inger+0.069
Nut+0.068
Neg logit contributions
 dip-0.052
 swim-0.051
 sip-0.051
 movie-0.049
 popcorn-0.049
Token had
Token ID550
Feature activation+7.63e-02

Pos logit contributions
Bet+0.084
inger+0.082
ross+0.082
ooks+0.078
Nut+0.078
Neg logit contributions
 look-0.042
 swim-0.040
 looks-0.039
 search-0.039
 drive-0.037
Token ever
Token ID1683
Feature activation+2.06e-02

Pos logit contributions
Bet+0.161
Nut+0.153
Mic+0.153
umper+0.151
ross+0.141
Neg logit contributions
 look-0.091
 swim-0.085
 search-0.085
 drive-0.084
 dip-0.083
Token seen
Token ID1775
Feature activation+4.00e-02

Pos logit contributions
ross+0.026
Bet+0.025
umper+0.024
inger+0.024
Nut+0.024
Neg logit contributions
 dip-0.039
 sip-0.038
 swim-0.037
 popcorn-0.036
 splash-0.036
Token!
Token ID0
Feature activation+7.29e-03

Pos logit contributions
Bet+0.090
inger+0.087
Nut+0.086
ross+0.085
umper+0.084
Neg logit contributions
 popcorn-0.036
 movie-0.034
 dip-0.033
 sip-0.032
 swim-0.032
Token He
Token ID679
Feature activation+2.85e-02

Pos logit contributions
ross+0.013
umper+0.012
Bet+0.012
inger+0.012
Nut+0.011
Neg logit contributions
 dip-0.010
 sip-0.010
 swim-0.010
 splash-0.010
 movie-0.009
Token wanted
Token ID2227
Feature activation+4.37e-03

Pos logit contributions
ross+0.055
umper+0.052
inger+0.052
Bet+0.051
orns+0.050
Neg logit contributions
 swim-0.038
 dip-0.036
 sip-0.036
 splash-0.035
 tug-0.034
Token.
Token ID13
Feature activation+2.97e-02

Pos logit contributions
 argue+0.045
 sip+0.045
 dip+0.045
 swim+0.043
 tug+0.043
Neg logit contributions
ross-0.023
 knowing-0.022
orns-0.019
but-0.019
ina-0.018
Token Polly
Token ID36898
Feature activation-3.77e-03

Pos logit contributions
ross+0.053
ich+0.050
umper+0.049
ppa+0.048
igi+0.048
Neg logit contributions
 sip-0.043
 dip-0.041
 look-0.041
 looks-0.040
 Today-0.040
Token happily
Token ID18177
Feature activation-4.41e-03

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.006
 splash+0.006
 popcorn+0.005
Neg logit contributions
ross-0.006
Bet-0.006
umper-0.005
inger-0.005
Nut-0.005
Token got
Token ID1392
Feature activation-3.21e-02

Pos logit contributions
 sip+0.007
 dip+0.007
 movie+0.007
 popcorn+0.007
 swim+0.006
Neg logit contributions
ross-0.006
Bet-0.006
umper-0.006
inger-0.006
Nut-0.006
Token a
Token ID257
Feature activation-7.29e-02

Pos logit contributions
 sip+0.051
 dip+0.051
 swim+0.049
 movie+0.048
 splash+0.048
Neg logit contributions
ross-0.045
umper-0.044
Bet-0.044
inger-0.042
Nut-0.042
Token big
Token ID1263
Feature activation-9.54e-02

Pos logit contributions
 argue+0.114
itionally+0.104
 Today+0.099
 search+0.096
rd+0.096
Neg logit contributions
eh-0.078
ich-0.067
 knowing-0.067
un-0.067
Wal-0.066
Token bucket
Token ID19236
Feature activation-1.82e-02

Pos logit contributions
itionally+0.124
rd+0.095
 argue+0.095
 seem+0.090
ksh+0.088
Neg logit contributions
 and-0.125
 knowing-0.122
 mag-0.110
 worth-0.108
eh-0.107
Token full
Token ID1336
Feature activation-1.39e-02

Pos logit contributions
 sip+0.035
 dip+0.035
 swim+0.034
 splash+0.033
 movie+0.033
Neg logit contributions
ross-0.021
Bet-0.020
umper-0.020
inger-0.019
Nut-0.019
Token of
Token ID286
Feature activation-4.34e-02

Pos logit contributions
 sip+0.028
 dip+0.028
 swim+0.027
 splash+0.026
 movie+0.026
Neg logit contributions
ross-0.015
umper-0.014
Bet-0.014
inger-0.013
Nut-0.013
Token popcorn
Token ID38914
Feature activation-4.05e-02

Pos logit contributions
 argue+0.041
 Today+0.035
 sip+0.034
 search+0.032
 dive+0.031
Neg logit contributions
Now-0.074
orns-0.073
 knowing-0.072
iring-0.070
umper-0.070
Token.
Token ID13
Feature activation+1.76e-02

Pos logit contributions
 sip+0.073
 dip+0.071
 argue+0.069
 sigh+0.068
 swim+0.068
Neg logit contributions
ross-0.047
inger-0.042
ich-0.040
but-0.040
Bet-0.039
Token dad
Token ID9955
Feature activation-5.98e-02

Pos logit contributions
 sip+0.049
 dip+0.049
 swim+0.047
 splash+0.046
 popcorn+0.046
Neg logit contributions
ross-0.055
Bet-0.052
umper-0.052
inger-0.051
Nut-0.051
Token.
Token ID13
Feature activation-2.85e-02

Pos logit contributions
 sip+0.093
 dip+0.091
 swim+0.085
 splash+0.085
 sigh+0.083
Neg logit contributions
ross-0.086
umper-0.083
Bet-0.079
inger-0.078
ully-0.075
Token They
Token ID1119
Feature activation-4.42e-02

Pos logit contributions
 dip+0.039
 dive+0.038
 swim+0.038
 sigh+0.038
 sip+0.037
Neg logit contributions
Bet-0.041
Nut-0.039
ydia-0.039
Mic-0.038
ross-0.037
Token have
Token ID423
Feature activation-3.75e-02

Pos logit contributions
 sip+0.060
 dip+0.059
 swim+0.057
 splash+0.055
 popcorn+0.055
Neg logit contributions
ross-0.077
Bet-0.073
umper-0.073
inger-0.072
Nut-0.071
Token a
Token ID257
Feature activation-6.47e-02

Pos logit contributions
 sip+0.056
 dip+0.054
 swim+0.052
 splash+0.051
 sigh+0.049
Neg logit contributions
ross-0.059
Bet-0.057
umper-0.056
inger-0.055
Nut-0.054
Token big
Token ID1263
Feature activation-9.20e-02

Pos logit contributions
 dip+0.101
 argue+0.100
 sip+0.098
 reel+0.096
 anticipation+0.095
Neg logit contributions
eh-0.069
ich-0.066
Bet-0.066
Kelly-0.063
Op-0.062
Token TV
Token ID3195
Feature activation-3.78e-02

Pos logit contributions
 dip+0.108
 sip+0.104
 reel+0.102
itionally+0.101
 argue+0.097
Neg logit contributions
eh-0.127
ase-0.125
Bet-0.121
 named-0.121
ich-0.118
Token in
Token ID287
Feature activation-3.03e-02

Pos logit contributions
 sip+0.062
 dip+0.062
 swim+0.059
 splash+0.057
 popcorn+0.056
Neg logit contributions
ross-0.054
Bet-0.050
umper-0.049
inger-0.049
Nut-0.048
Token the
Token ID262
Feature activation-4.43e-02

Pos logit contributions
 sip+0.045
 dip+0.045
 swim+0.043
 splash+0.042
 sigh+0.041
Neg logit contributions
ross-0.045
Bet-0.044
inger-0.043
ydia-0.043
umper-0.042
Token living
Token ID2877
Feature activation-2.38e-02

Pos logit contributions
 dip+0.075
 sip+0.075
 swim+0.071
 argue+0.069
 splash+0.069
Neg logit contributions
ross-0.057
umper-0.053
Bet-0.053
ase-0.052
inger-0.051
Token room
Token ID2119
Feature activation-1.38e-02

Pos logit contributions
 sip+0.035
 dip+0.035
 swim+0.033
 splash+0.032
 popcorn+0.031
Neg logit contributions
ross-0.038
umper-0.036
inger-0.036
Bet-0.036
ydia-0.034
Token yes
Token ID3763
Feature activation+1.05e-02

Pos logit contributions
 sip+0.002
 dip+0.002
 swim+0.002
 splash+0.002
 movie+0.002
Neg logit contributions
ross-0.002
Bet-0.002
umper-0.002
inger-0.002
Nut-0.002
Token and
Token ID290
Feature activation+5.10e-03

Pos logit contributions
ross+0.016
Bet+0.016
umper+0.016
inger+0.015
Nut+0.015
Neg logit contributions
 sip-0.016
 dip-0.016
 swim-0.016
 splash-0.015
 popcorn-0.015
Token gave
Token ID2921
Feature activation-1.17e-02

Pos logit contributions
ross+0.010
inger+0.009
umper+0.009
Bet+0.009
Nut+0.009
Neg logit contributions
 sip-0.006
 dip-0.006
 swim-0.006
 splash-0.006
 popcorn-0.006
Token him
Token ID683
Feature activation-4.03e-02

Pos logit contributions
 sip+0.017
 dip+0.017
 swim+0.016
 splash+0.016
 popcorn+0.016
Neg logit contributions
ross-0.020
Bet-0.019
umper-0.019
inger-0.018
Nut-0.018
Token a
Token ID257
Feature activation-7.77e-02

Pos logit contributions
 dip+0.061
 sip+0.060
 splash+0.059
 argue+0.058
 swim+0.058
Neg logit contributions
ross-0.055
umper-0.054
Bet-0.052
Nut-0.051
eh-0.051
Token big
Token ID1263
Feature activation-8.97e-02

Pos logit contributions
 argue+0.119
itionally+0.108
 search+0.106
 dip+0.105
 swim+0.103
Neg logit contributions
eh-0.086
illian-0.079
odi-0.078
 known-0.076
inger-0.075
Token bowl
Token ID9396
Feature activation-1.25e-02

Pos logit contributions
itionally+0.121
 argue+0.099
 seem+0.097
 search+0.093
 dip+0.092
Neg logit contributions
ase-0.112
eh-0.110
ross-0.107
aver-0.104
inger-0.103
Token of
Token ID286
Feature activation-5.26e-02

Pos logit contributions
 sip+0.022
 dip+0.022
 swim+0.021
 splash+0.020
 popcorn+0.020
Neg logit contributions
ross-0.017
Bet-0.016
umper-0.016
inger-0.016
Nut-0.015
Token beautiful
Token ID4950
Feature activation-7.85e-02

Pos logit contributions
 argue+0.057
itionally+0.049
 Today+0.047
 search+0.046
 sigh+0.045
Neg logit contributions
Now-0.082
orns-0.078
eh-0.076
umper-0.074
 its-0.074
Token,
Token ID11
Feature activation+1.33e-02

Pos logit contributions
 argue+0.102
itionally+0.094
 whine+0.088
 blame+0.087
 sigh+0.087
Neg logit contributions
orns-0.109
eh-0.109
ase-0.103
 and-0.101
rows-0.099
Token y
Token ID331
Feature activation-4.64e-02

Pos logit contributions
ross+0.026
umper+0.025
Bet+0.025
inger+0.025
Nut+0.024
Neg logit contributions
 sip-0.015
 dip-0.015
 swim-0.014
 splash-0.014
 popcorn-0.014
Token the
Token ID262
Feature activation-1.12e-02

Pos logit contributions
 sip+0.018
 dip+0.018
 movie+0.017
 splash+0.017
 swim+0.017
Neg logit contributions
Bet-0.009
Nut-0.008
umper-0.008
Op-0.008
ydia-0.008
Token store
Token ID3650
Feature activation+1.50e-03

Pos logit contributions
 sip+0.020
 dip+0.020
 swim+0.019
 splash+0.019
 dive+0.018
Neg logit contributions
ross-0.013
Nut-0.012
Bet-0.012
Op-0.012
umper-0.012
Token and
Token ID290
Feature activation-1.49e-02

Pos logit contributions
ross+0.002
Bet+0.002
umper+0.002
inger+0.002
Nut+0.002
Neg logit contributions
 sip-0.003
 dip-0.003
 swim-0.002
 splash-0.002
 popcorn-0.002
Token bought
Token ID5839
Feature activation-3.88e-02

Pos logit contributions
 sip+0.025
 dip+0.025
 movie+0.024
 swim+0.024
 popcorn+0.024
Neg logit contributions
Bet-0.019
ross-0.019
umper-0.018
Nut-0.018
ydia-0.017
Token a
Token ID257
Feature activation-7.18e-02

Pos logit contributions
 dip+0.066
 sip+0.065
 argue+0.064
 splash+0.064
 dive+0.064
Neg logit contributions
 known-0.040
Nut-0.040
umper-0.039
ily-0.039
 Pip-0.038
Token big
Token ID1263
Feature activation-8.90e-02

Pos logit contributions
 argue+0.113
 breaths+0.104
 seem+0.100
 search+0.100
 anticipation+0.099
Neg logit contributions
ich-0.068
eh-0.067
 knowing-0.067
 accidentally-0.065
Prin-0.062
Token bag
Token ID6131
Feature activation-3.58e-03

Pos logit contributions
itionally+0.123
 seem+0.119
 argue+0.109
ksh+0.107
rd+0.102
Neg logit contributions
 and-0.101
 knowing-0.092
ase-0.091
 named-0.087
eh-0.085
Token of
Token ID286
Feature activation-4.38e-02

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.006
 splash+0.006
 popcorn+0.006
Neg logit contributions
ross-0.005
Bet-0.005
umper-0.005
inger-0.005
Nut-0.005
Token popcorn
Token ID38914
Feature activation-3.79e-02

Pos logit contributions
 argue+0.044
 Today+0.037
 sip+0.037
 dive+0.036
 search+0.036
Neg logit contributions
orns-0.071
Now-0.071
Nut-0.069
umper-0.068
 knowing-0.067
Token.
Token ID13
Feature activation-8.87e-03

Pos logit contributions
 sip+0.057
 dip+0.056
 swim+0.054
 splash+0.053
 sigh+0.052
Neg logit contributions
ross-0.057
inger-0.053
umper-0.052
Bet-0.051
Nut-0.050
Token When
Token ID1649
Feature activation-1.36e-02

Pos logit contributions
 sip+0.014
 dip+0.014
 swim+0.014
 popcorn+0.013
 movie+0.013
Neg logit contributions
ross-0.013
Bet-0.013
umper-0.012
Nut-0.012
inger-0.012
Token and
Token ID290
Feature activation-8.64e-04

Pos logit contributions
 sip+0.029
 dip+0.028
 swim+0.027
 splash+0.027
 popcorn+0.026
Neg logit contributions
ross-0.016
Bet-0.014
umper-0.014
inger-0.014
ully-0.014
Token quickly
Token ID2952
Feature activation-1.62e-02

Pos logit contributions
 dip+0.001
 sip+0.001
 swim+0.001
 splash+0.001
 popcorn+0.001
Neg logit contributions
ross-0.002
umper-0.001
Bet-0.001
inger-0.001
Nut-0.001
Token ran
Token ID4966
Feature activation-2.89e-02

Pos logit contributions
 sip+0.025
 dip+0.024
 movie+0.024
 swim+0.024
 popcorn+0.023
Neg logit contributions
ross-0.025
Bet-0.023
umper-0.023
inger-0.023
Nut-0.022
Token to
Token ID284
Feature activation-2.10e-02

Pos logit contributions
 sip+0.054
 dip+0.054
 movie+0.053
 swim+0.052
 splash+0.051
Neg logit contributions
ross-0.032
Bet-0.031
inger-0.030
umper-0.030
ydia-0.030
Token get
Token ID651
Feature activation-5.91e-02

Pos logit contributions
 dip+0.037
 sip+0.037
 movie+0.037
 popcorn+0.036
 swim+0.036
Neg logit contributions
Bet-0.023
ross-0.023
umper-0.023
ydia-0.022
illian-0.022
Token a
Token ID257
Feature activation-8.66e-02

Pos logit contributions
 sip+0.096
 sigh+0.095
 movie+0.095
 splash+0.092
 swim+0.092
Neg logit contributions
 known-0.070
umper-0.069
illian-0.067
amed-0.062
ydia-0.061
Token bowl
Token ID9396
Feature activation-1.59e-02

Pos logit contributions
 argue+0.129
rd+0.119
 Today+0.117
itionally+0.113
 anticipation+0.113
Neg logit contributions
eh-0.097
 accidentally-0.088
illian-0.086
ich-0.083
odi-0.082
Token for
Token ID329
Feature activation-2.02e-02

Pos logit contributions
 sip+0.026
 dip+0.026
 swim+0.025
 movie+0.025
 popcorn+0.024
Neg logit contributions
ross-0.023
umper-0.021
Bet-0.021
inger-0.021
Nut-0.020
Token the
Token ID262
Feature activation-6.65e-02

Pos logit contributions
 dip+0.029
 sip+0.028
 swim+0.027
 splash+0.027
 looks+0.026
Neg logit contributions
ross-0.029
Bet-0.029
illian-0.028
Nut-0.027
umper-0.027
Token popcorn
Token ID38914
Feature activation-3.14e-02

Pos logit contributions
 sip+0.076
 argue+0.068
 swim+0.066
 sigh+0.064
itionally+0.064
Neg logit contributions
 known-0.093
ich-0.092
ross-0.091
 always-0.090
but-0.090
Token.
Token ID13
Feature activation-1.77e-02

Pos logit contributions
 sip+0.043
 dip+0.042
 swim+0.040
 splash+0.039
 movie+0.039
Neg logit contributions
ross-0.053
Bet-0.050
inger-0.050
umper-0.050
Nut-0.049
Token bowl
Token ID9396
Feature activation-1.25e-02

Pos logit contributions
itionally+0.121
 argue+0.099
 seem+0.097
 search+0.093
 dip+0.092
Neg logit contributions
ase-0.112
eh-0.110
ross-0.107
aver-0.104
inger-0.103
Token of
Token ID286
Feature activation-5.26e-02

Pos logit contributions
 sip+0.022
 dip+0.022
 swim+0.021
 splash+0.020
 popcorn+0.020
Neg logit contributions
ross-0.017
Bet-0.016
umper-0.016
inger-0.016
Nut-0.015
Token beautiful
Token ID4950
Feature activation-7.85e-02

Pos logit contributions
 argue+0.057
itionally+0.049
 Today+0.047
 search+0.046
 sigh+0.045
Neg logit contributions
Now-0.082
orns-0.078
eh-0.076
umper-0.074
 its-0.074
Token,
Token ID11
Feature activation+1.33e-02

Pos logit contributions
 argue+0.102
itionally+0.094
 whine+0.088
 blame+0.087
 sigh+0.087
Neg logit contributions
orns-0.109
eh-0.109
ase-0.103
 and-0.101
rows-0.099
Token y
Token ID331
Feature activation-4.64e-02

Pos logit contributions
ross+0.026
umper+0.025
Bet+0.025
inger+0.025
Nut+0.024
Neg logit contributions
 sip-0.015
 dip-0.015
 swim-0.014
 splash-0.014
 popcorn-0.014
Tokenummy
Token ID13513
Feature activation-8.54e-02

Pos logit contributions
 argue+0.104
 drive+0.101
 swim+0.101
 dip+0.101
 sip+0.101
Neg logit contributions
ross-0.036
umper-0.030
umbled-0.029
orns-0.028
illy-0.028
Token popcorn
Token ID38914
Feature activation-3.97e-02

Pos logit contributions
itionally+0.135
 argue+0.124
arse+0.103
 whine+0.102
 Today+0.101
Neg logit contributions
 and-0.110
 knowing-0.104
 of-0.102
eh-0.094
ase-0.093
Token.
Token ID13
Feature activation-8.73e-03

Pos logit contributions
 sip+0.057
 dip+0.057
 swim+0.054
 splash+0.053
 movie+0.052
Neg logit contributions
ross-0.063
inger-0.058
Bet-0.057
umper-0.057
Nut-0.056
Token Tim
Token ID5045
Feature activation+5.84e-03

Pos logit contributions
 dip+0.015
 sip+0.015
 swim+0.014
 movie+0.014
 popcorn+0.014
Neg logit contributions
ross-0.012
Bet-0.012
Nut-0.011
umper-0.011
inger-0.011
Tokenmy
Token ID1820
Feature activation-9.04e-03

Pos logit contributions
ross+0.011
Bet+0.010
Nut+0.010
inger+0.010
ydia+0.010
Neg logit contributions
 sip-0.007
 dip-0.007
 swim-0.007
 movie-0.007
 looks-0.006
Token was
Token ID373
Feature activation-9.85e-03

Pos logit contributions
 sip+0.014
 dip+0.014
 swim+0.014
 splash+0.013
 popcorn+0.013
Neg logit contributions
ross-0.014
Bet-0.014
umper-0.013
inger-0.013
Nut-0.013
Token served
Token ID4983
Feature activation-3.10e-02

Pos logit contributions
 sip+0.037
 dip+0.037
 swim+0.035
 splash+0.034
 movie+0.033
Neg logit contributions
ross-0.053
Bet-0.051
umper-0.050
Nut-0.049
inger-0.049
Token it
Token ID340
Feature activation-5.67e-02

Pos logit contributions
 sip+0.046
 dip+0.046
 swim+0.045
 splash+0.044
 sigh+0.043
Neg logit contributions
ross-0.046
umper-0.043
Bet-0.043
inger-0.041
Nut-0.041
Token with
Token ID351
Feature activation-2.89e-02

Pos logit contributions
 dip+0.088
 sip+0.086
 sigh+0.084
 argue+0.083
 splash+0.083
Neg logit contributions
ross-0.075
Bet-0.069
inger-0.069
eh-0.067
amed-0.065
Token a
Token ID257
Feature activation-5.84e-02

Pos logit contributions
 sip+0.036
 dip+0.036
 swim+0.034
 splash+0.033
 sigh+0.032
Neg logit contributions
Bet-0.048
ross-0.048
umper-0.048
Nut-0.047
inger-0.045
Token y
Token ID331
Feature activation-5.46e-02

Pos logit contributions
 dip+0.075
 sip+0.073
 argue+0.072
 swim+0.071
 search+0.067
Neg logit contributions
Bet-0.086
ross-0.085
Mic-0.081
eh-0.081
Wal-0.080
Tokenummy
Token ID13513
Feature activation-8.45e-02

Pos logit contributions
 argue+0.118
 movie+0.114
 dip+0.113
 swim+0.113
 sip+0.113
Neg logit contributions
ross-0.044
inger-0.037
ooks-0.035
umper-0.034
umbled-0.031
Token sauce
Token ID10746
Feature activation-3.43e-02

Pos logit contributions
itionally+0.128
 argue+0.122
 whine+0.101
ksh+0.097
 First+0.094
Neg logit contributions
eh-0.122
ull-0.105
 knowing-0.104
ase-0.102
illy-0.100
Token.
Token ID13
Feature activation-2.54e-02

Pos logit contributions
 sip+0.044
 dip+0.044
 swim+0.042
 splash+0.041
 popcorn+0.040
Neg logit contributions
ross-0.062
Bet-0.059
umper-0.059
inger-0.058
Nut-0.058
Token
Token ID220
Feature activation+1.62e-02

Pos logit contributions
 dip+0.042
 sip+0.042
 swim+0.041
 splash+0.039
 popcorn+0.039
Neg logit contributions
ross-0.035
Bet-0.035
umper-0.034
Nut-0.033
inger-0.033
Token
Token ID198
Feature activation-7.90e-03

Pos logit contributions
ross+0.031
umper+0.029
Bet+0.028
Nut+0.028
inger+0.027
Neg logit contributions
 sip-0.020
 swim-0.020
 dip-0.020
 splash-0.019
 look-0.019
Token
Token ID198
Feature activation-8.31e-03

Pos logit contributions
 sip+0.011
 swim+0.011
 dip+0.011
 splash+0.010
 movie+0.010
Neg logit contributions
ross-0.015
umper-0.013
inger-0.013
Bet-0.013
ydia-0.012
Token named
Token ID3706
Feature activation-5.06e-03

Pos logit contributions
 sip+0.003
 dip+0.003
 swim+0.003
 splash+0.003
 looks+0.003
Neg logit contributions
ross-0.002
umper-0.002
inger-0.002
Nut-0.001
Bet-0.001
Token Amelia
Token ID49769
Feature activation-6.20e-03

Pos logit contributions
 sip+0.007
 dip+0.006
 swim+0.006
 look+0.006
 splash+0.006
Neg logit contributions
ross-0.009
umper-0.009
inger-0.009
Nut-0.008
Bet-0.008
Token put
Token ID1234
Feature activation-2.74e-02

Pos logit contributions
 swim+0.009
 sip+0.009
 dip+0.009
 splash+0.008
 popcorn+0.008
Neg logit contributions
ross-0.011
Bet-0.010
umper-0.010
Nut-0.010
inger-0.010
Token on
Token ID319
Feature activation-1.19e-02

Pos logit contributions
 dip+0.048
 sip+0.048
 swim+0.047
 splash+0.046
 movie+0.045
Neg logit contributions
ross-0.034
umper-0.033
Bet-0.033
inger-0.032
Nut-0.032
Token her
Token ID607
Feature activation-5.38e-02

Pos logit contributions
 sip+0.023
 dip+0.023
 swim+0.023
 splash+0.023
 dive+0.022
Neg logit contributions
Bet-0.011
ross-0.011
Nut-0.011
inger-0.010
ydia-0.010
Token special
Token ID2041
Feature activation-8.42e-02

Pos logit contributions
 sip+0.066
 argue+0.061
 dip+0.057
 splash+0.052
 sigh+0.051
Neg logit contributions
eh-0.084
ich-0.082
inger-0.076
aver-0.075
ppa-0.075
Token wrapping
Token ID27074
Feature activation-3.32e-02

Pos logit contributions
 argue+0.093
 sip+0.091
 seem+0.086
itionally+0.084
 dip+0.082
Neg logit contributions
eh-0.131
ase-0.116
aver-0.114
ich-0.111
amed-0.110
Token hat
Token ID6877
Feature activation+9.91e-03

Pos logit contributions
 sip+0.040
 dip+0.038
 swim+0.038
 splash+0.037
 sigh+0.035
Neg logit contributions
ross-0.058
inger-0.056
umper-0.056
Bet-0.055
Nut-0.054
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
ross+0.018
Bet+0.017
umper+0.017
Nut+0.017
inger+0.016
Neg logit contributions
 dip-0.013
 sip-0.013
 swim-0.013
 look-0.013
 popcorn-0.013
Token She
Token ID1375
Feature activation-7.39e-03

Pos logit contributions
 sip+0.020
 dip+0.019
 swim+0.019
 splash+0.019
 popcorn+0.018
Neg logit contributions
ross-0.012
Bet-0.011
inger-0.011
umper-0.011
Nut-0.011
Token took
Token ID1718
Feature activation-2.09e-02

Pos logit contributions
 dip+0.011
 swim+0.011
 sip+0.010
 popcorn+0.010
 splash+0.010
Neg logit contributions
ross-0.014
Bet-0.013
inger-0.013
umper-0.013
Nut-0.012
Token They
Token ID1119
Feature activation-4.92e-02

Pos logit contributions
 sip+0.065
 dip+0.062
 swim+0.060
 movie+0.059
 popcorn+0.058
Neg logit contributions
Bet-0.043
ross-0.041
umper-0.040
inger-0.040
ooks-0.040
Token both
Token ID1111
Feature activation-4.88e-02

Pos logit contributions
 sip+0.081
 dip+0.080
 swim+0.078
 movie+0.076
 popcorn+0.076
Neg logit contributions
ross-0.068
umper-0.065
Bet-0.065
inger-0.062
Nut-0.061
Token put
Token ID1234
Feature activation-4.98e-02

Pos logit contributions
 sip+0.083
 dip+0.081
 swim+0.079
 movie+0.077
 popcorn+0.077
Neg logit contributions
ross-0.064
umper-0.060
Bet-0.058
amed-0.057
inger-0.057
Token on
Token ID319
Feature activation-4.17e-02

Pos logit contributions
 sip+0.092
 dip+0.091
 swim+0.089
 splash+0.088
 argue+0.086
Neg logit contributions
amed-0.054
umper-0.049
ross-0.048
orns-0.047
illian-0.047
Token their
Token ID511
Feature activation-7.19e-02

Pos logit contributions
 sip+0.075
 dip+0.071
 splash+0.068
 swim+0.067
 sigh+0.067
Neg logit contributions
amed-0.036
 known-0.036
 never-0.035
Kelly-0.035
Bet-0.034
Token favorite
Token ID4004
Feature activation-8.35e-02

Pos logit contributions
 reel+0.098
 sip+0.097
 dip+0.095
 argue+0.093
 splash+0.089
Neg logit contributions
amed-0.093
eh-0.084
anya-0.080
ily-0.080
ydia-0.078
Token clothes
Token ID8242
Feature activation-1.13e-02

Pos logit contributions
 argue+0.117
 reel+0.112
ksh+0.108
 sip+0.108
itionally+0.107
Neg logit contributions
eh-0.102
amed-0.095
ase-0.094
ons-0.088
anya-0.086
Token and
Token ID290
Feature activation-3.96e-02

Pos logit contributions
 sip+0.022
 dip+0.022
 swim+0.021
 splash+0.021
 movie+0.020
Neg logit contributions
ross-0.013
umper-0.012
inger-0.012
Bet-0.012
Nut-0.011
Token headed
Token ID9153
Feature activation-4.87e-02

Pos logit contributions
 sip+0.058
 dip+0.055
 sigh+0.053
 swim+0.052
 argue+0.052
Neg logit contributions
ross-0.056
amed-0.053
Bet-0.052
ydia-0.052
umper-0.052
Token outside
Token ID2354
Feature activation-4.26e-02

Pos logit contributions
 sip+0.097
 dip+0.091
 argue+0.089
 movie+0.089
 sigh+0.088
Neg logit contributions
ross-0.041
amed-0.040
inger-0.038
umper-0.038
enna-0.038
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
 sip+0.080
 dip+0.076
 sigh+0.071
 popcorn+0.070
 swim+0.069
Neg logit contributions
ross-0.044
 knowing-0.042
but-0.041
ina-0.041
ooks-0.039
Token poured
Token ID19036
Feature activation-4.41e-02

Pos logit contributions
 sip+0.023
 dip+0.023
 swim+0.022
 splash+0.021
 popcorn+0.021
Neg logit contributions
ross-0.028
umper-0.027
Bet-0.027
inger-0.026
Nut-0.026
Token the
Token ID262
Feature activation-7.02e-02

Pos logit contributions
 dip+0.063
 swim+0.063
 sip+0.062
 movie+0.061
 drive+0.060
Neg logit contributions
ross-0.066
Bet-0.065
umper-0.064
Nut-0.061
inger-0.061
Token popcorn
Token ID38914
Feature activation-6.10e-02

Pos logit contributions
 argue+0.076
 search+0.059
 whine+0.059
 Today+0.057
 compromise+0.055
Neg logit contributions
eh-0.123
amed-0.123
pped-0.119
Now-0.118
ase-0.112
Token into
Token ID656
Feature activation-1.25e-02

Pos logit contributions
 dip+0.108
 sip+0.107
 swim+0.103
 movie+0.103
 splash+0.101
Neg logit contributions
ross-0.073
inger-0.067
Bet-0.066
umper-0.065
amed-0.062
Token a
Token ID257
Feature activation-6.76e-02

Pos logit contributions
 dip+0.020
 sip+0.019
 swim+0.019
 splash+0.019
 movie+0.018
Neg logit contributions
ross-0.018
Bet-0.018
umper-0.017
Nut-0.017
inger-0.017
Token big
Token ID1263
Feature activation-8.25e-02

Pos logit contributions
 argue+0.090
 dip+0.078
 search+0.077
 swim+0.075
 seem+0.075
Neg logit contributions
eh-0.101
Mic-0.088
Prin-0.088
Bet-0.088
ase-0.086
Token bowl
Token ID9396
Feature activation-1.79e-02

Pos logit contributions
itionally+0.105
 argue+0.101
 seem+0.095
 swim+0.089
 names+0.088
Neg logit contributions
eh-0.106
pped-0.102
ase-0.101
Bet-0.098
ross-0.097
Token and
Token ID290
Feature activation-3.28e-02

Pos logit contributions
 sip+0.031
 dip+0.031
 swim+0.030
 splash+0.029
 popcorn+0.029
Neg logit contributions
ross-0.025
umper-0.024
Bet-0.024
Nut-0.023
inger-0.023
Token they
Token ID484
Feature activation-4.84e-02

Pos logit contributions
 sip+0.045
 dip+0.045
 swim+0.044
 movie+0.042
 splash+0.042
Neg logit contributions
ross-0.053
Bet-0.051
umper-0.050
Nut-0.049
inger-0.048
Token sat
Token ID3332
Feature activation-1.72e-02

Pos logit contributions
 sip+0.071
 dip+0.071
 swim+0.068
 movie+0.067
 splash+0.066
Neg logit contributions
ross-0.074
Bet-0.071
umper-0.071
inger-0.068
Nut-0.068
Token down
Token ID866
Feature activation-2.72e-02

Pos logit contributions
 sip+0.023
 dip+0.022
 swim+0.022
 splash+0.021
 popcorn+0.021
Neg logit contributions
ross-0.031
Bet-0.030
umper-0.030
inger-0.029
Nut-0.029
Tokenmy
Token ID1820
Feature activation-2.10e-02

Pos logit contributions
 sip+0.026
 dip+0.026
 swim+0.025
 splash+0.024
 look+0.024
Neg logit contributions
ross-0.035
inger-0.033
Bet-0.032
Nut-0.032
umper-0.031
Token made
Token ID925
Feature activation-2.52e-02

Pos logit contributions
 sip+0.029
 swim+0.028
 dip+0.028
 splash+0.026
 look+0.026
Neg logit contributions
ross-0.039
inger-0.037
Bet-0.036
Nut-0.036
ydia-0.035
Token her
Token ID607
Feature activation-3.41e-02

Pos logit contributions
 dip+0.036
 sip+0.035
 swim+0.034
 splash+0.034
 movie+0.032
Neg logit contributions
ross-0.041
umper-0.040
Bet-0.039
Nut-0.038
inger-0.038
Token some
Token ID617
Feature activation-4.68e-02

Pos logit contributions
 dip+0.053
 sip+0.052
 splash+0.052
 swim+0.052
 sigh+0.050
Neg logit contributions
eh-0.038
 known-0.035
umper-0.034
Bet-0.034
anya-0.034
Token y
Token ID331
Feature activation-4.35e-02

Pos logit contributions
 sip+0.052
 dip+0.051
 argue+0.050
 sigh+0.048
 swim+0.048
Neg logit contributions
ross-0.077
eh-0.076
umper-0.075
Nut-0.074
Bet-0.073
Tokenummy
Token ID13513
Feature activation-8.22e-02

Pos logit contributions
 swim+0.092
 dip+0.091
 drive+0.090
 argue+0.090
 sip+0.090
Neg logit contributions
ross-0.039
umper-0.037
orns-0.035
umbled-0.034
inger-0.032
Token w
Token ID266
Feature activation-1.79e-02

Pos logit contributions
itionally+0.139
 argue+0.126
 paddle+0.117
 drive+0.116
 Today+0.115
Neg logit contributions
eh-0.100
orns-0.089
ons-0.083
ase-0.082
Da-0.078
Tokenaffles
Token ID48501
Feature activation+1.20e-04

Pos logit contributions
 sip+0.027
 dip+0.027
 swim+0.026
 splash+0.026
 movie+0.025
Neg logit contributions
ross-0.028
umper-0.027
inger-0.026
Bet-0.026
Nut-0.025
Token for
Token ID329
Feature activation-4.63e-03

Pos logit contributions
ross+0.000
Bet+0.000
umper+0.000
inger+0.000
Nut+0.000
Neg logit contributions
 sip-0.000
 dip-0.000
 swim-0.000
 splash-0.000
 movie-0.000
Token breakfast
Token ID12607
Feature activation-1.06e-02

Pos logit contributions
 dip+0.004
 sip+0.004
 swim+0.004
 splash+0.004
 movie+0.003
Neg logit contributions
ross-0.010
umper-0.010
Bet-0.010
Nut-0.010
inger-0.010
Token.
Token ID13
Feature activation-2.18e-02

Pos logit contributions
 sip+0.013
 dip+0.013
 swim+0.012
 splash+0.012
 popcorn+0.012
Neg logit contributions
ross-0.020
Bet-0.019
umper-0.019
inger-0.019
Nut-0.019
Token mom
Token ID1995
Feature activation-6.42e-02

Pos logit contributions
 sip+0.075
 dip+0.074
 swim+0.069
 splash+0.069
 sigh+0.068
Neg logit contributions
ross-0.074
ich-0.073
Mic-0.073
umper-0.073
Bet-0.072
Token.
Token ID13
Feature activation-3.32e-02

Pos logit contributions
 sip+0.116
 dip+0.114
 swim+0.110
 splash+0.109
 dive+0.105
Neg logit contributions
umper-0.078
ross-0.075
Bet-0.072
inger-0.070
ully-0.068
Token They
Token ID1119
Feature activation-2.26e-02

Pos logit contributions
 dip+0.048
 sip+0.048
 swim+0.047
 popcorn+0.045
 movie+0.045
Neg logit contributions
ross-0.052
Bet-0.050
umper-0.048
ydia-0.048
inger-0.047
Token had
Token ID550
Feature activation-2.43e-02

Pos logit contributions
 sip+0.036
 dip+0.036
 swim+0.035
 splash+0.034
 look+0.033
Neg logit contributions
ross-0.037
inger-0.035
Bet-0.034
umper-0.034
Nut-0.033
Token a
Token ID257
Feature activation-5.73e-02

Pos logit contributions
 sip+0.034
 dip+0.034
 swim+0.033
 splash+0.032
 movie+0.031
Neg logit contributions
ross-0.041
Bet-0.039
umper-0.038
inger-0.038
Nut-0.037
Token big
Token ID1263
Feature activation-8.21e-02

Pos logit contributions
 dip+0.093
 sip+0.091
 swim+0.087
 anticipation+0.086
 splash+0.085
Neg logit contributions
Mic-0.063
eh-0.062
Bet-0.062
ich-0.059
ross-0.057
Token ball
Token ID2613
Feature activation-2.63e-02

Pos logit contributions
 dip+0.097
 sip+0.092
 swim+0.089
 splash+0.082
itionally+0.081
Neg logit contributions
eh-0.124
Bet-0.123
ase-0.122
Mic-0.122
ross-0.119
Token of
Token ID286
Feature activation-2.26e-02

Pos logit contributions
 sip+0.043
 dip+0.043
 swim+0.042
 splash+0.041
 popcorn+0.040
Neg logit contributions
ross-0.037
Bet-0.035
umper-0.035
inger-0.035
Nut-0.034
Token dough
Token ID15756
Feature activation-2.14e-02

Pos logit contributions
 sip+0.028
 sigh+0.027
 dip+0.026
 swim+0.026
 argue+0.025
Neg logit contributions
Nut-0.035
Mic-0.034
Bet-0.034
umper-0.034
ross-0.033
Token to
Token ID284
Feature activation-3.21e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 swim+0.026
 popcorn+0.025
 splash+0.025
Neg logit contributions
ross-0.040
Bet-0.039
umper-0.039
Nut-0.038
inger-0.038
Token roll
Token ID4836
Feature activation-9.64e-03

Pos logit contributions
 dip+0.027
 sip+0.027
 movie+0.026
 swim+0.025
 sigh+0.025
Neg logit contributions
ross-0.065
Bet-0.065
umper-0.064
Nut-0.064
inger-0.061
Token Mum
Token ID38367
Feature activation-3.42e-02

Pos logit contributions
 sip+0.029
 dip+0.029
 swim+0.028
 splash+0.027
 popcorn+0.027
Neg logit contributions
ross-0.033
Bet-0.032
umper-0.032
inger-0.031
Nut-0.031
Token and
Token ID290
Feature activation-8.20e-03

Pos logit contributions
 sip+0.055
 dip+0.055
 swim+0.053
 splash+0.052
 popcorn+0.052
Neg logit contributions
ross-0.051
Bet-0.048
umper-0.048
inger-0.047
Nut-0.046
Token dad
Token ID9955
Feature activation-4.29e-02

Pos logit contributions
 dip+0.007
 sip+0.007
 swim+0.007
 splash+0.007
 popcorn+0.007
Neg logit contributions
ross-0.018
inger-0.018
Bet-0.018
umper-0.017
Nut-0.017
Token had
Token ID550
Feature activation-2.60e-02

Pos logit contributions
 sip+0.070
 dip+0.069
 swim+0.067
 splash+0.065
 movie+0.065
Neg logit contributions
ross-0.060
umper-0.058
Bet-0.056
inger-0.055
Nut-0.054
Token a
Token ID257
Feature activation-6.14e-02

Pos logit contributions
 sip+0.038
 dip+0.038
 swim+0.036
 splash+0.035
 popcorn+0.035
Neg logit contributions
ross-0.043
Bet-0.041
umper-0.041
inger-0.040
Nut-0.039
Token big
Token ID1263
Feature activation-8.20e-02

Pos logit contributions
 dip+0.085
 sip+0.082
 swim+0.081
 argue+0.078
 reel+0.078
Neg logit contributions
 known-0.075
Bet-0.074
Kelly-0.073
 knowing-0.072
Op-0.071
Token surprise
Token ID5975
Feature activation-2.62e-02

Pos logit contributions
 dip+0.090
ksh+0.086
itionally+0.085
 swim+0.084
 sip+0.083
Neg logit contributions
amed-0.116
 knowing-0.115
ase-0.115
 named-0.115
Bet-0.112
Token for
Token ID329
Feature activation+1.08e-02

Pos logit contributions
 sip+0.044
 dip+0.043
 swim+0.042
 splash+0.041
 sigh+0.039
Neg logit contributions
ross-0.035
umper-0.031
Bet-0.031
ydia-0.030
 knowing-0.030
Token Tommy
Token ID19919
Feature activation-4.13e-02

Pos logit contributions
ross+0.019
Bet+0.018
inger+0.018
umper+0.017
Nut+0.017
Neg logit contributions
 dip-0.015
 sip-0.015
 swim-0.015
 popcorn-0.014
 movie-0.014
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
 sip+0.065
 dip+0.063
 splash+0.060
 swim+0.060
 movie+0.058
Neg logit contributions
ross-0.060
umper-0.057
inger-0.056
Bet-0.055
Nut-0.054
Token They
Token ID1119
Feature activation-2.63e-02

Pos logit contributions
 sip+0.017
 dip+0.017
 swim+0.016
 splash+0.016
 popcorn+0.016
Neg logit contributions
ross-0.022
Bet-0.021
umper-0.021
inger-0.021
Nut-0.021
Token and
Token ID290
Feature activation-2.22e-02

Pos logit contributions
 sip+0.018
 dip+0.018
 swim+0.017
 popcorn+0.017
 movie+0.017
Neg logit contributions
ross-0.018
inger-0.017
Bet-0.017
umper-0.016
Nut-0.016
Token turn
Token ID1210
Feature activation-4.05e-02

Pos logit contributions
 movie+0.026
 Today+0.023
 popcorn+0.023
 sip+0.023
rd+0.022
Neg logit contributions
Bet-0.034
ydia-0.034
ross-0.033
Op-0.033
inger-0.032
Token it
Token ID340
Feature activation-4.97e-02

Pos logit contributions
 sip+0.070
 dip+0.070
 movie+0.069
 picnic+0.068
 swim+0.067
Neg logit contributions
ross-0.045
umper-0.043
inger-0.042
Bet-0.042
pped-0.040
Token on
Token ID319
Feature activation-1.30e-02

Pos logit contributions
 movie+0.097
 sip+0.095
 popcorn+0.094
 dip+0.093
 picnic+0.092
Neg logit contributions
ross-0.048
inger-0.045
amed-0.043
Bet-0.040
but-0.038
Token.
Token ID13
Feature activation-5.27e-03

Pos logit contributions
 sip+0.016
 dip+0.016
 swim+0.015
 popcorn+0.015
 splash+0.015
Neg logit contributions
ross-0.025
umper-0.024
Bet-0.024
inger-0.023
Nut-0.023
Token Water
Token ID5638
Feature activation-8.13e-02

Pos logit contributions
 sip+0.008
 dip+0.008
 swim+0.008
 movie+0.007
 popcorn+0.007
Neg logit contributions
ross-0.008
Bet-0.008
inger-0.008
umper-0.008
Nut-0.008
Token fills
Token ID23816
Feature activation-1.32e-02

Pos logit contributions
 dip+0.108
 sip+0.106
 picnic+0.104
 movie+0.104
 argue+0.103
Neg logit contributions
ross-0.119
inger-0.115
Bet-0.111
orns-0.108
umper-0.107
Token the
Token ID262
Feature activation-7.28e-03

Pos logit contributions
 sip+0.019
 dip+0.019
 swim+0.018
 splash+0.018
 popcorn+0.018
Neg logit contributions
ross-0.022
Bet-0.021
umper-0.021
inger-0.021
Nut-0.020
Token bath
Token ID7837
Feature activation-7.19e-03

Pos logit contributions
 sip+0.008
 dip+0.008
 swim+0.008
 argue+0.008
 movie+0.007
Neg logit contributions
ross-0.013
inger-0.013
umper-0.013
Bet-0.012
amed-0.012
Tokentub
Token ID37995
Feature activation-3.90e-02

Pos logit contributions
 sip+0.013
 dip+0.013
 swim+0.013
 splash+0.012
 popcorn+0.012
Neg logit contributions
ross-0.009
Bet-0.009
umper-0.009
Nut-0.009
inger-0.009
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
 movie+0.075
 dip+0.073
 argue+0.073
 sip+0.072
 picnic+0.072
Neg logit contributions
ross-0.034
but-0.029
inger-0.028
amed-0.027
 knowing-0.026
TokenMom
Token ID29252
Feature activation-5.29e-02

Pos logit contributions
 dip+0.040
 sip+0.039
 swim+0.038
 splash+0.037
 sigh+0.037
Neg logit contributions
ross-0.019
Bet-0.019
Nut-0.017
inger-0.016
umper-0.016
Token and
Token ID290
Feature activation-2.20e-02

Pos logit contributions
 dip+0.057
 sip+0.057
 swim+0.054
 splash+0.052
 popcorn+0.050
Neg logit contributions
ross-0.103
umper-0.101
Bet-0.099
inger-0.098
ydia-0.095
Token Dad
Token ID17415
Feature activation-6.12e-02

Pos logit contributions
 sip+0.036
 dip+0.035
 movie+0.033
 swim+0.033
 sigh+0.032
Neg logit contributions
Bet-0.030
Nut-0.026
Da-0.025
Susan-0.025
Mill-0.025
Token have
Token ID423
Feature activation-3.35e-02

Pos logit contributions
 sip+0.068
 dip+0.067
 movie+0.064
 swim+0.064
 popcorn+0.063
Neg logit contributions
umper-0.109
ross-0.107
Bet-0.102
inger-0.101
ydia-0.101
Token a
Token ID257
Feature activation-6.27e-02

Pos logit contributions
 sip+0.050
 dip+0.049
 swim+0.047
 splash+0.047
 movie+0.044
Neg logit contributions
ross-0.052
umper-0.050
Bet-0.049
inger-0.048
Nut-0.047
Token big
Token ID1263
Feature activation-8.13e-02

Pos logit contributions
ksh+0.095
 dip+0.092
 argue+0.088
 reel+0.088
 swim+0.085
Neg logit contributions
eh-0.065
 known-0.063
illian-0.063
Op-0.063
 accidentally-0.063
Token surprise
Token ID5975
Feature activation-3.56e-02

Pos logit contributions
ksh+0.100
 dip+0.099
itionally+0.094
 reel+0.093
 swim+0.089
Neg logit contributions
eh-0.108
ase-0.108
Bet-0.105
ydia-0.104
 named-0.103
Token for
Token ID329
Feature activation-1.43e-02

Pos logit contributions
 dip+0.061
 sip+0.060
 swim+0.057
 splash+0.057
 sigh+0.055
Neg logit contributions
ross-0.047
ydia-0.039
 knowing-0.039
Bet-0.039
anya-0.038
Token them
Token ID606
Feature activation-4.83e-02

Pos logit contributions
 sip+0.023
 dip+0.023
 swim+0.022
 splash+0.022
 movie+0.021
Neg logit contributions
ross-0.020
Bet-0.019
umper-0.019
Nut-0.018
inger-0.018
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
 dip+0.074
 sip+0.074
 splash+0.069
 swim+0.068
 popcorn+0.065
Neg logit contributions
ross-0.071
umper-0.066
inger-0.065
Bet-0.065
ydia-0.062
Token They
Token ID1119
Feature activation-3.62e-02

Pos logit contributions
 dip+0.027
 swim+0.026
 sip+0.026
 movie+0.025
 dive+0.025
Neg logit contributions
ross-0.019
Bet-0.019
ydia-0.018
inger-0.017
anya-0.017
Token!
Token ID0
Feature activation-2.51e-02

Pos logit contributions
 sip+0.056
 dip+0.055
 swim+0.052
 splash+0.051
 sigh+0.049
Neg logit contributions
ross-0.053
Bet-0.047
inger-0.046
umper-0.045
odi-0.044
Token They
Token ID1119
Feature activation-4.02e-02

Pos logit contributions
 sip+0.040
 movie+0.038
 dip+0.038
 swim+0.037
 popcorn+0.037
Neg logit contributions
Bet-0.036
umper-0.035
ross-0.035
Nut-0.034
inger-0.034
Token put
Token ID1234
Feature activation-4.47e-02

Pos logit contributions
 sip+0.066
 dip+0.065
 swim+0.063
 movie+0.061
 popcorn+0.061
Neg logit contributions
ross-0.057
umper-0.055
Bet-0.054
inger-0.052
Nut-0.052
Token on
Token ID319
Feature activation-4.13e-02

Pos logit contributions
 sip+0.087
 dip+0.085
 swim+0.084
 splash+0.082
 argue+0.082
Neg logit contributions
amed-0.040
illian-0.037
odi-0.035
ross-0.034
umper-0.034
Token their
Token ID511
Feature activation-5.89e-02

Pos logit contributions
 sip+0.073
 dip+0.068
 sigh+0.066
 Today+0.066
 splash+0.066
Neg logit contributions
Kelly-0.039
 never-0.037
Bet-0.036
odi-0.036
amed-0.036
Token cheerful
Token ID37999
Feature activation-8.11e-02

Pos logit contributions
 sip+0.083
 dip+0.074
 reel+0.073
 argue+0.073
 splash+0.069
Neg logit contributions
eh-0.073
amed-0.069
odi-0.069
anya-0.067
ich-0.066
Token clothes
Token ID8242
Feature activation-1.00e-04

Pos logit contributions
 sip+0.107
 dip+0.098
 reel+0.091
 argue+0.089
 splash+0.084
Neg logit contributions
eh-0.119
ross-0.113
anya-0.113
amed-0.113
odi-0.108
Token and
Token ID290
Feature activation-2.96e-02

Pos logit contributions
 dip+0.000
 sip+0.000
 swim+0.000
 splash+0.000
 popcorn+0.000
Neg logit contributions
ross-0.000
Bet-0.000
umper-0.000
inger-0.000
Nut-0.000
Token hopped
Token ID45230
Feature activation-3.01e-02

Pos logit contributions
 sip+0.045
 dip+0.043
 swim+0.041
 movie+0.040
 sigh+0.040
Neg logit contributions
ross-0.043
Bet-0.041
umper-0.040
Nut-0.039
ydia-0.039
Token in
Token ID287
Feature activation-5.13e-02

Pos logit contributions
 sip+0.055
 dip+0.054
 movie+0.051
 argue+0.051
 swim+0.051
Neg logit contributions
ross-0.033
amed-0.031
inger-0.031
Bet-0.030
umper-0.030
Token the
Token ID262
Feature activation-4.19e-02

Pos logit contributions
 sip+0.102
 dip+0.099
 swim+0.096
 reel+0.094
ksh+0.093
Neg logit contributions
Kelly-0.034
Bet-0.032
Jan-0.030
ydia-0.030
 knowing-0.030
Token
Token ID198
Feature activation+9.49e-04

Pos logit contributions
ross+0.043
umper+0.040
Bet+0.040
inger+0.039
ydia+0.039
Neg logit contributions
 sip-0.025
 swim-0.025
 dip-0.024
 splash-0.024
 movie-0.023
Token
Token ID198
Feature activation+9.18e-03

Pos logit contributions
ross+0.002
inger+0.002
umper+0.002
Bet+0.002
ydia+0.002
Neg logit contributions
 sip-0.001
 swim-0.001
 dip-0.001
 movie-0.001
 splash-0.001
TokenHe
Token ID1544
Feature activation-2.37e-02

Pos logit contributions
ross+0.013
umper+0.013
inger+0.013
ydia+0.012
enna+0.012
Neg logit contributions
 swim-0.015
 sip-0.015
 dip-0.015
 splash-0.015
 drive-0.014
Token quickly
Token ID2952
Feature activation-2.77e-02

Pos logit contributions
 swim+0.033
 sip+0.032
 dip+0.032
 splash+0.031
 popcorn+0.031
Neg logit contributions
ross-0.044
inger-0.043
Bet-0.043
umper-0.042
Nut-0.042
Token put
Token ID1234
Feature activation-3.71e-02

Pos logit contributions
 sip+0.043
 dip+0.043
 swim+0.041
 movie+0.041
 popcorn+0.040
Neg logit contributions
ross-0.041
umper-0.039
Bet-0.039
inger-0.038
Nut-0.037
Token the
Token ID262
Feature activation-8.11e-02

Pos logit contributions
 sip+0.061
 dip+0.061
 swim+0.059
 splash+0.057
 movie+0.056
Neg logit contributions
ross-0.053
umper-0.051
Bet-0.050
inger-0.049
Nut-0.049
Token DVD
Token ID12490
Feature activation-4.77e-02

Pos logit contributions
 dip+0.108
 argue+0.104
 dive+0.104
 swim+0.103
 splash+0.099
Neg logit contributions
amed-0.116
ase-0.114
Prin-0.108
umper-0.107
but-0.107
Token in
Token ID287
Feature activation-1.88e-02

Pos logit contributions
 sip+0.072
 dip+0.071
 swim+0.069
 splash+0.067
 popcorn+0.067
Neg logit contributions
ross-0.076
Bet-0.073
umper-0.072
inger-0.072
Nut-0.071
Token the
Token ID262
Feature activation-4.62e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 swim+0.026
 popcorn+0.026
 splash+0.026
Neg logit contributions
ross-0.032
Bet-0.030
umper-0.030
inger-0.030
Nut-0.029
Token player
Token ID2137
Feature activation-3.32e-02

Pos logit contributions
 dip+0.057
 swim+0.053
 sip+0.053
 argue+0.051
 dive+0.050
Neg logit contributions
ase-0.079
ross-0.079
umper-0.079
amed-0.077
Mic-0.075
Token and
Token ID290
Feature activation-3.25e-02

Pos logit contributions
 dip+0.046
 sip+0.046
 swim+0.044
 splash+0.043
 popcorn+0.042
Neg logit contributions
ross-0.055
umper-0.053
Bet-0.052
inger-0.051
Nut-0.050
Token milk
Token ID7545
Feature activation-1.56e-02

Pos logit contributions
 argue+0.028
 dip+0.027
 swim+0.027
 sip+0.026
 splash+0.026
Neg logit contributions
inger-0.042
Bet-0.042
ross-0.042
eh-0.041
Nut-0.040
Token and
Token ID290
Feature activation-7.62e-03

Pos logit contributions
 sip+0.022
 dip+0.022
 swim+0.021
 popcorn+0.020
 splash+0.020
Neg logit contributions
ross-0.027
umper-0.027
Bet-0.026
inger-0.026
Nut-0.025
Token watching
Token ID4964
Feature activation-2.26e-02

Pos logit contributions
 dip+0.010
 sip+0.010
 swim+0.010
 splash+0.010
 look+0.010
Neg logit contributions
inger-0.014
ross-0.014
umper-0.014
Bet-0.013
Nut-0.013
Token the
Token ID262
Feature activation-3.60e-02

Pos logit contributions
 sip+0.036
 dip+0.036
 swim+0.034
 splash+0.033
 popcorn+0.033
Neg logit contributions
ross-0.034
Bet-0.032
umper-0.032
inger-0.032
Nut-0.031
Token fire
Token ID2046
Feature activation-2.49e-02

Pos logit contributions
 sip+0.054
 dip+0.054
 argue+0.049
 swim+0.047
 dive+0.047
Neg logit contributions
ross-0.048
ich-0.048
Bet-0.046
Wal-0.045
 ruled-0.044
Tokenwork
Token ID1818
Feature activation-8.09e-02

Pos logit contributions
 sip+0.035
 dip+0.035
 popcorn+0.032
 swim+0.032
 picnic+0.031
Neg logit contributions
ross-0.041
Bet-0.038
ich-0.038
umper-0.038
inger-0.037
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
 sip+0.102
 dip+0.102
 popcorn+0.099
 argue+0.097
 swim+0.095
Neg logit contributions
ross-0.120
Bet-0.107
 knowing-0.107
umper-0.106
inger-0.106
Token<|endoftext|>
Token ID50256
Feature activation-1.47e-02

Pos logit contributions
 sip+0.022
 dip+0.021
 look+0.021
 splash+0.020
 swim+0.020
Neg logit contributions
ross-0.027
umper-0.026
inger-0.026
Nut-0.025
Bet-0.024
TokenE
Token ID36
Feature activation-5.55e-03

Pos logit contributions
 sip+0.022
 swim+0.021
 dip+0.021
 movie+0.021
 popcorn+0.021
Neg logit contributions
ross-0.024
umper-0.022
Bet-0.022
inger-0.022
Nut-0.022
Tokendd
Token ID1860
Feature activation-1.42e-02

Pos logit contributions
 sip+0.011
 dip+0.011
 swim+0.010
 popcorn+0.010
 movie+0.010
Neg logit contributions
ross-0.007
Bet-0.006
umper-0.006
inger-0.006
Nut-0.006
Tokenie
Token ID494
Feature activation-1.11e-02

Pos logit contributions
 swim+0.021
 sip+0.020
 dip+0.020
 splash+0.019
 movie+0.019
Neg logit contributions
Nut-0.024
ross-0.024
Bet-0.023
Mic-0.023
inger-0.022
Token bite
Token ID13197
Feature activation-3.92e-02

Pos logit contributions
 dip+0.035
 sip+0.035
 swim+0.032
 splash+0.031
 popcorn+0.029
Neg logit contributions
ross-0.070
umper-0.068
Bet-0.067
inger-0.067
Nut-0.066
Token and
Token ID290
Feature activation-3.84e-02

Pos logit contributions
 sip+0.059
 dip+0.058
 swim+0.056
 popcorn+0.056
 movie+0.054
Neg logit contributions
ross-0.065
Bet-0.064
inger-0.062
Nut-0.062
umper-0.062
Token makes
Token ID1838
Feature activation-2.84e-02

Pos logit contributions
 dip+0.042
 argue+0.041
 sip+0.041
 movie+0.041
 Today+0.040
Neg logit contributions
ross-0.063
 knowing-0.057
 known-0.057
umper-0.056
ydia-0.056
Token a
Token ID257
Feature activation-5.08e-02

Pos logit contributions
 dip+0.042
 sip+0.042
 swim+0.040
 splash+0.040
 argue+0.039
Neg logit contributions
ross-0.040
umper-0.038
inger-0.036
Bet-0.036
ydia-0.036
Token y
Token ID331
Feature activation-5.10e-02

Pos logit contributions
 dip+0.068
 argue+0.062
 sip+0.062
 swim+0.061
 search+0.061
Neg logit contributions
ross-0.071
Bet-0.070
Wal-0.068
 knowing-0.067
ich-0.066
Tokenummy
Token ID13513
Feature activation-8.00e-02

Pos logit contributions
 dip+0.107
 sip+0.103
 argue+0.103
 swim+0.103
 tickets+0.102
Neg logit contributions
ross-0.049
inger-0.039
umper-0.039
umbled-0.037
ooks-0.036
Token sound
Token ID2128
Feature activation-2.42e-02

Pos logit contributions
itionally+0.113
 First+0.110
 plunge+0.104
riger+0.102
 dip+0.102
Neg logit contributions
 knowing-0.105
eh-0.095
ull-0.094
ase-0.088
anya-0.087
Token.
Token ID13
Feature activation-2.08e-02

Pos logit contributions
 dip+0.040
 sip+0.038
 picnic+0.037
 search+0.037
 argue+0.037
Neg logit contributions
ross-0.034
 knowing-0.030
umper-0.029
but-0.028
Bet-0.028
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
 sip+0.033
 dip+0.032
 swim+0.031
 splash+0.031
 popcorn+0.030
Neg logit contributions
ross-0.032
umper-0.031
Bet-0.031
inger-0.030
Nut-0.030
Token
Token ID198
Feature activation-2.37e-02

Pos logit contributions
 sip+0.017
 swim+0.017
 splash+0.016
 dip+0.016
 popcorn+0.015
Neg logit contributions
ross-0.028
umper-0.025
Bet-0.025
inger-0.025
ydia-0.024
Token"
Token ID1
Feature activation-2.82e-02

Pos logit contributions
 sip+0.040
 dip+0.039
 swim+0.039
 splash+0.037
 popcorn+0.037
Neg logit contributions
ross-0.034
umper-0.033
Bet-0.032
inger-0.032
ully-0.031
Token Ben
Token ID3932
Feature activation-3.51e-02

Pos logit contributions
 sip+0.001
 dip+0.001
 popcorn+0.001
 swim+0.001
 look+0.001
Neg logit contributions
ross-0.001
umper-0.001
inger-0.001
Bet-0.001
Nut-0.001
Token and
Token ID290
Feature activation-2.43e-02

Pos logit contributions
 sip+0.051
 dip+0.051
 swim+0.049
 splash+0.048
 popcorn+0.048
Neg logit contributions
ross-0.056
umper-0.053
Bet-0.053
inger-0.053
Nut-0.051
Token squee
Token ID13170
Feature activation-3.31e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 picnic+0.026
 movie+0.026
 swim+0.025
Neg logit contributions
ross-0.040
ydia-0.039
Bet-0.039
umper-0.039
Op-0.038
Tokenzes
Token ID12271
Feature activation-3.38e-02

Pos logit contributions
 dip+0.045
 sip+0.045
 movie+0.043
 swim+0.042
 splash+0.041
Neg logit contributions
ross-0.055
inger-0.053
umper-0.052
Nut-0.051
Bet-0.051
Token.
Token ID13
Feature activation-2.31e-03

Pos logit contributions
 dip+0.052
 sip+0.051
 swim+0.050
 splash+0.048
 movie+0.048
Neg logit contributions
ross-0.051
umper-0.049
Bet-0.049
inger-0.048
Nut-0.047
Token Water
Token ID5638
Feature activation-7.98e-02

Pos logit contributions
 sip+0.003
 dip+0.003
 swim+0.003
 splash+0.003
 popcorn+0.003
Neg logit contributions
ross-0.005
inger-0.004
umper-0.004
ppa-0.004
Bet-0.004
Token shoots
Token ID20611
Feature activation-2.57e-02

Pos logit contributions
 picnic+0.102
 dip+0.102
 movie+0.100
 search+0.099
 sip+0.098
Neg logit contributions
ross-0.122
inger-0.117
Bet-0.116
umper-0.112
orns-0.110
Token out
Token ID503
Feature activation-1.13e-02

Pos logit contributions
 sip+0.039
 dip+0.039
 swim+0.038
 splash+0.037
 movie+0.036
Neg logit contributions
ross-0.040
Bet-0.038
umper-0.038
inger-0.037
Nut-0.037
Token and
Token ID290
Feature activation-4.85e-02

Pos logit contributions
 sip+0.019
 dip+0.019
 swim+0.018
 splash+0.018
 popcorn+0.018
Neg logit contributions
ross-0.017
umper-0.016
Bet-0.016
inger-0.016
Nut-0.016
Token hits
Token ID7127
Feature activation-2.26e-02

Pos logit contributions
rd+0.069
 picnic+0.064
 movie+0.062
 Today+0.060
latable+0.059
Neg logit contributions
 Bree-0.061
ross-0.058
Bet-0.058
 mag-0.058
Op-0.057
Token him
Token ID683
Feature activation-3.18e-02

Pos logit contributions
 sip+0.034
 dip+0.034
 swim+0.033
 splash+0.032
 popcorn+0.032
Neg logit contributions
ross-0.036
Bet-0.034
umper-0.034
inger-0.034
Nut-0.033
Token.
Token ID13
Feature activation+5.57e-03

Pos logit contributions
ross+0.030
Bet+0.029
umper+0.029
inger+0.028
Nut+0.028
Neg logit contributions
 sip-0.022
 dip-0.022
 swim-0.021
 splash-0.020
 popcorn-0.020
Token I
Token ID314
Feature activation+1.98e-02

Pos logit contributions
ross+0.010
Bet+0.010
inger+0.010
umper+0.010
Nut+0.009
Neg logit contributions
 sip-0.007
 dip-0.007
 swim-0.007
 splash-0.007
 popcorn-0.007
Token should
Token ID815
Feature activation+8.16e-03

Pos logit contributions
ross+0.031
Bet+0.029
umper+0.029
inger+0.029
Nut+0.028
Neg logit contributions
 sip-0.031
 dip-0.031
 swim-0.030
 splash-0.029
 popcorn-0.029
Token have
Token ID423
Feature activation+8.77e-03

Pos logit contributions
ross+0.011
umper+0.011
Nut+0.011
Bet+0.010
inger+0.010
Neg logit contributions
 dip-0.013
 sip-0.013
 movie-0.013
 popcorn-0.012
 swim-0.012
Token shared
Token ID4888
Feature activation+3.15e-02

Pos logit contributions
ross+0.013
Bet+0.012
umper+0.012
inger+0.012
Nut+0.012
Neg logit contributions
 sip-0.014
 dip-0.014
 swim-0.014
 splash-0.013
 popcorn-0.013
Token with
Token ID351
Feature activation+4.85e-02

Pos logit contributions
ross+0.059
Bet+0.056
umper+0.056
inger+0.056
ully+0.054
Neg logit contributions
 sip-0.043
 popcorn-0.042
 dip-0.041
 swim-0.040
 movie-0.039
Token you
Token ID345
Feature activation+1.54e-03

Pos logit contributions
ross+0.106
inger+0.102
Bet+0.099
umper+0.096
amed+0.095
Neg logit contributions
 popcorn-0.049
 dip-0.047
 swim-0.046
 look-0.046
 ice-0.045
Token.
Token ID13
Feature activation+3.98e-03

Pos logit contributions
ross+0.002
umper+0.002
inger+0.002
Bet+0.002
Nut+0.002
Neg logit contributions
 dip-0.002
 sip-0.002
 splash-0.002
 swim-0.002
 movie-0.002
Token Sharing
Token ID36644
Feature activation-8.40e-03

Pos logit contributions
ross+0.007
Bet+0.007
umper+0.006
inger+0.006
Nut+0.006
Neg logit contributions
 sip-0.006
 dip-0.005
 swim-0.005
 splash-0.005
 popcorn-0.005
Token is
Token ID318
Feature activation+6.73e-03

Pos logit contributions
 sip+0.008
 swim+0.008
 dip+0.008
 popcorn+0.007
 splash+0.007
Neg logit contributions
ross-0.019
Bet-0.018
inger-0.018
umper-0.018
Nut-0.018
Token caring
Token ID18088
Feature activation+8.88e-03

Pos logit contributions
ross+0.014
umper+0.014
inger+0.014
Bet+0.013
Nut+0.013
Neg logit contributions
 sip-0.007
 swim-0.007
 dip-0.007
 popcorn-0.007
 splash-0.007
Token first
Token ID717
Feature activation-7.52e-03

Pos logit contributions
 dip+0.008
 swim+0.007
 sip+0.007
 splash+0.007
 popcorn+0.007
Neg logit contributions
Bet-0.012
ross-0.012
Nut-0.012
umper-0.012
inger-0.011
Token!
Token ID0
Feature activation-4.45e-03

Pos logit contributions
 dip+0.009
 sip+0.009
 swim+0.009
 splash+0.008
 popcorn+0.008
Neg logit contributions
ross-0.014
Bet-0.014
umper-0.014
Nut-0.013
inger-0.013
Token It
Token ID632
Feature activation-9.00e-03

Pos logit contributions
 sip+0.005
 dip+0.004
 swim+0.004
 splash+0.004
 Today+0.004
Neg logit contributions
ross-0.010
ppa-0.009
inger-0.009
umper-0.009
Bet-0.009
Token had
Token ID550
Feature activation+2.34e-02

Pos logit contributions
 swim+0.013
 splash+0.012
 dip+0.012
 drive+0.012
 sip+0.012
Neg logit contributions
ross-0.016
umper-0.016
Bet-0.016
inger-0.015
Nut-0.015
Token been
Token ID587
Feature activation+1.26e-02

Pos logit contributions
umper+0.041
ross+0.041
Bet+0.040
Mic+0.039
inger+0.039
Neg logit contributions
 dip-0.032
 look-0.032
 swim-0.032
 popcorn-0.031
 splash-0.031
Token worth
Token ID2861
Feature activation+4.84e-02

Pos logit contributions
Bet+0.023
ross+0.023
umper+0.022
inger+0.022
Nut+0.022
Neg logit contributions
 swim-0.016
 popcorn-0.016
 dip-0.016
 splash-0.015
 drive-0.015
Token the
Token ID262
Feature activation+1.53e-02

Pos logit contributions
ross+0.083
Bet+0.081
inger+0.080
umper+0.079
Nut+0.077
Neg logit contributions
 dip-0.067
 sip-0.066
 swim-0.066
 popcorn-0.063
 splash-0.062
Token delay
Token ID5711
Feature activation+2.70e-02

Pos logit contributions
ross+0.029
inger+0.027
umper+0.026
Bet+0.026
Nut+0.026
Neg logit contributions
 sip-0.019
 dip-0.018
 swim-0.017
 popcorn-0.016
 splash-0.016
Token!
Token ID0
Feature activation+2.51e-03

Pos logit contributions
Bet+0.051
umper+0.051
ross+0.050
Nut+0.049
inger+0.048
Neg logit contributions
 dip-0.034
 swim-0.033
 sip-0.032
 splash-0.032
 popcorn-0.031
Token<|endoftext|>
Token ID50256
Feature activation-1.81e-02

Pos logit contributions
ross+0.006
inger+0.005
ppa+0.005
umper+0.005
Bet+0.005
Neg logit contributions
 sip-0.002
 Today-0.002
 dip-0.002
 swim-0.002
 looks-0.002
TokenSus
Token ID30746
Feature activation-5.61e-03

Pos logit contributions
 sip+0.026
 swim+0.026
 dip+0.025
 movie+0.025
 popcorn+0.025
Neg logit contributions
ross-0.031
umper-0.028
Bet-0.028
inger-0.028
Nut-0.028
Token bird
Token ID6512
Feature activation+1.19e-02

Pos logit contributions
ross+0.056
umper+0.053
Bet+0.052
ydia+0.051
inger+0.051
Neg logit contributions
 swim-0.038
 dip-0.037
 sip-0.037
 splash-0.036
 movie-0.035
Token loved
Token ID6151
Feature activation+3.07e-02

Pos logit contributions
ross+0.023
ydia+0.021
umper+0.021
inger+0.021
Bet+0.020
Neg logit contributions
 swim-0.017
 looks-0.016
 sip-0.016
 splash-0.016
 dip-0.015
Token to
Token ID284
Feature activation+7.24e-03

Pos logit contributions
ross+0.065
inger+0.061
umper+0.060
ydia+0.060
amed+0.057
Neg logit contributions
 swim-0.039
 dip-0.036
 popcorn-0.036
 splash-0.035
 sip-0.034
Token sing
Token ID1702
Feature activation+2.76e-02

Pos logit contributions
ross+0.015
umper+0.014
Bet+0.014
inger+0.014
Nut+0.014
Neg logit contributions
 sip-0.008
 dip-0.008
 swim-0.007
 splash-0.007
 popcorn-0.007
Token and
Token ID290
Feature activation-1.25e-02

Pos logit contributions
ross+0.055
umper+0.055
inger+0.053
ydia+0.053
Bet+0.052
Neg logit contributions
 swim-0.034
 popcorn-0.032
 movie-0.032
 sip-0.031
 look-0.031
Token play
Token ID711
Feature activation+4.93e-02

Pos logit contributions
 sip+0.013
 dip+0.012
 popcorn+0.012
 movie+0.011
 swim+0.011
Neg logit contributions
ross-0.025
Bet-0.025
umper-0.024
Nut-0.024
inger-0.024
Token with
Token ID351
Feature activation+2.14e-02

Pos logit contributions
ross+0.088
umper+0.087
inger+0.086
Bet+0.084
enna+0.084
Neg logit contributions
 swim-0.069
 sip-0.067
 dip-0.065
 splash-0.065
 movie-0.062
Token his
Token ID465
Feature activation+1.35e-02

Pos logit contributions
ross+0.040
inger+0.037
ydia+0.036
Bet+0.035
umper+0.035
Neg logit contributions
 swim-0.032
 popcorn-0.031
 sip-0.030
 dip-0.030
 splash-0.029
Token friends
Token ID2460
Feature activation-1.47e-02

Pos logit contributions
ross+0.022
umper+0.020
Bet+0.020
inger+0.019
ydia+0.019
Neg logit contributions
 swim-0.021
 dip-0.021
 sip-0.021
 splash-0.020
 popcorn-0.020
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
 sip+0.020
 dip+0.020
 swim+0.019
 popcorn+0.019
 movie+0.019
Neg logit contributions
ross-0.025
umper-0.024
Bet-0.024
inger-0.023
Nut-0.023
Token One
Token ID1881
Feature activation+2.11e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 sigh+0.025
 popcorn+0.025
 argue+0.025
Neg logit contributions
Bet-0.018
umper-0.017
Nut-0.017
ross-0.017
inger-0.016
Token to
Token ID284
Feature activation-2.02e-03

Pos logit contributions
ross+0.022
inger+0.020
umper+0.020
Bet+0.020
ydia+0.020
Neg logit contributions
 swim-0.017
 dip-0.017
 sip-0.017
 popcorn-0.017
 splash-0.016
Token hop
Token ID1725
Feature activation+3.32e-02

Pos logit contributions
 sip+0.002
 dip+0.002
 popcorn+0.002
 movie+0.002
 sigh+0.002
Neg logit contributions
Bet-0.004
umper-0.004
Nut-0.004
ross-0.004
inger-0.004
Token around
Token ID1088
Feature activation+1.96e-02

Pos logit contributions
ross+0.065
illian+0.060
anya+0.060
Bet+0.059
enna+0.059
Neg logit contributions
 swim-0.046
 sip-0.044
 dip-0.044
 splash-0.041
 look-0.041
Token the
Token ID262
Feature activation+1.21e-02

Pos logit contributions
ross+0.038
inger+0.036
anya+0.035
ydia+0.035
enna+0.034
Neg logit contributions
 swim-0.029
 dip-0.027
 sip-0.026
 search-0.026
 splash-0.026
Token me
Token ID502
Feature activation+3.60e-02

Pos logit contributions
ross+0.021
Bet+0.019
inger+0.018
umper+0.018
ydia+0.018
Neg logit contributions
 dip-0.018
 swim-0.018
 sip-0.017
 splash-0.017
 popcorn-0.017
Tokenadow
Token ID4584
Feature activation+4.79e-02

Pos logit contributions
ross+0.058
Bet+0.054
Nut+0.054
umper+0.053
Mic+0.051
Neg logit contributions
 swim-0.055
 sip-0.054
 dip-0.054
 splash-0.052
 look-0.051
Token all
Token ID477
Feature activation-9.37e-03

Pos logit contributions
ross+0.082
umper+0.081
Bet+0.079
Nut+0.078
inger+0.078
Neg logit contributions
 swim-0.066
 sip-0.066
 dip-0.066
 splash-0.063
 look-0.061
Token day
Token ID1110
Feature activation+1.16e-02

Pos logit contributions
 dip+0.010
 sip+0.010
 swim+0.010
 splash+0.010
 movie+0.009
Neg logit contributions
ross-0.019
Bet-0.018
umper-0.018
inger-0.018
Nut-0.018
Token long
Token ID890
Feature activation+2.25e-02

Pos logit contributions
ross+0.022
Bet+0.021
umper+0.021
inger+0.021
Nut+0.020
Neg logit contributions
 sip-0.014
 dip-0.014
 swim-0.013
 splash-0.013
 movie-0.013
Token.
Token ID13
Feature activation+7.39e-04

Pos logit contributions
ross+0.051
Bet+0.051
inger+0.050
umper+0.049
Nut+0.049
Neg logit contributions
 swim-0.019
 sip-0.019
 dip-0.019
 popcorn-0.018
 splash-0.016
Token One
Token ID1881
Feature activation+1.45e-02

Pos logit contributions
Nut+0.001
umper+0.001
Bet+0.001
ross+0.001
Mic+0.001
Neg logit contributions
 sip-0.001
 dip-0.001
 movie-0.001
 popcorn-0.001
 argue-0.001
Token generous
Token ID14431
Feature activation+1.50e-02

Pos logit contributions
ross+0.010
Bet+0.010
umper+0.010
inger+0.010
Nut+0.010
Neg logit contributions
 dip-0.008
 sip-0.008
 swim-0.008
 splash-0.007
 popcorn-0.007
Token and
Token ID290
Feature activation+2.17e-02

Pos logit contributions
ross+0.026
Bet+0.025
inger+0.025
umper+0.025
Nut+0.025
Neg logit contributions
 dip-0.020
 swim-0.020
 popcorn-0.020
 sip-0.020
 movie-0.019
Token shared
Token ID4888
Feature activation+4.55e-02

Pos logit contributions
ross+0.034
umper+0.033
inger+0.033
Bet+0.033
Nut+0.031
Neg logit contributions
 dip-0.034
 swim-0.033
 sip-0.033
 splash-0.032
 look-0.032
Token whatever
Token ID4232
Feature activation+8.35e-03

Pos logit contributions
ross+0.068
umper+0.063
inger+0.062
Bet+0.062
Nut+0.059
Neg logit contributions
 sip-0.077
 dip-0.076
 swim-0.074
 popcorn-0.074
 movie-0.071
Token she
Token ID673
Feature activation+2.91e-02

Pos logit contributions
ross+0.012
umper+0.012
inger+0.012
Bet+0.012
Nut+0.011
Neg logit contributions
 dip-0.014
 sip-0.013
 swim-0.013
 popcorn-0.013
 movie-0.013
Token had
Token ID550
Feature activation+5.79e-02

Pos logit contributions
ross+0.048
Bet+0.047
inger+0.046
Nut+0.045
umper+0.044
Neg logit contributions
 dip-0.044
 swim-0.043
 sip-0.043
 popcorn-0.040
 look-0.040
Token with
Token ID351
Feature activation+2.95e-02

Pos logit contributions
Bet+0.123
Nut+0.122
Mic+0.116
umper+0.112
ross+0.110
Neg logit contributions
 swim-0.060
 look-0.060
 dip-0.060
 search-0.057
 wait-0.056
Token people
Token ID661
Feature activation+8.28e-03

Pos logit contributions
ross+0.060
Bet+0.057
inger+0.056
amed+0.055
umper+0.055
Neg logit contributions
 sip-0.035
 dip-0.034
 popcorn-0.034
 swim-0.033
 nap-0.032
Token in
Token ID287
Feature activation+1.10e-02

Pos logit contributions
ross+0.014
umper+0.013
Bet+0.013
inger+0.013
Nut+0.013
Neg logit contributions
 sip-0.012
 dip-0.012
 swim-0.011
 splash-0.011
 movie-0.011
Token need
Token ID761
Feature activation+1.39e-02

Pos logit contributions
ross+0.021
inger+0.019
Nut+0.019
Bet+0.019
umper+0.019
Neg logit contributions
 sip-0.015
 dip-0.015
 search-0.014
 swim-0.014
 look-0.014
Token.
Token ID13
Feature activation-1.40e-03

Pos logit contributions
ross+0.031
Bet+0.031
umper+0.030
Nut+0.030
inger+0.030
Neg logit contributions
 sip-0.012
 dip-0.012
 swim-0.012
 popcorn-0.011
 look-0.011
Token satisfaction
Token ID14676
Feature activation+3.38e-02

Pos logit contributions
 dip+0.010
 sip+0.009
 swim+0.009
 movie+0.009
 splash+0.009
Neg logit contributions
ross-0.010
Bet-0.010
umper-0.010
ydia-0.010
Nut-0.009
Token as
Token ID355
Feature activation+1.16e-02

Pos logit contributions
Bet+0.070
Nut+0.068
inger+0.068
umper+0.068
Mic+0.067
Neg logit contributions
 swim-0.038
 popcorn-0.037
 sip-0.036
 dip-0.036
 splash-0.035
Token she
Token ID673
Feature activation+1.87e-02

Pos logit contributions
inger+0.024
ross+0.023
umper+0.023
amed+0.023
Bet+0.023
Neg logit contributions
 swim-0.013
 dip-0.013
 splash-0.012
 sip-0.012
 popcorn-0.011
Token looked
Token ID3114
Feature activation-6.15e-03

Pos logit contributions
ross+0.033
inger+0.032
Bet+0.031
umper+0.031
Nut+0.030
Neg logit contributions
 swim-0.027
 dip-0.026
 sip-0.026
 splash-0.025
 drive-0.024
Token at
Token ID379
Feature activation+1.25e-02

Pos logit contributions
 dip+0.009
 sip+0.009
 swim+0.009
 splash+0.008
 popcorn+0.008
Neg logit contributions
ross-0.010
Bet-0.010
Nut-0.010
inger-0.010
umper-0.010
Token her
Token ID607
Feature activation+7.55e-03

Pos logit contributions
ross+0.024
Bet+0.022
inger+0.022
Nut+0.021
umper+0.021
Neg logit contributions
 sip-0.018
 dip-0.017
 swim-0.017
 splash-0.016
 popcorn-0.016
Token beautiful
Token ID4950
Feature activation-7.49e-04

Pos logit contributions
ross+0.012
Bet+0.012
inger+0.012
umper+0.012
Nut+0.011
Neg logit contributions
 sip-0.011
 dip-0.011
 swim-0.010
 popcorn-0.010
 splash-0.010
Token castle
Token ID16669
Feature activation+2.64e-02

Pos logit contributions
 dip+0.001
 sip+0.001
 swim+0.001
 splash+0.001
 movie+0.001
Neg logit contributions
ross-0.001
umper-0.001
Bet-0.001
inger-0.001
Nut-0.001
Token.
Token ID13
Feature activation+5.75e-04

Pos logit contributions
ross+0.050
umper+0.050
Bet+0.050
Nut+0.049
inger+0.048
Neg logit contributions
 dip-0.031
 sip-0.031
 swim-0.030
 splash-0.029
 movie-0.029
Token
Token ID220
Feature activation+3.43e-02

Pos logit contributions
ross+0.001
inger+0.001
umper+0.001
pped+0.001
ppa+0.001
Neg logit contributions
 Today-0.001
 sip-0.001
 looks-0.001
 swim-0.001
 look-0.001
Token
Token ID198
Feature activation+1.24e-02

Pos logit contributions
ross+0.074
umper+0.068
ppa+0.066
ully+0.066
Bet+0.066
Neg logit contributions
 sip-0.029
 Today-0.029
 swim-0.028
 look-0.028
 splash-0.026
Token a
Token ID257
Feature activation-3.63e-02

Pos logit contributions
 sip+0.029
 dip+0.029
 swim+0.028
 splash+0.027
 popcorn+0.026
Neg logit contributions
ross-0.040
Bet-0.038
umper-0.038
inger-0.038
Nut-0.037
Token beautiful
Token ID4950
Feature activation-5.76e-02

Pos logit contributions
 argue+0.046
 swim+0.046
 dip+0.045
 splash+0.044
 sip+0.044
Neg logit contributions
Bet-0.054
eh-0.052
Nut-0.052
illian-0.051
ross-0.051
Token,
Token ID11
Feature activation+2.60e-02

Pos logit contributions
 argue+0.070
 swim+0.066
 dip+0.066
 splash+0.062
 sip+0.061
Neg logit contributions
eh-0.091
ross-0.089
Bet-0.089
anya-0.087
ydia-0.086
Token graceful
Token ID44363
Feature activation-4.41e-02

Pos logit contributions
ross+0.056
umper+0.054
inger+0.054
Bet+0.054
Nut+0.052
Neg logit contributions
 dip-0.026
 sip-0.026
 swim-0.024
 popcorn-0.023
 splash-0.023
Token necklace
Token ID38987
Feature activation+2.02e-02

Pos logit contributions
 dip+0.055
 sip+0.054
 swim+0.053
 argue+0.053
 splash+0.050
Neg logit contributions
ross-0.073
Bet-0.070
inger-0.069
Nut-0.068
ydia-0.067
Token to
Token ID284
Feature activation+5.64e-03

Pos logit contributions
umper+0.043
Bet+0.041
Wal+0.041
ross+0.040
 known+0.040
Neg logit contributions
 look-0.021
 sip-0.021
 drive-0.020
 walk-0.020
 dip-0.020
Token wear
Token ID5806
Feature activation+3.79e-02

Pos logit contributions
ross+0.013
inger+0.013
Bet+0.013
umper+0.012
amed+0.012
Neg logit contributions
 dip-0.006
 sip-0.005
 swim-0.005
 look-0.005
 drive-0.005
Token to
Token ID284
Feature activation+1.66e-02

Pos logit contributions
ross+0.085
Bet+0.084
inger+0.081
umper+0.081
Mic+0.076
Neg logit contributions
 look-0.040
 dip-0.039
 popcorn-0.037
 sip-0.035
 swim-0.035
Token a
Token ID257
Feature activation-6.30e-03

Pos logit contributions
ross+0.037
umper+0.035
Bet+0.035
inger+0.035
Nut+0.034
Neg logit contributions
 dip-0.017
 sip-0.016
 swim-0.016
 look-0.015
 splash-0.015
Token party
Token ID2151
Feature activation+2.51e-02

Pos logit contributions
 sip+0.008
 dip+0.008
 swim+0.007
 splash+0.007
 popcorn+0.007
Neg logit contributions
Bet-0.011
ross-0.011
Nut-0.011
umper-0.010
Mic-0.010
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
umper+0.053
Nut+0.052
Bet+0.051
inger+0.051
ross+0.050
Neg logit contributions
 movie-0.026
 dip-0.025
 swim-0.025
 picnic-0.024
 popcorn-0.024
Token Bob
Token ID5811
Feature activation-1.26e-02

Pos logit contributions
 sip+0.031
 dip+0.031
 swim+0.030
 splash+0.029
 movie+0.029
Neg logit contributions
ross-0.030
Bet-0.028
umper-0.027
Nut-0.027
inger-0.027
Token started
Token ID2067
Feature activation-1.44e-02

Pos logit contributions
 swim+0.019
 dip+0.019
 sip+0.019
 splash+0.018
 popcorn+0.018
Neg logit contributions
ross-0.021
Bet-0.019
umper-0.019
inger-0.019
Nut-0.019
Token to
Token ID284
Feature activation-2.21e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 swim+0.025
 picnic+0.024
 splash+0.024
Neg logit contributions
ross-0.016
Bet-0.015
 known-0.015
inger-0.014
 knowing-0.014
Token feel
Token ID1254
Feature activation-1.45e-02

Pos logit contributions
 sip+0.025
 dip+0.024
 popcorn+0.023
 movie+0.022
 swim+0.022
Neg logit contributions
Bet-0.039
ross-0.038
 known-0.038
umper-0.037
Nut-0.036
Token very
Token ID845
Feature activation-2.60e-02

Pos logit contributions
 sip+0.021
 dip+0.021
 swim+0.020
 movie+0.020
 splash+0.019
Neg logit contributions
ross-0.022
umper-0.021
Bet-0.021
Nut-0.020
 known-0.020
Token sleepy
Token ID42023
Feature activation+7.07e-03

Pos logit contributions
 sip+0.043
 dip+0.041
 movie+0.040
 popcorn+0.039
 picnic+0.039
Neg logit contributions
ross-0.036
 known-0.031
inger-0.031
umper-0.030
 knowing-0.029
Token.
Token ID13
Feature activation-3.65e-03

Pos logit contributions
ross+0.010
umper+0.009
Bet+0.009
 knowing+0.009
inger+0.009
Neg logit contributions
 sip-0.012
 dip-0.011
 swim-0.011
 splash-0.011
 argue-0.010
Token He
Token ID679
Feature activation+1.86e-03

Pos logit contributions
 sip+0.007
 dip+0.007
 movie+0.006
 popcorn+0.006
 swim+0.006
Neg logit contributions
Bet-0.004
ross-0.004
Nut-0.004
inger-0.004
umper-0.004
Token tried
Token ID3088
Feature activation-1.39e-02

Pos logit contributions
ross+0.003
Bet+0.003
umper+0.003
inger+0.003
Nut+0.003
Neg logit contributions
 sip-0.003
 dip-0.003
 swim-0.003
 splash-0.003
 popcorn-0.003
Token his
Token ID465
Feature activation-1.18e-02

Pos logit contributions
 dip+0.026
 sip+0.026
 splash+0.024
 swim+0.024
 movie+0.023
Neg logit contributions
ross-0.015
Bet-0.015
Nut-0.014
umper-0.014
 knowing-0.013
Token best
Token ID1266
Feature activation-5.90e-03

Pos logit contributions
 sip+0.024
 dip+0.022
 splash+0.021
 tug+0.021
 reel+0.019
Neg logit contributions
inger-0.013
ich-0.013
ross-0.012
 known-0.012
 never-0.011
Token rock
Token ID3881
Feature activation+7.58e-03

Pos logit contributions
ross+0.016
Bet+0.015
inger+0.015
Nut+0.015
umper+0.015
Neg logit contributions
 sip-0.011
 dip-0.011
 swim-0.011
 splash-0.010
 movie-0.010
Token and
Token ID290
Feature activation+3.33e-03

Pos logit contributions
ross+0.012
Bet+0.011
umper+0.011
inger+0.011
Nut+0.011
Neg logit contributions
 sip-0.012
 swim-0.012
 dip-0.012
 splash-0.012
 popcorn-0.011
Token Cathy
Token ID40636
Feature activation-2.01e-02

Pos logit contributions
ross+0.006
umper+0.006
inger+0.006
Bet+0.006
Nut+0.005
Neg logit contributions
 dip-0.005
 sip-0.005
 swim-0.004
 popcorn-0.004
 splash-0.004
Token found
Token ID1043
Feature activation-7.79e-04

Pos logit contributions
 sip+0.032
 dip+0.032
 movie+0.031
 swim+0.030
 popcorn+0.030
Neg logit contributions
ross-0.028
umper-0.027
Bet-0.027
Nut-0.026
inger-0.026
Token a
Token ID257
Feature activation+9.50e-03

Pos logit contributions
 sip+0.001
 dip+0.001
 swim+0.001
 popcorn+0.001
 look+0.001
Neg logit contributions
ross-0.002
umper-0.001
Bet-0.001
inger-0.001
Nut-0.001
Token stick
Token ID4859
Feature activation+3.32e-03

Pos logit contributions
ross+0.017
Bet+0.017
umper+0.016
inger+0.016
Nut+0.016
Neg logit contributions
 sip-0.012
 dip-0.012
 swim-0.011
 splash-0.011
 movie-0.011
Token.
Token ID13
Feature activation+4.64e-04

Pos logit contributions
ross+0.006
Bet+0.005
umper+0.005
inger+0.005
Nut+0.005
Neg logit contributions
 sip-0.005
 dip-0.005
 swim-0.005
 splash-0.004
 popcorn-0.004
Token Then
Token ID3244
Feature activation-4.23e-03

Pos logit contributions
ross+0.001
umper+0.001
inger+0.001
ully+0.001
ydia+0.001
Neg logit contributions
 sip-0.001
 dip-0.001
 swim-0.001
 popcorn-0.001
 splash-0.001
Token,
Token ID11
Feature activation-3.98e-03

Pos logit contributions
 sip+0.006
 dip+0.006
 movie+0.006
 swim+0.006
 splash+0.006
Neg logit contributions
ross-0.007
Bet-0.007
Nut-0.006
umper-0.006
inger-0.006
Token they
Token ID484
Feature activation-1.36e-02

Pos logit contributions
 sip+0.006
 dip+0.006
 swim+0.005
 popcorn+0.005
 splash+0.005
Neg logit contributions
ross-0.007
umper-0.006
inger-0.006
Bet-0.006
Nut-0.006
Token worked
Token ID3111
Feature activation-8.42e-03

Pos logit contributions
 dip+0.019
 sip+0.019
 swim+0.019
 splash+0.018
 popcorn+0.017
Neg logit contributions
ross-0.025
inger-0.024
Bet-0.023
ydia-0.023
umper-0.023
Token very
Token ID845
Feature activation+8.16e-04

Pos logit contributions
ross+0.006
umper+0.005
Bet+0.005
inger+0.005
Nut+0.005
Neg logit contributions
 swim-0.004
 sip-0.004
 splash-0.004
 popcorn-0.004
 dip-0.004
Token sad
Token ID6507
Feature activation-3.79e-03

Pos logit contributions
ross+0.001
inger+0.001
umper+0.001
Bet+0.001
Nut+0.001
Neg logit contributions
 dip-0.001
 sip-0.001
 movie-0.001
 popcorn-0.001
 swim-0.001
Token and
Token ID290
Feature activation+4.95e-03

Pos logit contributions
 dip+0.008
 sip+0.008
 movie+0.007
 picnic+0.007
 popcorn+0.007
Neg logit contributions
ross-0.003
 knowing-0.003
umper-0.003
Bet-0.003
Nut-0.003
Token scared
Token ID12008
Feature activation+4.61e-03

Pos logit contributions
ross+0.008
Bet+0.008
umper+0.008
inger+0.008
Nut+0.008
Neg logit contributions
 sip-0.007
 dip-0.007
 swim-0.007
 splash-0.007
 popcorn-0.007
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
ross+0.008
Bet+0.008
umper+0.008
inger+0.008
Nut+0.008
Neg logit contributions
 sip-0.006
 dip-0.006
 swim-0.006
 splash-0.006
 popcorn-0.005
Token They
Token ID1119
Feature activation+2.00e-02

Pos logit contributions
ross+0.055
umper+0.053
inger+0.052
ppa+0.050
eh+0.049
Neg logit contributions
 swim-0.021
 sip-0.021
 splash-0.020
 dip-0.019
 look-0.019
Token wished
Token ID16555
Feature activation+2.56e-02

Pos logit contributions
ross+0.038
inger+0.036
umper+0.035
Bet+0.034
orns+0.033
Neg logit contributions
 sip-0.028
 swim-0.028
 dip-0.027
 look-0.027
 splash-0.027
Token they
Token ID484
Feature activation+1.23e-02

Pos logit contributions
inger+0.060
ross+0.059
umper+0.059
Bet+0.057
amed+0.057
Neg logit contributions
 swim-0.023
 splash-0.020
 dip-0.020
 sip-0.020
 popcorn-0.019
Token had
Token ID550
Feature activation+2.11e-02

Pos logit contributions
ross+0.024
inger+0.023
umper+0.022
Bet+0.022
ydia+0.021
Neg logit contributions
 swim-0.016
 sip-0.015
 look-0.015
 dip-0.015
 drive-0.015
Token never
Token ID1239
Feature activation+1.91e-02

Pos logit contributions
ross+0.029
umper+0.028
Bet+0.028
inger+0.028
Nut+0.026
Neg logit contributions
 dip-0.036
 sip-0.036
 swim-0.036
 popcorn-0.034
 splash-0.034
Token played
Token ID2826
Feature activation+4.17e-02

Pos logit contributions
ross+0.022
umper+0.021
Bet+0.021
Nut+0.020
inger+0.020
Neg logit contributions
 sip-0.036
 dip-0.036
 popcorn-0.034
 movie-0.034
 splash-0.034
Token inside
Token ID2641
Feature activation-1.85e-02

Pos logit contributions
 dip+0.021
 sip+0.021
 swim+0.020
 movie+0.020
 popcorn+0.020
Neg logit contributions
ross-0.017
Bet-0.017
inger-0.016
umper-0.016
Nut-0.016
Token and
Token ID290
Feature activation-2.37e-02

Pos logit contributions
 sip+0.031
 dip+0.030
 swim+0.029
 splash+0.029
 popcorn+0.028
Neg logit contributions
ross-0.029
umper-0.027
Bet-0.027
inger-0.027
Nut-0.026
Token got
Token ID1392
Feature activation-4.05e-02

Pos logit contributions
 dip+0.038
 movie+0.038
 Today+0.037
 sip+0.037
 popcorn+0.036
Neg logit contributions
Bet-0.030
ross-0.028
umper-0.027
Nut-0.027
ppa-0.027
Token some
Token ID617
Feature activation-3.40e-02

Pos logit contributions
 dip+0.064
 movie+0.064
 Today+0.062
 sip+0.062
 drive+0.059
Neg logit contributions
amed-0.049
 known-0.048
Bet-0.047
umper-0.047
Nut-0.045
Token bread
Token ID8509
Feature activation-1.45e-02

Pos logit contributions
 dip+0.038
 argue+0.038
 sip+0.036
 swim+0.035
 sigh+0.034
Neg logit contributions
ross-0.057
orns-0.057
Bet-0.057
Nut-0.056
umper-0.056
Token and
Token ID290
Feature activation-2.10e-02

Pos logit contributions
 sip+0.023
 dip+0.022
 swim+0.022
 splash+0.021
 popcorn+0.021
Neg logit contributions
ross-0.023
umper-0.022
Bet-0.022
inger-0.021
Nut-0.021
Token cheese
Token ID9891
Feature activation-1.06e-02

Pos logit contributions
 dip+0.025
 sip+0.025
 movie+0.024
 swim+0.023
 splash+0.023
Neg logit contributions
ross-0.036
Bet-0.036
Nut-0.035
umper-0.034
inger-0.034
Token.
Token ID13
Feature activation+3.57e-03

Pos logit contributions
 sip+0.014
 dip+0.013
 swim+0.013
 splash+0.013
 popcorn+0.012
Neg logit contributions
ross-0.019
umper-0.019
Bet-0.019
inger-0.018
Nut-0.018
Token They
Token ID1119
Feature activation-6.83e-03

Pos logit contributions
ross+0.006
umper+0.006
Bet+0.006
inger+0.006
Nut+0.006
Neg logit contributions
 sip-0.005
 dip-0.005
 swim-0.005
 splash-0.004
 popcorn-0.004
Token ran
Token ID4966
Feature activation-1.25e-02

Pos logit contributions
 sip+0.010
 dip+0.009
 swim+0.009
 splash+0.009
 popcorn+0.009
Neg logit contributions
ross-0.013
inger-0.012
umper-0.012
Bet-0.012
Nut-0.012
Token back
Token ID736
Feature activation-2.47e-02

Pos logit contributions
 dip+0.021
 sip+0.021
 swim+0.020
 movie+0.020
 splash+0.019
Neg logit contributions
ross-0.018
Bet-0.017
inger-0.016
umper-0.016
Nut-0.016
Token a
Token ID257
Feature activation-1.33e-02

Pos logit contributions
 sip+0.027
 dip+0.027
 swim+0.027
 splash+0.026
 popcorn+0.026
Neg logit contributions
ross-0.046
inger-0.044
Nut-0.044
umper-0.044
Bet-0.044
Token 3
Token ID513
Feature activation-9.61e-03

Pos logit contributions
 sip+0.018
 dip+0.018
 swim+0.017
 popcorn+0.017
 splash+0.017
Neg logit contributions
ross-0.023
Bet-0.022
umper-0.022
inger-0.021
Nut-0.021
Token year
Token ID614
Feature activation-2.79e-02

Pos logit contributions
 dip+0.017
 sip+0.017
 swim+0.016
 splash+0.015
 popcorn+0.015
Neg logit contributions
ross-0.013
Bet-0.012
umper-0.012
inger-0.012
Nut-0.012
Token old
Token ID1468
Feature activation-2.13e-02

Pos logit contributions
 sip+0.047
 dip+0.046
 swim+0.044
 splash+0.043
 popcorn+0.043
Neg logit contributions
ross-0.040
umper-0.037
inger-0.037
Bet-0.037
Nut-0.035
Token kid
Token ID5141
Feature activation-1.32e-02

Pos logit contributions
 sip+0.028
 dip+0.028
 swim+0.027
 splash+0.026
 popcorn+0.026
Neg logit contributions
ross-0.038
Bet-0.037
umper-0.036
inger-0.036
Nut-0.036
Token who
Token ID508
Feature activation-1.29e-02

Pos logit contributions
 sip+0.018
 dip+0.018
 swim+0.018
 splash+0.017
 movie+0.017
Neg logit contributions
ross-0.023
inger-0.022
Bet-0.022
umper-0.021
Nut-0.021
Token lived
Token ID5615
Feature activation+1.22e-03

Pos logit contributions
 dip+0.024
 sip+0.024
 swim+0.024
 splash+0.024
 popcorn+0.023
Neg logit contributions
ross-0.016
Bet-0.015
inger-0.015
umper-0.015
Nut-0.014
Token with
Token ID351
Feature activation-8.69e-03

Pos logit contributions
ross+0.002
Bet+0.002
umper+0.002
Nut+0.002
inger+0.002
Neg logit contributions
 swim-0.002
 sip-0.002
 dip-0.002
 popcorn-0.002
 splash-0.002
Token her
Token ID607
Feature activation-1.97e-02

Pos logit contributions
 sip+0.017
 dip+0.017
 swim+0.016
 splash+0.016
 movie+0.016
Neg logit contributions
Bet-0.009
umper-0.009
ross-0.009
Nut-0.009
ydia-0.009
Token mom
Token ID1995
Feature activation-4.16e-02

Pos logit contributions
 sip+0.026
 dip+0.026
 swim+0.025
 splash+0.024
 popcorn+0.024
Neg logit contributions
ross-0.036
Bet-0.034
umper-0.034
inger-0.034
Nut-0.033
Token and
Token ID290
Feature activation-1.80e-02

Pos logit contributions
 sip+0.063
 dip+0.063
 swim+0.061
 splash+0.059
 popcorn+0.059
Neg logit contributions
ross-0.066
Bet-0.062
umper-0.062
inger-0.061
Nut-0.060
Token!
Token ID0
Feature activation+2.53e-04

Pos logit contributions
ross+0.010
Bet+0.010
umper+0.010
Nut+0.009
inger+0.009
Neg logit contributions
 sip-0.011
 dip-0.011
 swim-0.010
 splash-0.010
 movie-0.010
Token What
Token ID1867
Feature activation-5.77e-03

Pos logit contributions
ross+0.000
inger+0.000
umper+0.000
Bet+0.000
Nut+0.000
Neg logit contributions
 sip-0.000
 dip-0.000
 swim-0.000
 splash-0.000
 popcorn-0.000
Token are
Token ID389
Feature activation-5.48e-03

Pos logit contributions
 sip+0.008
 dip+0.008
 splash+0.007
 swim+0.007
 popcorn+0.007
Neg logit contributions
ross-0.010
Bet-0.010
umper-0.009
ydia-0.009
inger-0.009
Token you
Token ID345
Feature activation+1.01e-02

Pos logit contributions
 sip+0.008
 dip+0.008
 swim+0.007
 splash+0.007
 popcorn+0.007
Neg logit contributions
ross-0.009
Bet-0.009
umper-0.009
inger-0.009
Nut-0.009
Token doing
Token ID1804
Feature activation+1.96e-02

Pos logit contributions
ross+0.017
Bet+0.016
Nut+0.016
inger+0.016
umper+0.016
Neg logit contributions
 swim-0.015
 dip-0.015
 sip-0.014
 splash-0.014
 look-0.014
Token?
Token ID30
Feature activation-1.37e-03

Pos logit contributions
ross+0.031
umper+0.030
Bet+0.030
inger+0.030
Nut+0.029
Neg logit contributions
 swim-0.030
 dip-0.029
 sip-0.029
 splash-0.029
 popcorn-0.028
Tokenâ
Token ID22940
Feature activation-1.06e-02

Pos logit contributions
 sip+0.002
 dip+0.002
 swim+0.002
 splash+0.002
 popcorn+0.001
Neg logit contributions
ross-0.003
inger-0.003
Bet-0.002
umper-0.002
Nut-0.002
Token€
Token ID26391
Feature activation+1.43e-02

Pos logit contributions
 dip+0.018
 sip+0.018
 swim+0.018
 popcorn+0.017
 splash+0.017
Neg logit contributions
ross-0.015
inger-0.014
Bet-0.014
umper-0.014
Nut-0.014
Token
Token ID198
Feature activation+4.24e-03

Pos logit contributions
ross+0.024
umper+0.023
inger+0.021
Bet+0.021
Nut+0.021
Neg logit contributions
 sip-0.021
 dip-0.020
 swim-0.020
 splash-0.019
 movie-0.019
Token
Token ID198
Feature activation+3.42e-03

Pos logit contributions
ross+0.008
umper+0.008
ully+0.008
inger+0.008
orns+0.007
Neg logit contributions
 sip-0.005
 swim-0.005
 splash-0.004
 sigh-0.004
 dip-0.004
TokenThe
Token ID464
Feature activation+1.94e-02

Pos logit contributions
ross+0.004
inger+0.004
umper+0.004
ully+0.004
iddles+0.004
Neg logit contributions
 sip-0.006
 dip-0.006
 swim-0.006
 splash-0.006
 popcorn-0.006
Token and
Token ID290
Feature activation-8.42e-03

Pos logit contributions
 movie+0.024
 popcorn+0.024
 sip+0.024
 dip+0.023
 anticipation+0.022
Neg logit contributions
ross-0.023
umper-0.022
inger-0.021
Nut-0.021
Bet-0.020
Token your
Token ID534
Feature activation+5.41e-03

Pos logit contributions
 sip+0.008
 dip+0.008
 swim+0.008
 splash+0.008
 popcorn+0.007
Neg logit contributions
ross-0.018
umper-0.017
Bet-0.017
inger-0.017
Nut-0.017
Token dad
Token ID9955
Feature activation-2.88e-02

Pos logit contributions
ross+0.010
umper+0.010
Bet+0.009
inger+0.009
Nut+0.009
Neg logit contributions
 sip-0.007
 dip-0.007
 swim-0.007
 splash-0.007
 movie-0.007
Token fix
Token ID4259
Feature activation+8.41e-03

Pos logit contributions
 sip+0.044
 dip+0.044
 movie+0.042
 splash+0.041
 popcorn+0.041
Neg logit contributions
ross-0.040
umper-0.039
inger-0.038
ppa-0.038
Nut-0.035
Token it
Token ID340
Feature activation-2.37e-02

Pos logit contributions
ross+0.015
Bet+0.014
umper+0.014
inger+0.013
Nut+0.013
Neg logit contributions
 dip-0.012
 sip-0.012
 swim-0.012
 popcorn-0.012
 splash-0.011
Token.
Token ID13
Feature activation-2.37e-03

Pos logit contributions
 dip+0.035
 sip+0.035
 swim+0.033
 splash+0.032
 movie+0.032
Neg logit contributions
ross-0.038
inger-0.035
umper-0.035
Bet-0.035
Nut-0.034
Token And
Token ID843
Feature activation-4.26e-03

Pos logit contributions
 sip+0.004
 dip+0.004
 swim+0.003
 splash+0.003
 popcorn+0.003
Neg logit contributions
ross-0.004
Bet-0.004
umper-0.004
Nut-0.004
inger-0.004
Token I
Token ID314
Feature activation+3.96e-03

Pos logit contributions
 sip+0.006
 dip+0.006
 movie+0.006
 swim+0.006
 popcorn+0.006
Neg logit contributions
ross-0.007
Bet-0.006
umper-0.006
Nut-0.006
inger-0.006
Token promise
Token ID6991
Feature activation-1.01e-02

Pos logit contributions
ross+0.007
Bet+0.007
umper+0.007
Nut+0.006
inger+0.006
Neg logit contributions
 dip-0.005
 sip-0.005
 swim-0.005
 popcorn-0.005
 movie-0.005
Token,
Token ID11
Feature activation+1.87e-02

Pos logit contributions
 sip+0.017
 dip+0.017
 movie+0.016
 popcorn+0.016
 swim+0.016
Neg logit contributions
ross-0.013
Nut-0.013
Bet-0.012
umper-0.012
inger-0.012
Token I
Token ID314
Feature activation+6.44e-03

Pos logit contributions
ross+0.032
umper+0.030
Bet+0.030
inger+0.030
Nut+0.029
Neg logit contributions
 sip-0.027
 dip-0.027
 swim-0.026
 splash-0.026
 popcorn-0.025
Token on
Token ID319
Feature activation+3.72e-03

Pos logit contributions
ross+0.005
Bet+0.005
umper+0.005
inger+0.005
Nut+0.005
Neg logit contributions
 sip-0.005
 dip-0.005
 swim-0.005
 splash-0.004
 popcorn-0.004
Token the
Token ID262
Feature activation+8.10e-03

Pos logit contributions
ross+0.004
Nut+0.004
umper+0.004
inger+0.004
Bet+0.004
Neg logit contributions
 sip-0.007
 dip-0.007
 movie-0.007
 splash-0.006
 swim-0.006
Token coat
Token ID13209
Feature activation+2.30e-02

Pos logit contributions
ross+0.017
Bet+0.016
umper+0.016
inger+0.016
Nut+0.016
Neg logit contributions
 dip-0.008
 sip-0.008
 swim-0.008
 splash-0.008
 popcorn-0.008
Token and
Token ID290
Feature activation+2.30e-03

Pos logit contributions
ross+0.040
Bet+0.038
umper+0.038
inger+0.037
ydia+0.036
Neg logit contributions
 dip-0.032
 sip-0.032
 look-0.032
 swim-0.032
 drive-0.031
Token went
Token ID1816
Feature activation-4.45e-03

Pos logit contributions
ross+0.004
Bet+0.004
umper+0.004
inger+0.003
Nut+0.003
Neg logit contributions
 sip-0.003
 dip-0.003
 swim-0.003
 splash-0.003
 popcorn-0.003
Token outside
Token ID2354
Feature activation-8.93e-03

Pos logit contributions
 sip+0.007
 dip+0.007
 movie+0.007
 popcorn+0.007
 swim+0.007
Neg logit contributions
ross-0.006
Bet-0.006
umper-0.006
inger-0.006
Nut-0.006
Token to
Token ID284
Feature activation-1.03e-02

Pos logit contributions
 sip+0.017
 dip+0.017
 popcorn+0.016
 picnic+0.016
 movie+0.016
Neg logit contributions
ross-0.008
but-0.008
 knowing-0.008
Bet-0.008
umper-0.008
Token play
Token ID711
Feature activation+4.17e-02

Pos logit contributions
 popcorn+0.010
 movie+0.010
ksh+0.010
 sip+0.010
 argue+0.009
Neg logit contributions
umper-0.019
Bet-0.018
Nut-0.018
eh-0.017
 Bree-0.017
Token.
Token ID13
Feature activation+1.15e-03

Pos logit contributions
ross+0.063
Bet+0.060
umper+0.059
Nut+0.059
inger+0.058
Neg logit contributions
 dip-0.064
 sip-0.063
 swim-0.059
 popcorn-0.059
 movie-0.059
Token The
Token ID383
Feature activation+1.02e-02

Pos logit contributions
Bet+0.001
Nut+0.001
ross+0.001
umper+0.001
inger+0.001
Neg logit contributions
 sip-0.002
 dip-0.002
 popcorn-0.002
 swim-0.002
 movie-0.002
Token sun
Token ID4252
Feature activation-1.76e-02

Pos logit contributions
ross+0.021
umper+0.021
Bet+0.021
inger+0.020
Nut+0.020
Neg logit contributions
 dip-0.010
 sip-0.010
 swim-0.010
 splash-0.010
 popcorn-0.009
Token play
Token ID711
Feature activation+1.97e-02

Pos logit contributions
 sip+0.012
 movie+0.011
 popcorn+0.011
 dip+0.011
 sigh+0.011
Neg logit contributions
Bet-0.029
umper-0.029
ross-0.029
Nut-0.029
ully-0.028
Token in
Token ID287
Feature activation-2.03e-02

Pos logit contributions
ross+0.030
Bet+0.028
umper+0.028
inger+0.028
Nut+0.027
Neg logit contributions
 sip-0.031
 dip-0.031
 swim-0.030
 splash-0.029
 popcorn-0.029
Token the
Token ID262
Feature activation-8.18e-03

Pos logit contributions
 sip+0.040
 dip+0.039
 sigh+0.038
 movie+0.036
 swim+0.036
Neg logit contributions
Bet-0.020
Nut-0.018
umper-0.018
Jan-0.017
ross-0.017
Token big
Token ID1263
Feature activation-3.55e-02

Pos logit contributions
 sip+0.014
 dip+0.013
 sigh+0.013
 swim+0.013
 argue+0.012
Neg logit contributions
Bet-0.011
ross-0.011
umper-0.011
Nut-0.011
inger-0.010
Token park
Token ID3952
Feature activation+2.03e-02

Pos logit contributions
 sip+0.059
 dip+0.058
 swim+0.054
 argue+0.053
 sigh+0.053
Neg logit contributions
Bet-0.044
orns-0.042
umper-0.042
ross-0.040
ase-0.039
Token.
Token ID13
Feature activation-5.58e-02

Pos logit contributions
ross+0.029
Bet+0.027
inger+0.026
umper+0.025
Nut+0.025
Neg logit contributions
 sip-0.032
 dip-0.032
 sigh-0.030
 movie-0.030
 popcorn-0.030
Token There
Token ID1318
Feature activation-1.83e-02

Pos logit contributions
 plunge+0.089
 sigh+0.088
 argue+0.088
 tug+0.084
 movie+0.083
Neg logit contributions
ooks-0.057
ily-0.055
Bet-0.052
ross-0.049
urse-0.049
Token were
Token ID547
Feature activation-2.76e-03

Pos logit contributions
 sip+0.029
 dip+0.029
 swim+0.028
 splash+0.028
 popcorn+0.027
Neg logit contributions
ross-0.028
Bet-0.026
umper-0.026
inger-0.026
Nut-0.025
Token many
Token ID867
Feature activation+1.25e-02

Pos logit contributions
 dip+0.004
 sip+0.004
 swim+0.004
 splash+0.004
 popcorn+0.004
Neg logit contributions
ross-0.004
umper-0.004
Bet-0.004
inger-0.004
Nut-0.004
Token things
Token ID1243
Feature activation+9.02e-03

Pos logit contributions
ross+0.021
Bet+0.021
umper+0.020
inger+0.020
Nut+0.020
Neg logit contributions
 sip-0.017
 dip-0.017
 swim-0.016
 splash-0.016
 movie-0.016
Token to
Token ID284
Feature activation-3.04e-03

Pos logit contributions
ross+0.011
umper+0.010
Bet+0.010
inger+0.010
Nut+0.010
Neg logit contributions
 sip-0.016
 dip-0.015
 movie-0.015
 swim-0.015
 popcorn-0.015
Token,
Token ID11
Feature activation+2.04e-02

Pos logit contributions
 dip+0.041
 sip+0.040
 argue+0.040
 movie+0.038
 drive+0.038
Neg logit contributions
ross-0.019
orns-0.017
Bet-0.016
ase-0.015
inger-0.015
Token with
Token ID351
Feature activation-1.65e-02

Pos logit contributions
ross+0.030
umper+0.029
Bet+0.029
inger+0.028
Nut+0.028
Neg logit contributions
 sip-0.033
 dip-0.033
 swim-0.032
 splash-0.031
 popcorn-0.031
Token black
Token ID2042
Feature activation-4.32e-02

Pos logit contributions
 sip+0.020
 dip+0.019
 swim+0.018
 movie+0.018
 argue+0.018
Neg logit contributions
ross-0.029
umper-0.029
Bet-0.028
Nut-0.028
inger-0.027
Token spots
Token ID10222
Feature activation+7.66e-03

Pos logit contributions
 sip+0.064
 dip+0.062
 argue+0.062
 movie+0.060
 walk+0.059
Neg logit contributions
ross-0.062
umper-0.061
orns-0.061
inger-0.058
Nut-0.057
Token.
Token ID13
Feature activation+4.53e-03

Pos logit contributions
ross+0.012
umper+0.011
inger+0.011
Bet+0.011
Nut+0.010
Neg logit contributions
 sip-0.012
 dip-0.012
 movie-0.011
 swim-0.011
 popcorn-0.011
Token It
Token ID632
Feature activation-5.46e-02

Pos logit contributions
ross+0.009
inger+0.009
umper+0.009
ully+0.008
Bet+0.008
Neg logit contributions
 sip-0.006
 dip-0.006
 splash-0.005
 look-0.005
 swim-0.005
Token has
Token ID468
Feature activation-1.12e-02

Pos logit contributions
 anticipation+0.087
 sip+0.086
 picnic+0.083
 dip+0.083
 argue+0.082
Neg logit contributions
py-0.058
 never-0.058
 ruled-0.057
umper-0.056
pie-0.056
Token a
Token ID257
Feature activation-3.49e-02

Pos logit contributions
 sip+0.015
 dip+0.014
 swim+0.014
 splash+0.013
 movie+0.013
Neg logit contributions
ross-0.020
Bet-0.019
umper-0.019
inger-0.019
Nut-0.019
Token long
Token ID890
Feature activation-4.16e-02

Pos logit contributions
 sip+0.046
 dip+0.044
 walk+0.042
 argue+0.041
 movie+0.041
Neg logit contributions
ross-0.053
inger-0.053
Nut-0.052
Bet-0.052
ich-0.051
Token tail
Token ID7894
Feature activation-4.30e-03

Pos logit contributions
 sip+0.065
 dip+0.063
 movie+0.062
 popcorn+0.060
 sigh+0.058
Neg logit contributions
ross-0.060
inger-0.059
Bet-0.054
Nut-0.053
umper-0.052
Token and
Token ID290
Feature activation-1.29e-02

Pos logit contributions
 sip+0.007
 dip+0.007
 movie+0.007
 popcorn+0.007
 swim+0.007
Neg logit contributions
ross-0.006
Bet-0.005
inger-0.005
umper-0.005
Nut-0.005
Token toys
Token ID14958
Feature activation-1.14e-02

Pos logit contributions
 sip+0.029
 dip+0.029
 swim+0.027
 splash+0.026
 movie+0.026
Neg logit contributions
ross-0.050
umper-0.049
inger-0.049
Bet-0.048
Nut-0.048
Token!"
Token ID2474
Feature activation-1.03e-02

Pos logit contributions
 sip+0.016
 dip+0.016
 swim+0.015
 splash+0.015
 popcorn+0.015
Neg logit contributions
ross-0.019
Bet-0.019
umper-0.019
inger-0.018
Nut-0.018
Token he
Token ID339
Feature activation-1.19e-02

Pos logit contributions
 sip+0.013
 swim+0.013
 dip+0.012
 splash+0.012
 popcorn+0.012
Neg logit contributions
ross-0.020
inger-0.019
umper-0.019
Bet-0.018
ully-0.018
Token said
Token ID531
Feature activation-1.07e-02

Pos logit contributions
 sip+0.015
 dip+0.015
 swim+0.015
 splash+0.014
 popcorn+0.014
Neg logit contributions
ross-0.023
Bet-0.022
umper-0.022
inger-0.022
Nut-0.021
Token with
Token ID351
Feature activation-2.23e-02

Pos logit contributions
 dip+0.015
 sip+0.015
 swim+0.014
 movie+0.013
 popcorn+0.013
Neg logit contributions
ross-0.019
Bet-0.017
umper-0.017
inger-0.017
Nut-0.017
Token a
Token ID257
Feature activation-4.90e-02

Pos logit contributions
 dip+0.031
 sip+0.031
 swim+0.030
 splash+0.029
 movie+0.029
Neg logit contributions
ross-0.037
Bet-0.035
umper-0.035
inger-0.034
Nut-0.034
Token big
Token ID1263
Feature activation-5.67e-02

Pos logit contributions
 dip+0.057
 sip+0.057
 swim+0.054
 movie+0.052
 popcorn+0.052
Neg logit contributions
ross-0.091
Bet-0.089
umper-0.087
inger-0.087
Nut-0.085
Token smile
Token ID8212
Feature activation-3.54e-03

Pos logit contributions
 dip+0.062
 sip+0.059
 swim+0.057
 movie+0.056
 popcorn+0.054
Neg logit contributions
ross-0.101
Bet-0.099
inger-0.099
umper-0.098
ydia-0.095
Token.
Token ID13
Feature activation-2.36e-03

Pos logit contributions
 dip+0.005
 sip+0.005
 swim+0.005
 splash+0.005
 popcorn+0.005
Neg logit contributions
ross-0.006
umper-0.005
Bet-0.005
inger-0.005
Nut-0.005
Token
Token ID198
Feature activation-7.23e-03

Pos logit contributions
 sip+0.003
 swim+0.003
 splash+0.003
 sigh+0.002
 dip+0.002
Neg logit contributions
ross-0.005
inger-0.005
umper-0.005
ich-0.004
ully-0.004
Token
Token ID198
Feature activation-5.67e-03

Pos logit contributions
 sip+0.008
 swim+0.008
 movie+0.007
 splash+0.007
 popcorn+0.007
Neg logit contributions
ross-0.015
umper-0.014
inger-0.014
ich-0.014
ully-0.013
Token up
Token ID510
Feature activation-1.11e-02

Pos logit contributions
 sip+0.019
 dip+0.018
 swim+0.018
 popcorn+0.017
 splash+0.017
Neg logit contributions
ross-0.026
Bet-0.025
umper-0.025
inger-0.025
Nut-0.025
Token their
Token ID511
Feature activation-4.48e-02

Pos logit contributions
 sip+0.015
 popcorn+0.014
 look+0.014
 dip+0.014
 search+0.013
Neg logit contributions
ross-0.021
umper-0.021
Nut-0.021
inger-0.020
Bet-0.020
Token room
Token ID2119
Feature activation+2.27e-03

Pos logit contributions
 sip+0.056
 dip+0.055
 splash+0.051
 swim+0.050
 argue+0.049
Neg logit contributions
ross-0.063
eh-0.063
ently-0.059
ich-0.059
inger-0.059
Token and
Token ID290
Feature activation-3.01e-02

Pos logit contributions
umper+0.004
Bet+0.004
Nut+0.004
ross+0.004
inger+0.003
Neg logit contributions
 sip-0.004
 dip-0.003
 swim-0.003
 popcorn-0.003
 look-0.003
Token made
Token ID925
Feature activation-2.11e-02

Pos logit contributions
 sip+0.045
 dip+0.045
 swim+0.043
 splash+0.042
 popcorn+0.042
Neg logit contributions
ross-0.049
Bet-0.047
umper-0.047
inger-0.046
Nut-0.045
Token the
Token ID262
Feature activation-4.94e-02

Pos logit contributions
 sip+0.031
 dip+0.030
 swim+0.029
 splash+0.028
 movie+0.028
Neg logit contributions
ross-0.034
umper-0.033
Bet-0.032
inger-0.032
Nut-0.031
Token beds
Token ID20237
Feature activation-7.75e-03

Pos logit contributions
 sip+0.064
 swim+0.062
 dip+0.061
 argue+0.060
 splash+0.058
Neg logit contributions
ross-0.077
umper-0.072
amed-0.071
anya-0.070
but-0.070
Token look
Token ID804
Feature activation-2.89e-02

Pos logit contributions
 sip+0.011
 dip+0.011
 swim+0.011
 movie+0.010
 popcorn+0.010
Neg logit contributions
ross-0.012
inger-0.011
Bet-0.011
amed-0.011
umper-0.010
Token nice
Token ID3621
Feature activation-2.75e-02

Pos logit contributions
 sip+0.037
 dip+0.037
 swim+0.036
 splash+0.034
 movie+0.034
Neg logit contributions
ross-0.052
umper-0.049
Bet-0.049
inger-0.048
Nut-0.047
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
 argue+0.050
 sip+0.050
 dip+0.049
 swim+0.048
 drive+0.047
Neg logit contributions
ross-0.031
 knowing-0.029
but-0.026
amed-0.025
ier-0.025
Token
Token ID198
Feature activation-1.24e-02

Pos logit contributions
 sip+0.032
 dip+0.031
 swim+0.030
 splash+0.030
 popcorn+0.029
Neg logit contributions
ross-0.037
inger-0.035
umper-0.034
Bet-0.034
Nut-0.034
Token She
Token ID1375
Feature activation+1.84e-02

Pos logit contributions
ross+0.037
inger+0.033
Bet+0.032
umper+0.032
pie+0.031
Neg logit contributions
 dip-0.028
 sip-0.027
 look-0.027
 splash-0.026
 swim-0.026
Token was
Token ID373
Feature activation+5.85e-03

Pos logit contributions
ross+0.031
Bet+0.029
umper+0.029
inger+0.029
Nut+0.028
Neg logit contributions
 sip-0.027
 dip-0.027
 swim-0.026
 splash-0.025
 popcorn-0.025
Token scared
Token ID12008
Feature activation+8.68e-03

Pos logit contributions
ross+0.009
Bet+0.009
umper+0.008
inger+0.008
Nut+0.008
Neg logit contributions
 sip-0.009
 dip-0.009
 swim-0.009
 splash-0.009
 movie-0.008
Token of
Token ID286
Feature activation+1.93e-02

Pos logit contributions
ross+0.012
Bet+0.012
umper+0.012
inger+0.011
Nut+0.011
Neg logit contributions
 sip-0.015
 dip-0.015
 swim-0.014
 splash-0.014
 popcorn-0.014
Token the
Token ID262
Feature activation-4.01e-02

Pos logit contributions
ross+0.032
umper+0.030
Bet+0.030
inger+0.030
Nut+0.029
Neg logit contributions
 dip-0.029
 sip-0.029
 swim-0.028
 popcorn-0.027
 splash-0.027
Token bright
Token ID6016
Feature activation-5.48e-02

Pos logit contributions
 sip+0.054
 dip+0.052
 swim+0.048
 splash+0.045
 dive+0.045
Neg logit contributions
ross-0.063
ully-0.062
umper-0.062
Bet-0.061
ydia-0.061
Token colors
Token ID7577
Feature activation+1.92e-02

Pos logit contributions
 sip+0.081
 dip+0.079
 argue+0.076
 swim+0.075
 tug+0.073
Neg logit contributions
ully-0.075
ina-0.073
ross-0.073
ase-0.072
umper-0.071
Token and
Token ID290
Feature activation+2.40e-02

Pos logit contributions
ross+0.032
Bet+0.031
umper+0.031
Nut+0.030
inger+0.030
Neg logit contributions
 sip-0.028
 dip-0.028
 swim-0.027
 splash-0.026
 popcorn-0.026
Token shapes
Token ID15268
Feature activation+1.85e-02

Pos logit contributions
ross+0.037
umper+0.037
inger+0.036
Bet+0.035
Nut+0.034
Neg logit contributions
 dip-0.038
 sip-0.038
 swim-0.037
 splash-0.037
 look-0.036
Token that
Token ID326
Feature activation+2.07e-03

Pos logit contributions
ross+0.034
Bet+0.033
umper+0.033
inger+0.032
Nut+0.032
Neg logit contributions
 sip-0.024
 dip-0.024
 swim-0.023
 splash-0.022
 popcorn-0.022
Token moved
Token ID3888
Feature activation+1.58e-02

Pos logit contributions
ross+0.004
umper+0.004
inger+0.004
Bet+0.003
Nut+0.003
Neg logit contributions
 sip-0.003
 dip-0.003
 swim-0.003
 splash-0.003
 look-0.003