TOP ACTIVATIONS
MAX = 3.257

trick - or - t reating anymore . She sadly put
the elderly man on a stret cher . She thanked Tim
frustrated and started to f idget . Her mom
with a man on a stret cher . The man 's
said a voice on the other end .
added gentle kisses while smoot hing the baby 's hair .
jar red and bottled and vacuum - se aled and wrapped
One day , when Br idget was walking in the me
my smiled and said there were no monsters . Then she
want to go empty - handed , so she sque aked
- hearted princess named Br idget . She was always calm
a rock and started to bleed . Billy tried to help
asked for a band - aid . Mom cleaned Tom 's
Not usually - they â
Not yet , Alice , â
never ask to play with switches again and never disob ey
shiny and made a z ooming sound . L
and put a band - aid on it . Then we
don 't get a sun burn ." Lily yawn ed and
s bite was not severe . But Tom realized he

MIN ACTIVATIONS
MIN = -4.103

worked hard . The grass ho pper was spoiled and didn
Gr ass ho pper , let â
The nos y grass ho pper hopped over to Tom
." The grass ho pper sighed and decided to
the wardrobe a few days ago , so she opened it
?" The grass ho pper said , " I
so happy that the grass ho pper had said yes .
ried ly , the grass ho pper rushed over and tried
coins that people used long ago . They saw paintings and
her birthday a few days ago . She liked to practice
of animals that lived long ago . They saw shiny rocks
ac orn a few days ago so I could have some
the pigeon all those weeks ago . <|endoftext|> Mike and his
by a famous artist long ago . One
time , not so long ago , there was a big
Daisy had planted it weeks ago , but now she could
But it was so long ago that everything was a bit
an ant and a grass ho pper . The ant was
ancestors who sang it long ago . Would you like to
who had passed away long ago . One day , a

INTERVAL 1.417 - 3.257
CONTAINS 0.913%

." Sue agreed , " That 's a good idea ,
upon a time , there were two friends called Tom and
He was taken to the hospital , but it was too
friends ! <|endoftext|> Once there were two little girls who loved
to the toy shop . But when he saw the prices

INTERVAL -0.423 - 1.417
CONTAINS 77.312%

. He never wanted to do any work .
important to forgive and work together to make things better .
So , Lily and her mom had a bath
're going to stay in a hotel !" Once
It has a lot of memories . But it is not

INTERVAL -2.263 - -0.423
CONTAINS 21.757%

. He said , " Don 't worry ,
shield and the scarf , making holes and r ips .
on his journey home . Jack was so excited to show
flew to a beautiful place far away . Jane and Pete
a time there was a mouse who was very troubled .

INTERVAL -4.103 - -2.263
CONTAINS 0.018%

shared everything , even their sp oons . The end .
" My sp ade is broken , Mom
cal mer ." P aco and Felix ate their
a puzzle , a cr ay on , a dinosaur ,
me ." The cricket ch ir ped and waved back .
Token trick
Token ID6908
Feature activation+5.24e-01

Pos logit contributions
 Wolf+0.040
Mo+0.039
 cub+0.039
 Wilson+0.038
Jo+0.038
Neg logit contributions
ets-0.059
issors-0.056
ocus-0.056
 similarities-0.051
ols-0.050
Token-
Token ID12
Feature activation+7.28e-01

Pos logit contributions
handed+0.012
 Wolf+0.012
 cub+0.011
Mo+0.011
seat+0.011
Neg logit contributions
issors-0.024
ocus-0.024
 similarities-0.024
ets-0.023
 seventeen-0.022
Tokenor
Token ID273
Feature activation+3.15e-01

Pos logit contributions
 cub+0.021
 Wolf+0.020
seat+0.019
 baby+0.019
 therm+0.019
Neg logit contributions
issors-0.029
ocus-0.028
 similarities-0.027
ets-0.026
 seventeen-0.025
Token-
Token ID12
Feature activation+7.30e-01

Pos logit contributions
seat+0.008
 Wolf+0.008
 cub+0.008
 distance+0.008
Mo+0.007
Neg logit contributions
ocus-0.013
issors-0.013
aces-0.013
ets-0.013
 similarities-0.012
Tokent
Token ID83
Feature activation+1.97e-01

Pos logit contributions
 cub+0.021
 Wolf+0.020
seat+0.019
 baby+0.019
 Bear+0.019
Neg logit contributions
issors-0.029
ocus-0.028
 similarities-0.027
ets-0.026
 seventeen-0.025
Tokenreating
Token ID34567
Feature activation+3.22e+00

Pos logit contributions
 Wolf+0.005
 cub+0.005
Mo+0.005
handed+0.005
 Wilson+0.005
Neg logit contributions
ets-0.008
 similarities-0.008
issors-0.008
ocus-0.008
 brushes-0.007
Token anymore
Token ID7471
Feature activation+6.22e-01

Pos logit contributions
 Wolf+0.082
Mo+0.076
 cub+0.074
 therm+0.073
eled+0.072
Neg logit contributions
ets-0.144
issors-0.142
 similarities-0.140
ocus-0.140
aces-0.135
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
rolley+0.010
handed+0.010
 Wolf+0.010
Mo+0.009
hand+0.009
Neg logit contributions
ocus-0.032
 similarities-0.032
ets-0.031
issors-0.031
aces-0.030
Token She
Token ID1375
Feature activation+7.68e-01

Pos logit contributions
burn+0.004
handed+0.004
 Wolf+0.004
Mo+0.003
 therm+0.003
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
ets-0.006
 meanings-0.006
Token sadly
Token ID21098
Feature activation-3.75e-01

Pos logit contributions
handed+0.019
 Wolf+0.019
Mo+0.017
seat+0.017
hand+0.017
Neg logit contributions
ocus-0.033
 similarities-0.033
issors-0.033
ets-0.032
 seventeen-0.031
Token put
Token ID1234
Feature activation-2.64e-02

Pos logit contributions
ocus+0.016
 similarities+0.015
issors+0.015
ets+0.015
 seventeen+0.014
Neg logit contributions
handed-0.010
 Wolf-0.010
rolley-0.009
Mo-0.009
 therm-0.009
Token the
Token ID262
Feature activation-4.71e-01

Pos logit contributions
handed+0.013
 Wolf+0.013
Mo+0.012
rolley+0.012
seat+0.012
Neg logit contributions
issors-0.032
 similarities-0.030
ocus-0.030
ets-0.030
 seventeen-0.030
Token elderly
Token ID13830
Feature activation+9.02e-02

Pos logit contributions
issors+0.017
 similarities+0.017
ocus+0.016
ets+0.016
 seventeen+0.015
Neg logit contributions
Mo-0.015
 Wolf-0.014
handed-0.014
hand-0.014
esh-0.013
Token man
Token ID582
Feature activation-2.72e-01

Pos logit contributions
Mo+0.003
 Rabbit+0.003
 Wolf+0.003
 Bear+0.003
 Bunny+0.003
Neg logit contributions
 similarities-0.003
ocus-0.003
ets-0.003
 ind-0.003
issors-0.003
Token on
Token ID319
Feature activation+6.24e-01

Pos logit contributions
ocus+0.010
issors+0.010
ets+0.010
 similarities+0.010
aces+0.009
Neg logit contributions
 Wolf-0.009
Mo-0.008
handed-0.008
 Wilson-0.008
rolley-0.008
Token a
Token ID257
Feature activation+1.38e-01

Pos logit contributions
handed+0.013
rolley+0.013
burn+0.012
 Wolf+0.012
Mo+0.011
Neg logit contributions
issors-0.029
 similarities-0.028
ocus-0.027
 seventeen-0.027
ets-0.026
Token stret
Token ID5759
Feature activation+3.10e+00

Pos logit contributions
handed+0.004
 Wolf+0.004
Mo+0.004
hand+0.004
seat+0.004
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Tokencher
Token ID2044
Feature activation+7.02e-01

Pos logit contributions
 Wolf+0.097
Mo+0.095
 therm+0.092
 baby+0.092
handed+0.086
Neg logit contributions
ocus-0.112
issors-0.108
 similarities-0.108
ets-0.104
 seventeen-0.103
Token.
Token ID13
Feature activation-7.97e-02

Pos logit contributions
 Wolf+0.012
handed+0.011
Mo+0.011
rolley+0.009
hand+0.009
Neg logit contributions
ets-0.036
issors-0.036
ocus-0.036
aces-0.035
 ind-0.034
Token She
Token ID1375
Feature activation+5.81e-01

Pos logit contributions
issors+0.003
ocus+0.003
 similarities+0.003
ets+0.002
 seventeen+0.002
Neg logit contributions
handed-0.003
burn-0.003
 Wolf-0.003
 cub-0.003
Mo-0.003
Token thanked
Token ID26280
Feature activation-4.41e-01

Pos logit contributions
handed+0.017
 Wolf+0.016
Mo+0.015
hand+0.015
rolley+0.015
Neg logit contributions
ocus-0.023
 similarities-0.022
issors-0.022
ets-0.022
 seventeen-0.021
Token Tim
Token ID5045
Feature activation-7.02e-02

Pos logit contributions
issors+0.018
 similarities+0.018
ocus+0.017
ets+0.017
 seventeen+0.017
Neg logit contributions
handed-0.012
rolley-0.011
 Wolf-0.011
seat-0.011
burn-0.011
Token frustrated
Token ID14718
Feature activation+3.51e-01

Pos logit contributions
issors+0.013
 similarities+0.013
ocus+0.013
ets+0.012
 meanings+0.012
Neg logit contributions
 Wolf-0.007
Mo-0.007
handed-0.007
seat-0.006
hand-0.006
Token and
Token ID290
Feature activation+2.09e-01

Pos logit contributions
handed+0.008
Mo+0.008
 Wolf+0.008
burn+0.007
rolley+0.007
Neg logit contributions
ets-0.017
ocus-0.016
issors-0.016
aces-0.015
 similarities-0.015
Token started
Token ID2067
Feature activation+6.93e-01

Pos logit contributions
 Wolf+0.005
handed+0.005
 cub+0.005
 anyway+0.005
 baby+0.004
Neg logit contributions
issors-0.009
ocus-0.009
 similarities-0.009
ets-0.009
 seventeen-0.009
Token to
Token ID284
Feature activation-1.55e-01

Pos logit contributions
handed+0.025
rolley+0.025
Mo+0.025
 Wolf+0.025
hand+0.023
Neg logit contributions
 similarities-0.022
ocus-0.021
issors-0.021
ets-0.019
 meanings-0.019
Token f
Token ID277
Feature activation+1.40e+00

Pos logit contributions
issors+0.006
 similarities+0.006
ocus+0.006
ets+0.005
 seventeen+0.005
Neg logit contributions
handed-0.005
 Wolf-0.005
Mo-0.005
hand-0.004
rolley-0.004
Tokenidget
Token ID17484
Feature activation+3.07e+00

Pos logit contributions
handed+0.036
 Wolf+0.034
 anyway+0.032
rolley+0.031
Mo+0.031
Neg logit contributions
 similarities-0.063
ocus-0.061
issors-0.061
 seventeen-0.059
ets-0.058
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
handed+0.078
 clearing+0.076
Mo+0.073
 continuing+0.071
 Wolf+0.071
Neg logit contributions
ocus-0.126
issors-0.123
ets-0.123
aces-0.121
ems-0.117
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
 cub+0.000
Mo+0.000
burn+0.000
Neg logit contributions
issors-0.001
 similarities-0.001
ocus-0.001
ets-0.001
 ind-0.001
Token
Token ID198
Feature activation+6.00e-01

Pos logit contributions
handed+0.006
burn+0.006
 therm+0.006
 Wolf+0.006
 cub+0.006
Neg logit contributions
issors-0.009
ocus-0.008
 similarities-0.008
ets-0.008
apes-0.008
TokenHer
Token ID9360
Feature activation+8.67e-01

Pos logit contributions
 Wolf+0.014
handed+0.014
Mo+0.012
 cub+0.012
 anyway+0.012
Neg logit contributions
ocus-0.028
issors-0.028
 similarities-0.027
ets-0.027
 seventeen-0.026
Token mom
Token ID1995
Feature activation-2.82e-01

Pos logit contributions
 Wolf+0.016
handed+0.015
 baby+0.014
 cub+0.014
 therm+0.014
Neg logit contributions
ocus-0.045
issors-0.045
 similarities-0.044
ets-0.044
 seventeen-0.043
Token with
Token ID351
Feature activation-4.09e-01

Pos logit contributions
handed+0.004
 Wolf+0.004
Mo+0.004
rolley+0.004
burn+0.004
Neg logit contributions
ocus-0.004
issors-0.004
 similarities-0.004
ets-0.004
apes-0.004
Token a
Token ID257
Feature activation-2.26e-01

Pos logit contributions
issors+0.018
 similarities+0.018
 seventeen+0.017
ets+0.017
 ind+0.016
Neg logit contributions
handed-0.010
Mo-0.009
 Wolf-0.009
rolley-0.009
hand-0.009
Token man
Token ID582
Feature activation-1.38e-01

Pos logit contributions
issors+0.009
ocus+0.009
 similarities+0.009
ets+0.008
 seventeen+0.008
Neg logit contributions
handed-0.007
 Wolf-0.007
Mo-0.006
hand-0.006
 cub-0.006
Token on
Token ID319
Feature activation+9.63e-01

Pos logit contributions
ocus+0.006
issors+0.006
ets+0.006
 similarities+0.006
 ind+0.006
Neg logit contributions
Mo-0.003
 Wolf-0.003
handed-0.003
rolley-0.003
 Wilson-0.003
Token a
Token ID257
Feature activation+1.00e-01

Pos logit contributions
handed+0.022
rolley+0.021
 Wolf+0.019
Mo+0.019
seat+0.019
Neg logit contributions
issors-0.043
 similarities-0.043
ocus-0.041
 seventeen-0.041
 ind-0.040
Token stret
Token ID5759
Feature activation+3.04e+00

Pos logit contributions
handed+0.003
 Wolf+0.003
Mo+0.003
hand+0.002
rolley+0.002
Neg logit contributions
issors-0.004
ocus-0.004
 similarities-0.004
 seventeen-0.004
ets-0.004
Tokencher
Token ID2044
Feature activation+6.82e-01

Pos logit contributions
 Wolf+0.093
Mo+0.093
 baby+0.089
 therm+0.089
handed+0.085
Neg logit contributions
ocus-0.110
issors-0.107
 similarities-0.103
 seventeen-0.101
ets-0.101
Token.
Token ID13
Feature activation-1.73e-01

Pos logit contributions
handed+0.012
 Wolf+0.012
Mo+0.011
 Doctor+0.010
hand+0.010
Neg logit contributions
issors-0.034
ets-0.034
ocus-0.034
aces-0.033
 ind-0.032
Token The
Token ID383
Feature activation+1.35e-01

Pos logit contributions
issors+0.006
ocus+0.006
 similarities+0.006
 seventeen+0.006
ets+0.006
Neg logit contributions
handed-0.006
 Wolf-0.005
Mo-0.005
burn-0.005
hand-0.005
Token man
Token ID582
Feature activation-8.34e-01

Pos logit contributions
Mo+0.004
handed+0.004
 Wilson+0.004
 Willie+0.004
 Rabbit+0.004
Neg logit contributions
 similarities-0.005
issors-0.005
 seventeen-0.004
ets-0.004
 brushes-0.004
Token's
Token ID338
Feature activation-5.12e-01

Pos logit contributions
ocus+0.034
issors+0.034
 similarities+0.034
ets+0.032
 seventeen+0.032
Neg logit contributions
handed-0.023
 Wolf-0.022
Mo-0.021
seat-0.020
rolley-0.020
Token said
Token ID531
Feature activation+7.28e-01

Pos logit contributions
handed+0.007
 Wolf+0.006
rolley+0.006
hand+0.006
seat+0.006
Neg logit contributions
issors-0.010
ocus-0.009
 similarities-0.009
 ind-0.009
ets-0.009
Token a
Token ID257
Feature activation+2.41e-01

Pos logit contributions
rolley+0.025
handed+0.024
seat+0.023
Mo+0.021
hand+0.021
Neg logit contributions
issors-0.023
 ind-0.023
 similarities-0.021
ige-0.020
 draw-0.020
Token voice
Token ID3809
Feature activation+1.06e+00

Pos logit contributions
handed+0.008
 Wolf+0.008
Mo+0.007
eled+0.007
rolley+0.007
Neg logit contributions
 seventeen-0.008
 similarities-0.008
 ind-0.008
ocus-0.008
issors-0.008
Token on
Token ID319
Feature activation+1.06e+00

Pos logit contributions
handed+0.021
 Wolf+0.020
Mo+0.020
rolley+0.020
burn+0.017
Neg logit contributions
ets-0.050
 ind-0.049
ocus-0.049
issors-0.049
ols-0.047
Token the
Token ID262
Feature activation+7.71e-01

Pos logit contributions
handed+0.027
rolley+0.024
seat+0.023
hand+0.022
 Wolf+0.021
Neg logit contributions
issors-0.048
 similarities-0.047
ocus-0.045
 ind-0.044
ets-0.044
Token other
Token ID584
Feature activation+2.95e+00

Pos logit contributions
 Wolf+0.023
handed+0.023
Mo+0.022
 cub+0.022
 anyway+0.021
Neg logit contributions
issors-0.030
ocus-0.030
 similarities-0.029
ets-0.028
 seventeen-0.028
Token end
Token ID886
Feature activation+1.70e+00

Pos logit contributions
handed+0.068
 Wolf+0.066
Mo+0.064
burn+0.059
seat+0.059
Neg logit contributions
issors-0.139
ets-0.134
 similarities-0.133
ocus-0.132
 ind-0.126
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
handed+0.019
 Wolf+0.019
Mo+0.015
 cub+0.015
 therm+0.014
Neg logit contributions
ocus-0.098
issors-0.097
 similarities-0.096
ets-0.094
 seventeen-0.093
Token
Token ID220
Feature activation+1.09e+00

Pos logit contributions
handed+0.006
burn+0.005
rolley+0.005
 Wolf+0.005
Mo+0.005
Neg logit contributions
issors-0.008
ocus-0.008
 similarities-0.007
 ind-0.007
 seventeen-0.007
Token
Token ID198
Feature activation+3.03e-01

Pos logit contributions
handed+0.027
 elf+0.027
 cub+0.027
 Wolf+0.027
 therm+0.027
Neg logit contributions
issors-0.048
ocus-0.046
 similarities-0.042
apes-0.042
ets-0.042
Token
Token ID198
Feature activation+4.81e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.006
burn+0.005
 therm+0.005
Neg logit contributions
issors-0.015
ocus-0.015
 similarities-0.014
 seventeen-0.014
ets-0.014
Token added
Token ID2087
Feature activation+2.32e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
rolley+0.002
Mo+0.002
 anyways+0.002
Neg logit contributions
 similarities-0.003
ocus-0.003
 ind-0.003
ets-0.003
 draws-0.003
Token gentle
Token ID10296
Feature activation+8.67e-01

Pos logit contributions
handed+0.005
 Wolf+0.005
Mo+0.004
 cub+0.004
seat+0.004
Neg logit contributions
ocus-0.011
 similarities-0.011
issors-0.011
ets-0.011
 seventeen-0.011
Token kisses
Token ID36544
Feature activation+2.10e+00

Pos logit contributions
 Wolf+0.030
handed+0.030
 cub+0.029
 baby+0.028
 therm+0.028
Neg logit contributions
issors-0.030
ocus-0.030
 similarities-0.029
ets-0.028
 seventeen-0.027
Token while
Token ID981
Feature activation-2.91e-01

Pos logit contributions
handed+0.051
 Wolf+0.046
Mo+0.044
seat+0.042
 cub+0.042
Neg logit contributions
issors-0.094
 similarities-0.094
ets-0.094
ocus-0.093
 ind-0.089
Token smoot
Token ID32746
Feature activation+5.50e-01

Pos logit contributions
 similarities+0.012
ocus+0.012
issors+0.012
 ind+0.012
 seventeen+0.011
Neg logit contributions
handed-0.009
rolley-0.008
seat-0.007
esh-0.007
hand-0.007
Tokenhing
Token ID722
Feature activation+2.94e+00

Pos logit contributions
 Wolf+0.017
handed+0.017
 cub+0.016
 baby+0.016
 anyway+0.016
Neg logit contributions
ocus-0.021
issors-0.021
ets-0.020
 similarities-0.020
 seventeen-0.019
Token the
Token ID262
Feature activation-2.93e-01

Pos logit contributions
 Wolf+0.091
handed+0.091
 cub+0.085
Mo+0.085
 therm+0.084
Neg logit contributions
issors-0.111
ocus-0.111
 similarities-0.110
ets-0.105
 seventeen-0.103
Token baby
Token ID5156
Feature activation+6.24e-01

Pos logit contributions
 similarities+0.015
issors+0.015
 meanings+0.014
ocus+0.014
 seventeen+0.014
Neg logit contributions
handed-0.004
Mo-0.004
 Wolf-0.004
 able-0.004
 anyway-0.004
Token's
Token ID338
Feature activation-3.81e-01

Pos logit contributions
handed+0.017
Mo+0.017
Jon+0.016
Son+0.016
rolley+0.016
Neg logit contributions
ets-0.024
ocus-0.024
 similarities-0.024
aces-0.024
 meanings-0.023
Token hair
Token ID4190
Feature activation-3.62e-01

Pos logit contributions
issors+0.013
ocus+0.013
 similarities+0.013
ets+0.012
 seventeen+0.012
Neg logit contributions
handed-0.013
 Wolf-0.013
Mo-0.013
 cub-0.012
 anyway-0.012
Token.
Token ID13
Feature activation-2.18e-02

Pos logit contributions
ocus+0.019
ets+0.019
issors+0.019
 similarities+0.019
 ind+0.018
Neg logit contributions
 Wolf-0.006
handed-0.006
Mo-0.005
 cub-0.005
rolley-0.005
Token jar
Token ID17379
Feature activation+7.31e-02

Pos logit contributions
 Wolf+0.014
handed+0.014
 cub+0.013
Mo+0.013
 baby+0.013
Neg logit contributions
issors-0.020
ocus-0.020
 similarities-0.020
ets-0.019
 seventeen-0.019
Tokenred
Token ID445
Feature activation+3.97e-01

Pos logit contributions
 Wolf+0.002
Mo+0.001
handed+0.001
 cub+0.001
 Wilson+0.001
Neg logit contributions
ets-0.004
ocus-0.003
issors-0.003
 similarities-0.003
aces-0.003
Token and
Token ID290
Feature activation+1.05e-01

Pos logit contributions
 Wolf+0.008
handed+0.008
Mo+0.007
seat+0.007
rolley+0.007
Neg logit contributions
 similarities-0.019
ocus-0.019
ets-0.019
issors-0.018
 seventeen-0.018
Token bottled
Token ID34123
Feature activation-8.82e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
 cub+0.003
Mo+0.003
 anyway+0.003
Neg logit contributions
ocus-0.004
issors-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Token and
Token ID290
Feature activation-1.07e-01

Pos logit contributions
issors+0.043
ocus+0.043
 similarities+0.042
ets+0.041
 seventeen+0.040
Neg logit contributions
 Wolf-0.018
handed-0.018
 cub-0.016
 baby-0.016
Mo-0.016
Token vacuum
Token ID17076
Feature activation+2.92e+00

Pos logit contributions
issors+0.004
ocus+0.004
 similarities+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.003
handed-0.003
 cub-0.003
Mo-0.003
 anyway-0.003
Token-
Token ID12
Feature activation+6.60e-01

Pos logit contributions
 Wolf+0.085
handed+0.084
Mo+0.080
 cub+0.080
 therm+0.077
Neg logit contributions
ets-0.116
issors-0.112
ocus-0.110
 similarities-0.110
 seventeen-0.103
Tokense
Token ID325
Feature activation+6.15e-01

Pos logit contributions
 Wolf+0.019
 cub+0.017
seat+0.017
 baby+0.017
 therm+0.017
Neg logit contributions
ocus-0.027
issors-0.027
 similarities-0.026
ets-0.026
 seventeen-0.025
Tokenaled
Token ID3021
Feature activation+1.44e+00

Pos logit contributions
 Wolf+0.016
handed+0.016
 Doctor+0.015
seat+0.015
Mo+0.015
Neg logit contributions
ocus-0.026
ets-0.026
 similarities-0.025
issors-0.024
 seventeen-0.024
Token and
Token ID290
Feature activation+4.87e-01

Pos logit contributions
 Wolf+0.032
handed+0.032
Mo+0.029
 cub+0.028
rolley+0.028
Neg logit contributions
issors-0.067
ocus-0.066
 similarities-0.066
ets-0.066
 seventeen-0.064
Token wrapped
Token ID12908
Feature activation+9.74e-01

Pos logit contributions
 Wolf+0.013
handed+0.013
 cub+0.012
Mo+0.012
 anyway+0.011
Neg logit contributions
ocus-0.021
issors-0.021
 similarities-0.021
ets-0.020
 seventeen-0.020
TokenOne
Token ID3198
Feature activation-2.59e-01

Pos logit contributions
handed+0.035
 Wolf+0.032
 cub+0.031
rolley+0.031
 baby+0.030
Neg logit contributions
 similarities-0.038
ocus-0.037
issors-0.037
 ind-0.035
apes-0.034
Token day
Token ID1110
Feature activation-1.44e-01

Pos logit contributions
 similarities+0.009
ocus+0.009
issors+0.009
ets+0.009
 ind+0.008
Neg logit contributions
handed-0.009
 Wolf-0.008
Mo-0.008
hand-0.008
rolley-0.008
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
ocus+0.005
issors+0.005
 similarities+0.005
 ind+0.005
ets+0.005
Neg logit contributions
handed-0.005
rolley-0.005
 Wolf-0.004
 cub-0.004
seat-0.004
Token when
Token ID618
Feature activation-3.92e-01

Pos logit contributions
handed+0.004
rolley+0.003
 cub+0.003
 Wolf+0.003
hand+0.003
Neg logit contributions
issors-0.006
 similarities-0.006
ocus-0.006
 ind-0.006
 brushes-0.005
Token Br
Token ID1709
Feature activation+1.45e+00

Pos logit contributions
 similarities+0.016
ocus+0.015
 ind+0.015
issors+0.015
 brushes+0.014
Neg logit contributions
handed-0.014
rolley-0.012
 cub-0.010
hand-0.010
Son-0.010
Tokenidget
Token ID17484
Feature activation+2.92e+00

Pos logit contributions
handed+0.036
 Wolf+0.035
 cub+0.033
hand+0.032
Mo+0.032
Neg logit contributions
issors-0.065
ocus-0.065
 similarities-0.062
ets-0.062
aces-0.058
Token was
Token ID373
Feature activation+8.82e-01

Pos logit contributions
handed+0.066
 Wolf+0.063
Mo+0.059
 anyway+0.058
 anyways+0.058
Neg logit contributions
ocus-0.132
ets-0.126
 similarities-0.126
issors-0.126
 ind-0.120
Token walking
Token ID6155
Feature activation+5.23e-01

Pos logit contributions
handed+0.021
 Wolf+0.021
Mo+0.019
 cub+0.019
hand+0.018
Neg logit contributions
ocus-0.040
issors-0.040
 similarities-0.039
ets-0.038
 seventeen-0.037
Token in
Token ID287
Feature activation-9.09e-01

Pos logit contributions
handed+0.016
 Wolf+0.015
 therm+0.014
 cub+0.014
rolley+0.014
Neg logit contributions
ocus-0.020
issors-0.020
 similarities-0.020
ets-0.019
 ind-0.018
Token the
Token ID262
Feature activation+4.69e-01

Pos logit contributions
 similarities+0.032
ocus+0.032
 ey+0.032
issors+0.031
 Puzzles+0.030
Neg logit contributions
handed-0.027
rolley-0.027
burn-0.026
eled-0.024
Son-0.024
Token me
Token ID502
Feature activation-1.22e+00

Pos logit contributions
 Wolf+0.011
handed+0.011
 cub+0.010
Mo+0.010
 anyway+0.010
Neg logit contributions
ocus-0.021
issors-0.021
 similarities-0.021
ets-0.020
 seventeen-0.020
Tokenmy
Token ID1820
Feature activation-3.40e-01

Pos logit contributions
ocus+0.018
ets+0.018
issors+0.018
 similarities+0.017
 ind+0.017
Neg logit contributions
handed-0.012
 Wolf-0.010
rolley-0.010
Mo-0.010
seat-0.009
Token smiled
Token ID13541
Feature activation+3.42e-01

Pos logit contributions
ocus+0.012
ets+0.012
 similarities+0.012
 ind+0.012
issors+0.011
Neg logit contributions
handed-0.011
seat-0.010
rolley-0.010
 Wolf-0.010
Mo-0.010
Token and
Token ID290
Feature activation+2.18e-01

Pos logit contributions
handed+0.014
 Wolf+0.012
Mo+0.012
rolley+0.012
hand+0.011
Neg logit contributions
ets-0.010
 ind-0.010
 similarities-0.010
ocus-0.010
 does-0.009
Token said
Token ID531
Feature activation+1.21e+00

Pos logit contributions
handed+0.007
rolley+0.007
 Wolf+0.007
seat+0.006
Mo+0.006
Neg logit contributions
ocus-0.007
 similarities-0.007
 ind-0.007
ets-0.007
issors-0.007
Token there
Token ID612
Feature activation+1.76e+00

Pos logit contributions
handed+0.031
 Wolf+0.030
seat+0.028
rolley+0.028
Mo+0.028
Neg logit contributions
ocus-0.053
 similarities-0.052
issors-0.052
 seventeen-0.050
ets-0.050
Token were
Token ID547
Feature activation+2.88e+00

Pos logit contributions
handed+0.041
 Wolf+0.036
Mo+0.036
seat+0.035
rolley+0.035
Neg logit contributions
 similarities-0.081
issors-0.079
ocus-0.078
ets-0.075
 meanings-0.075
Token no
Token ID645
Feature activation+2.09e+00

Pos logit contributions
handed+0.079
rolley+0.071
seat+0.070
 Wolf+0.068
Mo+0.067
Neg logit contributions
 similarities-0.123
issors-0.118
ocus-0.117
 meanings-0.115
 seventeen-0.114
Token monsters
Token ID10963
Feature activation+2.14e+00

Pos logit contributions
handed+0.074
Mo+0.069
 Wolf+0.067
rolley+0.065
 Wilson+0.064
Neg logit contributions
 similarities-0.074
ets-0.071
 meanings-0.069
issors-0.068
ocus-0.067
Token.
Token ID13
Feature activation+6.68e-01

Pos logit contributions
handed+0.043
 Wolf+0.043
rolley+0.040
Mo+0.040
 therm+0.039
Neg logit contributions
ocus-0.103
ets-0.102
issors-0.101
 similarities-0.100
 seventeen-0.095
Token Then
Token ID3244
Feature activation+1.28e+00

Pos logit contributions
 Wolf+0.020
handed+0.020
 cub+0.019
Mo+0.019
 therm+0.019
Neg logit contributions
issors-0.026
ocus-0.026
 similarities-0.025
ets-0.024
 seventeen-0.024
Token she
Token ID673
Feature activation+1.70e-01

Pos logit contributions
handed+0.040
rolley+0.037
seat+0.033
 Wolf+0.032
Mo+0.031
Neg logit contributions
 similarities-0.050
ocus-0.047
 ind-0.046
issors-0.046
 does-0.045
Token want
Token ID765
Feature activation-1.38e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
rolley+0.003
seat+0.003
Mo+0.003
Neg logit contributions
 similarities-0.004
issors-0.004
ocus-0.004
ets-0.004
 seventeen-0.004
Token to
Token ID284
Feature activation+7.46e-01

Pos logit contributions
issors+0.006
ocus+0.006
 similarities+0.006
ets+0.006
 seventeen+0.005
Neg logit contributions
handed-0.004
 Wolf-0.004
 cub-0.003
Mo-0.003
seat-0.003
Token go
Token ID467
Feature activation+1.33e+00

Pos logit contributions
 Wolf+0.026
handed+0.025
rolley+0.025
seat+0.025
Mo+0.024
Neg logit contributions
 similarities-0.025
issors-0.025
ocus-0.024
ets-0.023
 seventeen-0.023
Token empty
Token ID6565
Feature activation+7.38e-01

Pos logit contributions
 Wolf+0.033
handed+0.032
Mo+0.031
rolley+0.031
 therm+0.030
Neg logit contributions
issors-0.057
ocus-0.057
ets-0.056
 similarities-0.056
 seventeen-0.053
Token-
Token ID12
Feature activation+8.66e-01

Pos logit contributions
 Wolf+0.016
handed+0.016
 cub+0.014
Mo+0.014
 anyway+0.014
Neg logit contributions
issors-0.035
ocus-0.035
 similarities-0.035
ets-0.034
 seventeen-0.033
Tokenhanded
Token ID13638
Feature activation+2.81e+00

Pos logit contributions
 Wolf+0.008
 therm+0.006
 cub+0.006
 baby+0.006
Mo+0.006
Neg logit contributions
issors-0.052
ocus-0.051
 similarities-0.050
ets-0.050
 seventeen-0.049
Token,
Token ID11
Feature activation+3.91e-01

Pos logit contributions
 Wolf+0.058
Mo+0.058
burn+0.056
 therm+0.056
rolley+0.054
Neg logit contributions
ets-0.130
issors-0.125
ocus-0.124
 similarities-0.123
aces-0.118
Token so
Token ID523
Feature activation-2.70e-01

Pos logit contributions
 Wolf+0.009
handed+0.009
 anyway+0.008
 cub+0.008
 baby+0.008
Neg logit contributions
issors-0.018
ocus-0.018
 similarities-0.018
ets-0.017
 seventeen-0.017
Token she
Token ID673
Feature activation-2.71e-01

Pos logit contributions
ocus+0.013
 similarities+0.013
issors+0.013
 seventeen+0.012
ets+0.012
Neg logit contributions
handed-0.005
 Wolf-0.005
rolley-0.005
burn-0.005
 therm-0.005
Token sque
Token ID35776
Feature activation-1.76e+00

Pos logit contributions
ocus+0.012
issors+0.012
 similarities+0.012
ets+0.012
 seventeen+0.012
Neg logit contributions
 Wolf-0.006
handed-0.006
Mo-0.005
 cub-0.005
 therm-0.005
Tokenaked
Token ID4335
Feature activation+3.57e-01

Pos logit contributions
issors+0.061
 similarities+0.060
ocus+0.060
 seventeen+0.057
ets+0.056
Neg logit contributions
handed-0.061
 Wolf-0.060
 anyway-0.057
 cub-0.057
Mo-0.056
Token-
Token ID12
Feature activation-3.72e-01

Pos logit contributions
issors+0.033
ocus+0.033
 similarities+0.032
ets+0.031
 seventeen+0.031
Neg logit contributions
handed-0.020
 Wolf-0.019
hand-0.018
Mo-0.018
 anyway-0.017
Tokenhearted
Token ID20122
Feature activation-7.86e-01

Pos logit contributions
issors+0.016
ocus+0.016
 similarities+0.016
ets+0.015
 seventeen+0.015
Neg logit contributions
 Wolf-0.009
handed-0.009
 cub-0.009
Mo-0.008
seat-0.008
Token princess
Token ID21752
Feature activation-4.15e-01

Pos logit contributions
issors+0.034
ocus+0.034
 similarities+0.034
ets+0.033
 ind+0.032
Neg logit contributions
handed-0.019
 Wolf-0.017
hand-0.017
Mo-0.017
 anyway-0.016
Token named
Token ID3706
Feature activation-1.02e+00

Pos logit contributions
ocus+0.016
ets+0.015
 ind+0.015
 similarities+0.014
aces+0.014
Neg logit contributions
handed-0.012
hand-0.012
 colder-0.011
 unconscious-0.011
 Wolf-0.011
Token Br
Token ID1709
Feature activation+1.95e+00

Pos logit contributions
ocus+0.037
issors+0.037
 similarities+0.036
ets+0.035
 seventeen+0.034
Neg logit contributions
 Wolf-0.033
handed-0.032
 therm-0.031
rolley-0.030
seat-0.030
Tokenidget
Token ID17484
Feature activation+2.78e+00

Pos logit contributions
 Wolf+0.061
handed+0.060
 cub+0.058
hand+0.056
 baby+0.055
Neg logit contributions
issors-0.074
ocus-0.074
ets-0.071
 similarities-0.068
aces-0.066
Token.
Token ID13
Feature activation+6.25e-01

Pos logit contributions
handed+0.086
 continuing+0.078
 further+0.076
 calling+0.074
seat+0.073
Neg logit contributions
aces-0.102
ocus-0.099
 likes-0.099
ets-0.099
 ind-0.096
Token She
Token ID1375
Feature activation+9.09e-01

Pos logit contributions
handed+0.019
 Wolf+0.018
 cub+0.017
burn+0.017
hand+0.017
Neg logit contributions
issors-0.025
 similarities-0.024
ocus-0.024
ets-0.023
 ind-0.022
Token was
Token ID373
Feature activation+4.50e-03

Pos logit contributions
 Wolf+0.025
 cub+0.025
handed+0.024
 baby+0.024
Mo+0.024
Neg logit contributions
issors-0.039
ocus-0.038
 similarities-0.037
 seventeen-0.036
ets-0.035
Token always
Token ID1464
Feature activation-6.06e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
 cub+0.000
hand+0.000
Mo+0.000
Neg logit contributions
ocus-0.000
issors-0.000
 similarities-0.000
ets-0.000
 seventeen-0.000
Token calm
Token ID9480
Feature activation-3.56e-01

Pos logit contributions
 similarities+0.023
ocus+0.023
 ind+0.022
issors+0.022
ets+0.022
Neg logit contributions
handed-0.018
hand-0.018
rolley-0.018
 Wolf-0.017
Mo-0.016
Token a
Token ID257
Feature activation+3.65e-01

Pos logit contributions
handed+0.006
rolley+0.006
seat+0.006
 Wolf+0.005
burn+0.005
Neg logit contributions
issors-0.012
 similarities-0.012
ocus-0.012
 seventeen-0.012
 ind-0.012
Token rock
Token ID3881
Feature activation+5.98e-01

Pos logit contributions
handed+0.012
 Wolf+0.011
hand+0.011
seat+0.011
rolley+0.011
Neg logit contributions
ocus-0.013
issors-0.013
 seventeen-0.013
ets-0.013
 similarities-0.013
Token and
Token ID290
Feature activation-2.55e-02

Pos logit contributions
handed+0.019
 Wolf+0.019
rolley+0.018
Mo+0.018
hand+0.018
Neg logit contributions
ocus-0.022
ets-0.022
issors-0.021
 seventeen-0.020
 ind-0.020
Token started
Token ID2067
Feature activation+9.90e-01

Pos logit contributions
ocus+0.001
issors+0.001
ets+0.001
 similarities+0.001
 seventeen+0.001
Neg logit contributions
handed-0.001
rolley-0.001
 Wolf-0.001
hand-0.001
seat-0.001
Token to
Token ID284
Feature activation+6.97e-03

Pos logit contributions
rolley+0.042
handed+0.040
seat+0.037
 Wolf+0.037
hand+0.037
Neg logit contributions
ocus-0.027
 similarities-0.025
 ind-0.024
issors-0.023
sed-0.023
Token bleed
Token ID30182
Feature activation+2.78e+00

Pos logit contributions
rolley+0.000
hand+0.000
handed+0.000
ipt+0.000
seat+0.000
Neg logit contributions
ocus-0.000
 does-0.000
 draw-0.000
 similarities-0.000
ets-0.000
Token.
Token ID13
Feature activation+4.57e-02

Pos logit contributions
rolley+0.081
handed+0.081
hand+0.071
Son+0.070
seat+0.069
Neg logit contributions
ets-0.117
ocus-0.110
aces-0.108
 does-0.107
 ind-0.106
Token Billy
Token ID15890
Feature activation-3.66e-01

Pos logit contributions
 Wolf+0.001
handed+0.001
 cub+0.001
Mo+0.001
 anyway+0.001
Neg logit contributions
issors-0.002
ocus-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token tried
Token ID3088
Feature activation+3.49e-01

Pos logit contributions
ocus+0.012
ets+0.012
 does+0.012
 ind+0.011
issors+0.011
Neg logit contributions
handed-0.013
seat-0.012
rolley-0.012
hand-0.012
burn-0.011
Token to
Token ID284
Feature activation-5.82e-01

Pos logit contributions
rolley+0.014
handed+0.014
seat+0.013
 cub+0.012
 Wolf+0.012
Neg logit contributions
 similarities-0.010
issors-0.009
ocus-0.009
ets-0.008
 seventeen-0.008
Token help
Token ID1037
Feature activation-4.28e-01

Pos logit contributions
ets+0.016
issors+0.016
 similarities+0.016
 draw+0.015
ocus+0.015
Neg logit contributions
rolley-0.022
seat-0.021
handed-0.021
hand-0.020
 Wolf-0.019
Token asked
Token ID1965
Feature activation+8.72e-01

Pos logit contributions
handed+0.014
 Wolf+0.014
Mo+0.014
 cub+0.013
hand+0.013
Neg logit contributions
issors-0.019
ocus-0.018
 similarities-0.018
ets-0.018
 seventeen-0.017
Token for
Token ID329
Feature activation-3.31e-01

Pos logit contributions
handed+0.025
 Wolf+0.025
Mo+0.023
 cub+0.023
 therm+0.023
Neg logit contributions
issors-0.036
 similarities-0.035
ocus-0.035
ets-0.034
 seventeen-0.033
Token a
Token ID257
Feature activation+3.25e-01

Pos logit contributions
 similarities+0.015
issors+0.015
ocus+0.014
 seventeen+0.013
ets+0.013
Neg logit contributions
 Wolf-0.008
handed-0.008
rolley-0.008
Mo-0.008
 cub-0.008
Token band
Token ID4097
Feature activation+1.22e+00

Pos logit contributions
handed+0.010
 Wolf+0.010
Mo+0.009
rolley+0.009
hand+0.009
Neg logit contributions
 similarities-0.012
issors-0.012
ocus-0.012
 seventeen-0.012
 ind-0.011
Token-
Token ID12
Feature activation+1.32e-01

Pos logit contributions
 Wolf+0.029
Mo+0.028
 cub+0.025
 continuing+0.025
 baby+0.025
Neg logit contributions
issors-0.056
ets-0.056
ocus-0.054
 similarities-0.053
aces-0.051
Tokenaid
Token ID1698
Feature activation+2.76e+00

Pos logit contributions
 Wolf+0.004
handed+0.004
 cub+0.004
Mo+0.004
 baby+0.004
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Token.
Token ID13
Feature activation-2.55e-01

Pos logit contributions
handed+0.060
 Wolf+0.057
Mo+0.057
eled+0.050
 continuing+0.049
Neg logit contributions
issors-0.135
ets-0.132
ocus-0.128
 similarities-0.124
aces-0.124
Token Mom
Token ID11254
Feature activation-1.72e-01

Pos logit contributions
ocus+0.013
ets+0.013
 similarities+0.013
issors+0.012
 seventeen+0.012
Neg logit contributions
 Wolf-0.005
 another-0.005
handed-0.005
 anyway-0.005
 baby-0.004
Token cleaned
Token ID20750
Feature activation+1.34e+00

Pos logit contributions
ocus+0.007
issors+0.007
 similarities+0.007
ets+0.006
 seventeen+0.006
Neg logit contributions
handed-0.005
 Wolf-0.005
Mo-0.005
seat-0.004
 cub-0.004
Token Tom
Token ID4186
Feature activation-4.51e-01

Pos logit contributions
handed+0.029
 Wolf+0.029
 cub+0.027
Mo+0.027
seat+0.026
Neg logit contributions
issors-0.064
ocus-0.062
 similarities-0.061
ets-0.059
 seventeen-0.058
Token's
Token ID338
Feature activation-2.14e-01

Pos logit contributions
ocus+0.018
issors+0.018
 similarities+0.018
ets+0.017
 seventeen+0.017
Neg logit contributions
 Wolf-0.013
handed-0.013
Mo-0.012
seat-0.012
hand-0.012
Token
Token ID6184
Feature activation-5.21e-01

Pos logit contributions
handed+0.003
 Wolf+0.003
rolley+0.003
Mo+0.003
seat+0.003
Neg logit contributions
ocus-0.005
issors-0.005
 similarities-0.004
 seventeen-0.004
 ind-0.004
Token
Token ID95
Feature activation-1.17e+00

Pos logit contributions
 similarities+0.016
issors+0.016
ocus+0.016
ets+0.015
 seventeen+0.015
Neg logit contributions
handed-0.019
 Wolf-0.019
Mo-0.018
 therm-0.018
 anyway-0.018
Token
Token ID26391
Feature activation+2.42e-01

Pos logit contributions
 similarities+0.037
issors+0.037
ocus+0.037
ets+0.034
 seventeen+0.034
Neg logit contributions
handed-0.044
 Wolf-0.043
 anyway-0.040
Mo-0.040
hand-0.040
Token
Token ID129
Feature activation-8.26e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.007
Mo+0.007
 baby+0.007
Neg logit contributions
ocus-0.009
issors-0.009
 similarities-0.009
ets-0.009
 seventeen-0.009
Token
Token ID241
Feature activation-9.04e-03

Pos logit contributions
ocus+0.030
 similarities+0.030
issors+0.030
ets+0.029
 seventeen+0.028
Neg logit contributions
handed-0.026
 Wolf-0.025
 anyway-0.024
Mo-0.024
 therm-0.023
TokenNot
Token ID3673
Feature activation+2.75e+00

Pos logit contributions
 similarities+0.000
ocus+0.000
issors+0.000
 seventeen+0.000
ets+0.000
Neg logit contributions
handed-0.000
 Wolf-0.000
 cub-0.000
 therm-0.000
burn-0.000
Token usually
Token ID3221
Feature activation-2.57e-01

Pos logit contributions
handed+0.082
 Wolf+0.077
rolley+0.075
Mo+0.074
seat+0.073
Neg logit contributions
 similarities-0.110
ocus-0.109
ets-0.105
issors-0.105
 seventeen-0.102
Token -
Token ID532
Feature activation+7.65e-01

Pos logit contributions
ocus+0.010
issors+0.010
 similarities+0.010
ets+0.010
 seventeen+0.009
Neg logit contributions
handed-0.008
 Wolf-0.008
Mo-0.007
 cub-0.007
rolley-0.007
Token they
Token ID484
Feature activation+1.23e+00

Pos logit contributions
 Wolf+0.023
handed+0.023
 cub+0.021
Mo+0.021
 therm+0.021
Neg logit contributions
ocus-0.030
issors-0.030
 similarities-0.029
ets-0.028
 seventeen-0.028
Tokenâ
Token ID22940
Feature activation-6.59e-01

Pos logit contributions
 Wolf+0.048
handed+0.048
Mo+0.045
 cub+0.045
 therm+0.045
Neg logit contributions
ocus-0.036
issors-0.036
 similarities-0.036
ets-0.034
 seventeen-0.033
Token
Token ID26391
Feature activation+3.98e-01

Pos logit contributions
 similarities+0.022
ocus+0.022
issors+0.022
 seventeen+0.021
ets+0.020
Neg logit contributions
handed-0.023
 Wolf-0.023
 anyway-0.022
hand-0.021
Mo-0.021
Token
Token ID6184
Feature activation-9.97e-01

Pos logit contributions
handed+0.004
burn+0.004
 Wolf+0.004
Mo+0.004
 able+0.004
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.004
 seventeen-0.004
ets-0.004
Token
Token ID95
Feature activation-1.31e+00

Pos logit contributions
 similarities+0.033
issors+0.033
ocus+0.032
ets+0.031
 seventeen+0.031
Neg logit contributions
handed-0.036
 Wolf-0.035
 therm-0.033
Mo-0.033
 anyway-0.033
Token
Token ID26391
Feature activation+5.06e-02

Pos logit contributions
issors+0.041
ocus+0.041
 similarities+0.041
ets+0.039
 seventeen+0.038
Neg logit contributions
handed-0.049
 Wolf-0.049
 cub-0.046
Mo-0.046
 anyway-0.046
Token
Token ID129
Feature activation-8.43e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
 cub+0.001
 baby+0.001
 anyway+0.001
Neg logit contributions
ocus-0.002
issors-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token
Token ID241
Feature activation-2.65e-01

Pos logit contributions
issors+0.030
ocus+0.030
 similarities+0.030
ets+0.029
 seventeen+0.028
Neg logit contributions
 Wolf-0.027
handed-0.027
 anyway-0.025
Mo-0.025
 therm-0.025
TokenNot
Token ID3673
Feature activation+2.74e+00

Pos logit contributions
ocus+0.009
 similarities+0.009
issors+0.009
 seventeen+0.009
ets+0.009
Neg logit contributions
 Wolf-0.009
handed-0.009
 cub-0.008
burn-0.008
 Rabbit-0.008
Token yet
Token ID1865
Feature activation+1.03e+00

Pos logit contributions
handed+0.082
 Wolf+0.078
Mo+0.075
rolley+0.075
 cub+0.073
Neg logit contributions
ocus-0.108
 similarities-0.108
issors-0.104
ets-0.104
 seventeen-0.101
Token,
Token ID11
Feature activation+2.55e-01

Pos logit contributions
handed+0.026
rolley+0.025
eled+0.024
 Wolf+0.024
 cub+0.023
Neg logit contributions
ocus-0.045
 similarities-0.042
issors-0.041
ets-0.041
 does-0.041
Token Alice
Token ID14862
Feature activation+1.23e+00

Pos logit contributions
handed+0.007
 Wolf+0.007
Mo+0.006
 cub+0.006
seat+0.006
Neg logit contributions
ocus-0.010
 similarities-0.010
issors-0.010
ets-0.010
 seventeen-0.010
Token,
Token ID11
Feature activation-6.19e-01

Pos logit contributions
handed+0.027
 Wolf+0.026
Mo+0.024
hand+0.024
burn+0.024
Neg logit contributions
ocus-0.058
issors-0.055
ets-0.055
 similarities-0.055
 ind-0.053
Tokenâ
Token ID22940
Feature activation-6.55e-01

Pos logit contributions
issors+0.024
ocus+0.024
 similarities+0.024
ets+0.023
 seventeen+0.023
Neg logit contributions
 Wolf-0.019
handed-0.018
 baby-0.017
 anyway-0.017
 cub-0.017
Token never
Token ID1239
Feature activation-1.01e-01

Pos logit contributions
ocus+0.023
issors+0.022
 similarities+0.022
ets+0.021
 seventeen+0.021
Neg logit contributions
 Wolf-0.017
handed-0.017
 cub-0.016
 anyway-0.016
 baby-0.016
Token ask
Token ID1265
Feature activation+2.12e-01

Pos logit contributions
issors+0.004
ocus+0.004
 similarities+0.004
 seventeen+0.004
ets+0.004
Neg logit contributions
 Wolf-0.003
handed-0.003
 anyway-0.003
 cub-0.003
 baby-0.003
Token to
Token ID284
Feature activation+3.77e-01

Pos logit contributions
handed+0.005
 Wolf+0.005
rolley+0.004
Mo+0.004
burn+0.004
Neg logit contributions
issors-0.010
 similarities-0.010
ocus-0.009
ets-0.009
 seventeen-0.009
Token play
Token ID711
Feature activation+1.08e+00

Pos logit contributions
 Wolf+0.012
handed+0.012
Mo+0.011
 cub+0.011
 therm+0.011
Neg logit contributions
issors-0.014
ocus-0.014
 similarities-0.014
ets-0.014
 seventeen-0.013
Token with
Token ID351
Feature activation+2.08e-01

Pos logit contributions
 Wolf+0.027
handed+0.026
Mo+0.024
 cub+0.024
 therm+0.024
Neg logit contributions
ocus-0.048
issors-0.048
 similarities-0.047
ets-0.046
 seventeen-0.044
Token switches
Token ID18225
Feature activation+2.74e+00

Pos logit contributions
burn+0.005
 Wolf+0.005
rolley+0.005
handed+0.005
Mo+0.005
Neg logit contributions
issors-0.009
 similarities-0.009
ocus-0.009
ets-0.009
aces-0.008
Token again
Token ID757
Feature activation-6.73e-01

Pos logit contributions
 Wolf+0.054
handed+0.053
Mo+0.051
 cub+0.047
 therm+0.046
Neg logit contributions
ocus-0.134
issors-0.133
ets-0.132
 similarities-0.131
 seventeen-0.125
Token and
Token ID290
Feature activation+3.42e-02

Pos logit contributions
ets+0.033
ocus+0.033
 similarities+0.032
issors+0.032
apes+0.031
Neg logit contributions
handed-0.012
rolley-0.012
 Wolf-0.012
burn-0.011
Mo-0.010
Token never
Token ID1239
Feature activation+4.39e-02

Pos logit contributions
 Wolf+0.001
handed+0.001
 cub+0.001
Mo+0.001
 therm+0.001
Neg logit contributions
ocus-0.002
issors-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token disob
Token ID30163
Feature activation+5.05e-01

Pos logit contributions
 Wolf+0.001
handed+0.001
 cub+0.001
 baby+0.001
 anyway+0.001
Neg logit contributions
issors-0.002
ocus-0.002
 similarities-0.002
 seventeen-0.002
ets-0.002
Tokeney
Token ID2959
Feature activation+4.19e-01

Pos logit contributions
 Wolf+0.016
 therm+0.015
seat+0.015
rolley+0.015
 Doctor+0.015
Neg logit contributions
issors-0.019
ocus-0.018
 similarities-0.017
ols-0.017
apes-0.017
Token shiny
Token ID22441
Feature activation-2.03e-01

Pos logit contributions
 Wolf+0.009
handed+0.009
 cub+0.008
 baby+0.008
Mo+0.008
Neg logit contributions
issors-0.015
ocus-0.015
 similarities-0.014
ets-0.014
 seventeen-0.014
Token and
Token ID290
Feature activation+3.62e-01

Pos logit contributions
ocus+0.010
ets+0.010
 similarities+0.010
issors+0.010
 ind+0.010
Neg logit contributions
handed-0.004
 Wolf-0.004
Mo-0.003
rolley-0.003
hand-0.003
Token made
Token ID925
Feature activation-8.54e-02

Pos logit contributions
 Wolf+0.010
handed+0.010
 baby+0.009
 cub+0.009
Mo+0.009
Neg logit contributions
issors-0.015
ocus-0.015
 similarities-0.014
ets-0.014
 seventeen-0.014
Token a
Token ID257
Feature activation-3.00e-01

Pos logit contributions
 similarities+0.004
ocus+0.004
issors+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
handed-0.002
 Wolf-0.002
Mo-0.002
seat-0.002
rolley-0.002
Token z
Token ID1976
Feature activation-5.99e-02

Pos logit contributions
ocus+0.010
issors+0.010
 similarities+0.010
ets+0.010
 seventeen+0.009
Neg logit contributions
handed-0.011
 Wolf-0.011
Mo-0.010
 cub-0.010
hand-0.010
Tokenooming
Token ID30602
Feature activation+2.73e+00

Pos logit contributions
issors+0.002
ocus+0.002
 similarities+0.002
ets+0.002
 seventeen+0.002
Neg logit contributions
 Wolf-0.002
handed-0.002
 cub-0.002
Mo-0.002
 anyway-0.002
Token sound
Token ID2128
Feature activation+1.28e+00

Pos logit contributions
handed+0.068
 Wolf+0.068
Mo+0.063
 therm+0.059
 cub+0.059
Neg logit contributions
ocus-0.121
 similarities-0.120
ets-0.119
issors-0.118
 seventeen-0.114
Token.
Token ID13
Feature activation-3.62e-01

Pos logit contributions
handed+0.028
 Wolf+0.027
rolley+0.026
Mo+0.025
 Wilson+0.023
Neg logit contributions
ets-0.064
ocus-0.061
 ind-0.059
 similarities-0.057
 seventeen-0.057
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
ocus+0.019
issors+0.019
 similarities+0.019
ets+0.018
 seventeen+0.018
Neg logit contributions
 Wolf-0.006
handed-0.006
 anyway-0.006
 cub-0.006
 baby-0.006
Token
Token ID198
Feature activation+9.09e-02

Pos logit contributions
ocus+0.012
issors+0.012
 similarities+0.012
ets+0.012
 seventeen+0.011
Neg logit contributions
 Wolf-0.006
burn-0.006
handed-0.006
 therm-0.006
 cub-0.006
TokenL
Token ID43
Feature activation-7.29e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
Mo+0.002
 cub+0.002
 anyway+0.002
Neg logit contributions
issors-0.004
ocus-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Token and
Token ID290
Feature activation+1.92e-01

Pos logit contributions
 Wolf+0.021
Mo+0.020
 cub+0.020
handed+0.020
eled+0.019
Neg logit contributions
issors-0.032
ets-0.032
ocus-0.031
aces-0.029
 does-0.028
Token put
Token ID1234
Feature activation+3.70e-01

Pos logit contributions
 Wolf+0.005
handed+0.005
 baby+0.005
 cub+0.005
 anyway+0.005
Neg logit contributions
ocus-0.008
issors-0.008
 similarities-0.008
ets-0.008
 seventeen-0.008
Token a
Token ID257
Feature activation-1.09e-01

Pos logit contributions
handed+0.010
 Wolf+0.010
Mo+0.009
 cub+0.009
seat+0.009
Neg logit contributions
issors-0.016
ocus-0.016
 similarities-0.015
ets-0.015
 seventeen-0.015
Token band
Token ID4097
Feature activation+1.10e+00

Pos logit contributions
 similarities+0.004
issors+0.004
ocus+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.003
handed-0.003
Mo-0.003
hand-0.003
 Wilson-0.003
Token-
Token ID12
Feature activation+2.69e-01

Pos logit contributions
 Wolf+0.033
 cub+0.030
handed+0.030
Mo+0.030
 Wilson+0.030
Neg logit contributions
ocus-0.044
ets-0.044
issors-0.044
 similarities-0.042
aces-0.040
Tokenaid
Token ID1698
Feature activation+2.73e+00

Pos logit contributions
 Wolf+0.009
 cub+0.008
 Wilson+0.008
handed+0.008
Mo+0.008
Neg logit contributions
ocus-0.010
issors-0.010
 similarities-0.009
ets-0.009
 seventeen-0.009
Token on
Token ID319
Feature activation+6.56e-01

Pos logit contributions
 Wolf+0.092
handed+0.091
Mo+0.087
 cub+0.085
hand+0.082
Neg logit contributions
issors-0.100
ets-0.099
ocus-0.097
 similarities-0.091
aces-0.089
Token it
Token ID340
Feature activation-5.96e-01

Pos logit contributions
handed+0.022
seat+0.021
 Wolf+0.021
rolley+0.020
 cub+0.020
Neg logit contributions
issors-0.025
ocus-0.023
 similarities-0.023
ets-0.022
 seventeen-0.021
Token.
Token ID13
Feature activation-4.30e-02

Pos logit contributions
issors+0.029
ets+0.029
ocus+0.029
 similarities+0.027
aces+0.026
Neg logit contributions
 Wolf-0.013
handed-0.012
Mo-0.012
 cub-0.011
seat-0.011
Token Then
Token ID3244
Feature activation+3.36e-01

Pos logit contributions
ocus+0.001
issors+0.001
 similarities+0.001
ets+0.001
 seventeen+0.001
Neg logit contributions
 Wolf-0.002
 cub-0.001
handed-0.001
 baby-0.001
 anyway-0.001
Token we
Token ID356
Feature activation+7.46e-02

Pos logit contributions
handed+0.012
 Wolf+0.012
rolley+0.011
Mo+0.011
seat+0.011
Neg logit contributions
 similarities-0.011
ocus-0.011
issors-0.011
ets-0.010
 seventeen-0.010
Token don
Token ID836
Feature activation-8.80e-01

Pos logit contributions
issors+0.016
ocus+0.015
 similarities+0.015
 seventeen+0.014
ets+0.014
Neg logit contributions
 Wolf-0.021
handed-0.021
 cub-0.020
 anyway-0.020
 therm-0.020
Token't
Token ID470
Feature activation-1.44e-01

Pos logit contributions
issors+0.028
ocus+0.027
ets+0.024
 similarities+0.024
ols+0.024
Neg logit contributions
handed-0.033
 Wolf-0.032
 cub-0.032
hand-0.031
seat-0.031
Token get
Token ID651
Feature activation+9.43e-01

Pos logit contributions
issors+0.005
ocus+0.005
 similarities+0.005
ets+0.005
 seventeen+0.005
Neg logit contributions
handed-0.005
 Wolf-0.005
 cub-0.005
Mo-0.005
 therm-0.005
Token a
Token ID257
Feature activation+1.92e-01

Pos logit contributions
handed+0.025
 Wolf+0.024
rolley+0.023
Mo+0.023
 Wilson+0.023
Neg logit contributions
issors-0.040
ocus-0.040
 similarities-0.039
ets-0.039
 ind-0.036
Token sun
Token ID4252
Feature activation+4.57e-01

Pos logit contributions
handed+0.006
 Wolf+0.006
Mo+0.006
 cub+0.005
hand+0.005
Neg logit contributions
 similarities-0.007
issors-0.007
ocus-0.007
ets-0.007
 seventeen-0.006
Tokenburn
Token ID10899
Feature activation+2.73e+00

Pos logit contributions
handed+0.005
 Wolf+0.005
Mo+0.005
 cub+0.004
hand+0.004
Neg logit contributions
issors-0.026
ocus-0.026
ets-0.026
 similarities-0.025
 ind-0.025
Token."
Token ID526
Feature activation+2.36e-01

Pos logit contributions
handed+0.062
Mo+0.062
 clearing+0.058
Far+0.055
 Wolf+0.055
Neg logit contributions
ets-0.129
issors-0.127
aces-0.119
ocus-0.116
ems-0.115
Token Lily
Token ID20037
Feature activation+7.25e-02

Pos logit contributions
handed+0.006
 Wolf+0.006
 anyway+0.006
 baby+0.006
 anyways+0.006
Neg logit contributions
ocus-0.010
issors-0.010
 similarities-0.010
 seventeen-0.010
ets-0.010
Token yawn
Token ID40908
Feature activation-5.45e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
Mo+0.002
seat+0.002
 cub+0.002
Neg logit contributions
ocus-0.003
issors-0.003
 similarities-0.003
ets-0.003
 seventeen-0.003
Tokened
Token ID276
Feature activation-5.01e-02

Pos logit contributions
ets+0.019
ocus+0.018
issors+0.018
 seventeen+0.017
 ind+0.017
Neg logit contributions
handed-0.018
 Wolf-0.018
Mo-0.017
seat-0.017
 cub-0.017
Token and
Token ID290
Feature activation+3.08e-03

Pos logit contributions
ocus+0.002
ets+0.002
 similarities+0.002
issors+0.002
 ind+0.002
Neg logit contributions
handed-0.002
 Wolf-0.002
Mo-0.001
rolley-0.001
seat-0.001
Token
Token ID8151
Feature activation+9.41e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
 cub+0.004
 baby+0.004
 therm+0.004
Neg logit contributions
ocus-0.004
issors-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Tokens
Token ID82
Feature activation-1.43e-01

Pos logit contributions
 lamb+0.030
 therm+0.030
 Wolf+0.030
Where+0.030
 elf+0.030
Neg logit contributions
issors-0.034
ocus-0.032
ets-0.029
ige-0.028
 seventeen-0.028
Token bite
Token ID13197
Feature activation+3.53e-01

Pos logit contributions
ocus+0.006
 similarities+0.006
issors+0.006
ets+0.006
 seventeen+0.005
Neg logit contributions
handed-0.004
 Wolf-0.004
Mo-0.004
seat-0.004
rolley-0.004
Token was
Token ID373
Feature activation+8.78e-01

Pos logit contributions
handed+0.008
 Wolf+0.008
Mo+0.007
 cub+0.007
seat+0.007
Neg logit contributions
ocus-0.016
issors-0.016
ets-0.016
 similarities-0.016
 seventeen-0.015
Token not
Token ID407
Feature activation+1.08e+00

Pos logit contributions
handed+0.024
rolley+0.024
 Wolf+0.023
seat+0.023
Mo+0.022
Neg logit contributions
ocus-0.036
 similarities-0.035
issors-0.035
ets-0.035
 seventeen-0.034
Token severe
Token ID6049
Feature activation+2.73e+00

Pos logit contributions
handed+0.030
rolley+0.029
 Wolf+0.029
hand+0.028
seat+0.028
Neg logit contributions
ets-0.044
 similarities-0.043
ocus-0.043
issors-0.042
 seventeen-0.040
Token.
Token ID13
Feature activation+4.34e-01

Pos logit contributions
Mo+0.078
 Wolf+0.073
handed+0.073
rolley+0.072
seat+0.072
Neg logit contributions
ets-0.105
 similarities-0.104
ocus-0.102
issors-0.099
 seventeen-0.098
Token But
Token ID887
Feature activation+2.29e+00

Pos logit contributions
 Wolf+0.013
handed+0.013
 cub+0.013
Mo+0.013
 baby+0.012
Neg logit contributions
issors-0.017
ocus-0.016
 similarities-0.016
ets-0.016
 seventeen-0.015
Token Tom
Token ID4186
Feature activation-2.25e-01

Pos logit contributions
 Wolf+0.057
handed+0.057
 cub+0.052
Mo+0.052
 therm+0.051
Neg logit contributions
ocus-0.101
issors-0.101
 similarities-0.100
ets-0.096
 seventeen-0.095
Token realized
Token ID6939
Feature activation-1.43e-01

Pos logit contributions
ocus+0.010
issors+0.009
 similarities+0.009
ets+0.009
 seventeen+0.009
Neg logit contributions
handed-0.006
 Wolf-0.006
seat-0.005
Mo-0.005
rolley-0.005
Token he
Token ID339
Feature activation-6.82e-01

Pos logit contributions
ocus+0.005
issors+0.005
 similarities+0.005
 does+0.005
ets+0.005
Neg logit contributions
handed-0.004
rolley-0.004
seat-0.004
burn-0.004
 Wolf-0.004
Token worked
Token ID3111
Feature activation+5.33e-01

Pos logit contributions
issors+0.014
ocus+0.013
 similarities+0.013
ets+0.013
 seventeen+0.013
Neg logit contributions
 Wolf-0.007
handed-0.007
 baby-0.007
 cub-0.006
 anyway-0.006
Token hard
Token ID1327
Feature activation+6.31e-01

Pos logit contributions
 Wolf+0.015
handed+0.015
 cub+0.014
Mo+0.014
 baby+0.014
Neg logit contributions
issors-0.022
ocus-0.022
 similarities-0.021
ets-0.021
 seventeen-0.020
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 Wolf+0.013
handed+0.013
 anyway+0.012
 cub+0.012
 therm+0.012
Neg logit contributions
ocus-0.030
issors-0.030
 similarities-0.030
ets-0.029
 seventeen-0.029
Token The
Token ID383
Feature activation-4.41e-01

Pos logit contributions
issors+0.010
ocus+0.010
 similarities+0.010
 seventeen+0.009
ets+0.009
Neg logit contributions
handed-0.008
 Wolf-0.007
burn-0.007
 therm-0.007
Mo-0.007
Token grass
Token ID8701
Feature activation-7.74e-01

Pos logit contributions
ocus+0.020
issors+0.020
 similarities+0.020
ets+0.020
 seventeen+0.019
Neg logit contributions
 Wolf-0.010
handed-0.010
 baby-0.010
 cub-0.010
 therm-0.009
Tokenho
Token ID8873
Feature activation-4.10e+00

Pos logit contributions
issors+0.045
ocus+0.043
 similarities+0.043
ets+0.042
 seventeen+0.041
Neg logit contributions
 Wolf-0.010
handed-0.009
 baby-0.009
 cub-0.009
 anyway-0.009
Tokenpper
Token ID2848
Feature activation-9.81e-01

Pos logit contributions
ocus+0.156
issors+0.154
 similarities+0.148
ets+0.148
 seventeen+0.144
Neg logit contributions
 Wolf-0.132
handed-0.128
 cub-0.121
Mo-0.121
 baby-0.121
Token was
Token ID373
Feature activation-1.70e-01

Pos logit contributions
issors+0.044
ocus+0.044
 similarities+0.043
ets+0.042
 seventeen+0.041
Neg logit contributions
 Wolf-0.024
handed-0.023
 cub-0.022
Mo-0.021
 anyway-0.021
Token spoiled
Token ID34781
Feature activation-7.62e-02

Pos logit contributions
ocus+0.007
 similarities+0.007
issors+0.007
 seventeen+0.007
ets+0.007
Neg logit contributions
handed-0.005
 Wolf-0.004
rolley-0.004
 cub-0.004
seat-0.004
Token and
Token ID290
Feature activation+2.50e-01

Pos logit contributions
ocus+0.003
ets+0.003
issors+0.003
 similarities+0.003
aces+0.003
Neg logit contributions
handed-0.002
 Wolf-0.002
Mo-0.002
rolley-0.002
seat-0.002
Token didn
Token ID1422
Feature activation+5.31e-01

Pos logit contributions
handed+0.007
 Wolf+0.007
Mo+0.006
 cub+0.006
seat+0.006
Neg logit contributions
ocus-0.011
issors-0.011
 similarities-0.011
ets-0.010
 seventeen-0.010
Token
Token ID26391
Feature activation-1.18e-01

Pos logit contributions
 similarities+0.043
ocus+0.042
issors+0.042
ets+0.039
 narrative+0.038
Neg logit contributions
handed-0.056
 Wolf-0.053
Mo-0.051
hand-0.050
 front-0.050
Token
Token ID129
Feature activation-9.70e-01

Pos logit contributions
issors+0.005
ocus+0.005
 similarities+0.005
ets+0.005
 seventeen+0.005
Neg logit contributions
 Wolf-0.003
handed-0.003
 cub-0.003
Mo-0.003
 anyway-0.003
Token
Token ID241
Feature activation-5.13e-01

Pos logit contributions
ocus+0.037
 similarities+0.036
issors+0.036
ets+0.035
 seventeen+0.034
Neg logit contributions
handed-0.030
 Wolf-0.029
Mo-0.028
 anyway-0.028
 cub-0.027
TokenGr
Token ID8642
Feature activation-1.05e+00

Pos logit contributions
ocus+0.018
 similarities+0.018
 seventeen+0.018
issors+0.018
 ind+0.017
Neg logit contributions
 Wolf-0.016
handed-0.016
 therm-0.016
 cub-0.015
burn-0.015
Tokenass
Token ID562
Feature activation+2.22e-01

Pos logit contributions
issors+0.036
ocus+0.036
 similarities+0.036
ets+0.035
 seventeen+0.033
Neg logit contributions
 Wolf-0.036
handed-0.036
 cub-0.034
Mo-0.034
 therm-0.034
Tokenho
Token ID8873
Feature activation-3.78e+00

Pos logit contributions
handed+0.006
 Wolf+0.006
seat+0.006
rolley+0.006
burn+0.006
Neg logit contributions
ocus-0.009
issors-0.009
 similarities-0.009
ets-0.009
 seventeen-0.009
Tokenpper
Token ID2848
Feature activation-2.02e-01

Pos logit contributions
ocus+0.133
issors+0.124
 ind+0.117
 seventeen+0.115
ets+0.112
Neg logit contributions
 Wolf-0.135
rolley-0.132
handed-0.132
seat-0.131
 baby-0.130
Token,
Token ID11
Feature activation-3.90e-01

Pos logit contributions
ocus+0.010
 ind+0.010
issors+0.010
ets+0.010
 similarities+0.009
Neg logit contributions
handed-0.004
rolley-0.004
burn-0.004
 Wolf-0.003
seat-0.003
Token let
Token ID1309
Feature activation+1.92e-01

Pos logit contributions
issors+0.017
ocus+0.017
 similarities+0.017
ets+0.016
 seventeen+0.016
Neg logit contributions
 Wolf-0.010
handed-0.010
 cub-0.009
 baby-0.009
 therm-0.009
Tokenâ
Token ID22940
Feature activation-6.70e-01

Pos logit contributions
seat+0.007
 continuing+0.007
handed+0.006
hand+0.006
rolley+0.006
Neg logit contributions
issors-0.006
ocus-0.006
ets-0.006
ige-0.005
 does-0.005
Token
Token ID26391
Feature activation+4.61e-01

Pos logit contributions
ocus+0.023
 similarities+0.022
issors+0.022
 seventeen+0.021
ets+0.021
Neg logit contributions
handed-0.024
 Wolf-0.023
 anyway-0.022
Mo-0.022
hand-0.022
Token
Token ID198
Feature activation+5.24e-01

Pos logit contributions
handed+0.005
burn+0.005
 Wolf+0.005
 baby+0.005
 therm+0.005
Neg logit contributions
ocus-0.011
issors-0.011
 similarities-0.011
 seventeen-0.010
ets-0.010
TokenThe
Token ID464
Feature activation+1.04e-01

Pos logit contributions
 Wolf+0.016
handed+0.016
 cub+0.015
 therm+0.015
 baby+0.015
Neg logit contributions
issors-0.020
ocus-0.020
 similarities-0.020
ets-0.019
 seventeen-0.019
Token nos
Token ID43630
Feature activation-6.09e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
 baby+0.003
 cub+0.003
Mo+0.003
Neg logit contributions
ocus-0.004
issors-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Tokeny
Token ID88
Feature activation-3.37e-01

Pos logit contributions
ocus+0.026
issors+0.026
ets+0.025
 similarities+0.025
 seventeen+0.024
Neg logit contributions
 Wolf-0.016
handed-0.016
 therm-0.015
 anyway-0.015
 anyways-0.015
Token grass
Token ID8701
Feature activation+3.08e-01

Pos logit contributions
issors+0.017
ocus+0.017
 similarities+0.016
ets+0.016
 seventeen+0.016
Neg logit contributions
 Wolf-0.007
handed-0.007
 cub-0.006
 baby-0.006
 therm-0.006
Tokenho
Token ID8873
Feature activation-3.76e+00

Pos logit contributions
 Wolf+0.008
handed+0.008
 cub+0.007
 baby+0.007
 therm+0.007
Neg logit contributions
issors-0.013
ocus-0.013
 similarities-0.013
ets-0.013
 seventeen-0.012
Tokenpper
Token ID2848
Feature activation-5.88e-01

Pos logit contributions
ocus+0.123
issors+0.117
ets+0.108
 seventeen+0.108
 ind+0.108
Neg logit contributions
 Wolf-0.142
handed-0.137
seat-0.136
 baby-0.136
rolley-0.134
Token hopped
Token ID45230
Feature activation+2.73e-01

Pos logit contributions
issors+0.027
ocus+0.026
 similarities+0.026
ets+0.025
 seventeen+0.025
Neg logit contributions
 Wolf-0.014
handed-0.014
 cub-0.013
Mo-0.013
 baby-0.013
Token over
Token ID625
Feature activation+3.49e-01

Pos logit contributions
handed+0.006
 Wolf+0.006
 cub+0.006
Mo+0.006
 therm+0.006
Neg logit contributions
issors-0.012
ocus-0.012
 similarities-0.012
ets-0.012
 seventeen-0.012
Token to
Token ID284
Feature activation+7.01e-02

Pos logit contributions
handed+0.010
 Wolf+0.009
burn+0.009
 therm+0.009
 cub+0.009
Neg logit contributions
ocus-0.014
 similarities-0.014
issors-0.014
ets-0.014
 seventeen-0.013
Token Tom
Token ID4186
Feature activation+5.29e-01

Pos logit contributions
rolley+0.002
handed+0.002
seat+0.002
burn+0.002
 therm+0.002
Neg logit contributions
 similarities-0.002
issors-0.002
ocus-0.002
ets-0.002
 seventeen-0.002
Token."
Token ID526
Feature activation+1.09e-01

Pos logit contributions
issors+0.022
ocus+0.022
ets+0.020
 similarities+0.019
agon+0.019
Neg logit contributions
handed-0.015
burn-0.015
eled-0.015
 Wolf-0.014
 cub-0.014
Token
Token ID198
Feature activation+2.36e-01

Pos logit contributions
handed+0.002
burn+0.002
 Wolf+0.002
 therm+0.002
 baby+0.002
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Token
Token ID198
Feature activation+4.88e-01

Pos logit contributions
burn+0.006
handed+0.005
 therm+0.005
 Wolf+0.005
rolley+0.005
Neg logit contributions
issors-0.010
ocus-0.010
 similarities-0.010
 seventeen-0.009
apes-0.009
TokenThe
Token ID464
Feature activation-6.49e-02

Pos logit contributions
 Wolf+0.013
handed+0.013
seat+0.012
 baby+0.012
burn+0.012
Neg logit contributions
issors-0.020
 similarities-0.020
ocus-0.020
 seventeen-0.019
ets-0.019
Token grass
Token ID8701
Feature activation+2.94e-01

Pos logit contributions
issors+0.003
 similarities+0.003
ocus+0.003
 seventeen+0.003
 ind+0.002
Neg logit contributions
handed-0.002
seat-0.002
 Wolf-0.002
hand-0.002
rolley-0.002
Tokenho
Token ID8873
Feature activation-3.75e+00

Pos logit contributions
 Wolf+0.010
 cub+0.009
handed+0.009
 baby+0.009
 anyway+0.009
Neg logit contributions
issors-0.011
ocus-0.011
 similarities-0.010
ets-0.010
 seventeen-0.010
Tokenpper
Token ID2848
Feature activation-5.69e-01

Pos logit contributions
ocus+0.125
issors+0.123
 seventeen+0.114
 similarities+0.112
ets+0.111
Neg logit contributions
 Wolf-0.137
handed-0.132
seat-0.132
 baby-0.132
 therm-0.128
Token sighed
Token ID21893
Feature activation+3.31e-01

Pos logit contributions
issors+0.026
ocus+0.026
 similarities+0.026
ets+0.025
 seventeen+0.025
Neg logit contributions
 Wolf-0.013
handed-0.013
 cub-0.012
 anyway-0.012
Mo-0.012
Token and
Token ID290
Feature activation-1.36e-01

Pos logit contributions
handed+0.009
 Wolf+0.009
Mo+0.008
rolley+0.008
seat+0.008
Neg logit contributions
ocus-0.014
 similarities-0.013
issors-0.013
ets-0.013
 seventeen-0.013
Token decided
Token ID3066
Feature activation+3.98e-01

Pos logit contributions
ocus+0.005
 similarities+0.005
issors+0.005
ets+0.005
 seventeen+0.005
Neg logit contributions
handed-0.004
 Wolf-0.004
rolley-0.004
seat-0.004
Mo-0.004
Token to
Token ID284
Feature activation+5.59e-02

Pos logit contributions
handed+0.012
 Wolf+0.012
Mo+0.011
seat+0.011
 cub+0.011
Neg logit contributions
ocus-0.015
 similarities-0.015
issors-0.015
ets-0.015
 seventeen-0.014
Token the
Token ID262
Feature activation+1.61e-01

Pos logit contributions
 similarities+0.031
 ey+0.030
issors+0.030
 brushes+0.029
 ind+0.028
Neg logit contributions
handed-0.021
 Wolf-0.021
rolley-0.021
burn-0.020
 cub-0.020
Token wardrobe
Token ID35593
Feature activation+2.63e-01

Pos logit contributions
handed+0.004
 able+0.004
 Wolf+0.004
Mo+0.004
ge+0.004
Neg logit contributions
 similarities-0.006
issors-0.006
ets-0.006
ocus-0.006
 seventeen-0.006
Token a
Token ID257
Feature activation-2.10e-01

Pos logit contributions
 Wolf+0.006
handed+0.005
Mo+0.005
 cub+0.005
 baby+0.005
Neg logit contributions
ocus-0.013
issors-0.013
ets-0.012
 similarities-0.012
 seventeen-0.012
Token few
Token ID1178
Feature activation+1.77e-01

Pos logit contributions
ocus+0.008
issors+0.008
 similarities+0.008
ets+0.008
 seventeen+0.008
Neg logit contributions
handed-0.006
 Wolf-0.006
Mo-0.006
 cub-0.006
hand-0.006
Token days
Token ID1528
Feature activation-8.26e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
burn+0.005
Mo+0.005
 Wilson+0.005
Neg logit contributions
ocus-0.006
 similarities-0.006
ets-0.006
issors-0.006
 seventeen-0.006
Token ago
Token ID2084
Feature activation-3.69e+00

Pos logit contributions
ocus+0.029
ets+0.028
issors+0.027
 similarities+0.026
 ind+0.024
Neg logit contributions
 Wolf-0.030
handed-0.028
Mo-0.028
 cub-0.027
burn-0.027
Token,
Token ID11
Feature activation-2.76e-01

Pos logit contributions
ocus+0.186
issors+0.185
ets+0.180
 similarities+0.179
aces+0.173
Neg logit contributions
 Wolf-0.069
handed-0.067
Mo-0.064
 cub-0.059
 therm-0.058
Token so
Token ID523
Feature activation-7.00e-01

Pos logit contributions
issors+0.014
ocus+0.013
 similarities+0.013
 seventeen+0.013
ets+0.013
Neg logit contributions
 Wolf-0.006
handed-0.006
 anyway-0.006
 baby-0.005
 therm-0.005
Token she
Token ID673
Feature activation-3.06e-01

Pos logit contributions
 similarities+0.033
ocus+0.033
issors+0.033
 meanings+0.032
 ind+0.031
Neg logit contributions
handed-0.014
 Wolf-0.013
rolley-0.013
 cub-0.012
burn-0.012
Token opened
Token ID4721
Feature activation-5.26e-02

Pos logit contributions
issors+0.016
 similarities+0.016
ocus+0.016
 seventeen+0.015
ets+0.015
Neg logit contributions
 Wolf-0.005
handed-0.005
 cub-0.005
 anyway-0.005
 baby-0.005
Token it
Token ID340
Feature activation-6.27e-01

Pos logit contributions
 ind+0.002
ocus+0.002
issors+0.002
 similarities+0.001
 brushes+0.001
Neg logit contributions
handed-0.002
 Wolf-0.002
rolley-0.002
burn-0.002
 cub-0.002
Token?"
Token ID1701
Feature activation+7.84e-01

Pos logit contributions
 similarities+0.025
issors+0.025
ocus+0.025
 seventeen+0.024
ets+0.024
Neg logit contributions
 anyway-0.011
 Wolf-0.010
handed-0.010
.-0.010
!-0.010
Token
Token ID198
Feature activation+5.37e-01

Pos logit contributions
burn+0.018
handed+0.018
rolley+0.017
 Wolf+0.017
seat+0.016
Neg logit contributions
ocus-0.035
issors-0.035
 similarities-0.034
 seventeen-0.032
 ind-0.032
Token
Token ID198
Feature activation+6.57e-01

Pos logit contributions
burn+0.012
rolley+0.011
handed+0.011
seat+0.011
 baby+0.011
Neg logit contributions
issors-0.024
ocus-0.024
 similarities-0.023
 seventeen-0.023
 ind-0.022
TokenThe
Token ID464
Feature activation-8.00e-03

Pos logit contributions
 Wolf+0.016
handed+0.016
seat+0.015
 baby+0.015
 anyway+0.015
Neg logit contributions
ocus-0.029
issors-0.028
 similarities-0.028
 seventeen-0.027
ets-0.026
Token grass
Token ID8701
Feature activation+3.03e-01

Pos logit contributions
issors+0.000
 similarities+0.000
ocus+0.000
 seventeen+0.000
 ind+0.000
Neg logit contributions
handed-0.000
seat-0.000
 Wolf-0.000
hand-0.000
burn-0.000
Tokenho
Token ID8873
Feature activation-3.69e+00

Pos logit contributions
 Wolf+0.011
 cub+0.010
handed+0.010
 therm+0.010
 baby+0.010
Neg logit contributions
issors-0.011
ocus-0.010
 similarities-0.010
ets-0.010
 seventeen-0.009
Tokenpper
Token ID2848
Feature activation-5.19e-01

Pos logit contributions
ocus+0.119
issors+0.116
 seventeen+0.108
 ind+0.103
ets+0.103
Neg logit contributions
 Wolf-0.139
seat-0.135
 baby-0.135
handed-0.133
rolley-0.131
Token said
Token ID531
Feature activation+5.86e-01

Pos logit contributions
issors+0.024
ocus+0.024
 similarities+0.023
ets+0.023
 seventeen+0.022
Neg logit contributions
 Wolf-0.012
handed-0.012
 cub-0.011
Mo-0.011
 anyway-0.011
Token,
Token ID11
Feature activation+1.61e-01

Pos logit contributions
handed+0.015
 Wolf+0.014
rolley+0.014
seat+0.014
Mo+0.013
Neg logit contributions
ocus-0.026
issors-0.025
 similarities-0.025
 seventeen-0.024
ets-0.024
Token "
Token ID366
Feature activation+2.52e-01

Pos logit contributions
handed+0.005
rolley+0.005
seat+0.005
 Wolf+0.005
burn+0.005
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
 seventeen-0.006
 ind-0.006
TokenI
Token ID40
Feature activation+1.09e+00

Pos logit contributions
 Wolf+0.005
handed+0.005
Mo+0.005
 cub+0.005
 anyway+0.005
Neg logit contributions
ocus-0.012
issors-0.012
 similarities-0.012
ets-0.012
 seventeen-0.011
Token so
Token ID523
Feature activation-1.78e-01

Pos logit contributions
handed+0.014
rolley+0.014
 Wolf+0.013
Mo+0.013
hand+0.013
Neg logit contributions
ocus-0.017
 ind-0.017
 seventeen-0.016
ets-0.015
 similarities-0.015
Token happy
Token ID3772
Feature activation-2.04e-01

Pos logit contributions
ocus+0.006
 similarities+0.005
 ind+0.005
 seventeen+0.005
ets+0.005
Neg logit contributions
 Wolf-0.007
handed-0.006
rolley-0.006
hand-0.006
burn-0.006
Token that
Token ID326
Feature activation-1.54e-01

Pos logit contributions
ocus+0.009
ets+0.009
 similarities+0.008
issors+0.008
apes+0.008
Neg logit contributions
handed-0.005
 Wolf-0.005
Mo-0.005
burn-0.005
rolley-0.005
Token the
Token ID262
Feature activation+3.93e-03

Pos logit contributions
 similarities+0.007
issors+0.007
ocus+0.007
 ind+0.007
 seventeen+0.007
Neg logit contributions
handed-0.003
rolley-0.003
hand-0.003
Mo-0.003
 Wolf-0.003
Token grass
Token ID8701
Feature activation+2.51e-02

Pos logit contributions
handed+0.000
 Wolf+0.000
 cub+0.000
Mo+0.000
 anyway+0.000
Neg logit contributions
issors-0.000
 similarities-0.000
ocus-0.000
ets-0.000
 seventeen-0.000
Tokenho
Token ID8873
Feature activation-3.59e+00

Pos logit contributions
handed+0.001
 Wolf+0.001
Mo+0.000
 cub+0.000
 anyway+0.000
Neg logit contributions
ocus-0.001
issors-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Tokenpper
Token ID2848
Feature activation-6.89e-01

Pos logit contributions
ocus+0.125
issors+0.119
ets+0.113
 similarities+0.111
 seventeen+0.111
Neg logit contributions
 Wolf-0.127
handed-0.122
seat-0.121
 baby-0.119
rolley-0.119
Token had
Token ID550
Feature activation-6.78e-01

Pos logit contributions
ocus+0.027
ets+0.027
 similarities+0.027
issors+0.026
 ind+0.025
Neg logit contributions
handed-0.020
 Wolf-0.020
burn-0.018
Mo-0.018
rolley-0.018
Token said
Token ID531
Feature activation+9.51e-01

Pos logit contributions
 similarities+0.027
ocus+0.027
ets+0.026
issors+0.026
 ind+0.025
Neg logit contributions
 Wolf-0.020
handed-0.020
 therm-0.018
 cub-0.018
rolley-0.018
Token yes
Token ID3763
Feature activation-5.09e-01

Pos logit contributions
handed+0.026
 Wolf+0.025
rolley+0.023
Mo+0.023
 cub+0.023
Neg logit contributions
ocus-0.040
 similarities-0.039
issors-0.039
 seventeen-0.038
ets-0.038
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
ets+0.027
ocus+0.026
issors+0.026
 similarities+0.026
 ind+0.025
Neg logit contributions
handed-0.009
seat-0.008
 Wolf-0.008
rolley-0.008
eled-0.007
Tokenried
Token ID2228
Feature activation+5.60e-01

Pos logit contributions
 Wolf+0.015
handed+0.014
 cub+0.014
 baby+0.014
 therm+0.014
Neg logit contributions
ocus-0.018
issors-0.017
ets-0.016
 similarities-0.016
 seventeen-0.016
Tokenly
Token ID306
Feature activation+3.52e-02

Pos logit contributions
 Wolf+0.010
handed+0.010
 cub+0.009
Mo+0.009
 anyway+0.009
Neg logit contributions
issors-0.029
ocus-0.029
 similarities-0.028
ets-0.028
 seventeen-0.027
Token,
Token ID11
Feature activation+2.19e-01

Pos logit contributions
 Wolf+0.001
handed+0.001
Mo+0.001
rolley+0.001
burn+0.001
Neg logit contributions
ocus-0.001
issors-0.001
ets-0.001
 similarities-0.001
 seventeen-0.001
Token the
Token ID262
Feature activation-3.90e-01

Pos logit contributions
handed+0.006
 Wolf+0.005
rolley+0.005
burn+0.005
seat+0.005
Neg logit contributions
ocus-0.009
 similarities-0.009
issors-0.009
ets-0.009
 seventeen-0.009
Token grass
Token ID8701
Feature activation+1.17e-01

Pos logit contributions
issors+0.017
 similarities+0.017
ocus+0.017
 seventeen+0.016
ets+0.016
Neg logit contributions
handed-0.010
 Wolf-0.010
seat-0.009
Mo-0.009
 anyway-0.009
Tokenho
Token ID8873
Feature activation-3.49e+00

Pos logit contributions
handed+0.004
 Wolf+0.004
Mo+0.003
 cub+0.003
 anyway+0.003
Neg logit contributions
ocus-0.005
issors-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Tokenpper
Token ID2848
Feature activation-6.19e-01

Pos logit contributions
ocus+0.112
issors+0.107
 seventeen+0.100
ets+0.100
 ind+0.095
Neg logit contributions
 Wolf-0.137
seat-0.130
 baby-0.128
handed-0.127
rolley-0.127
Token rushed
Token ID13999
Feature activation+8.41e-02

Pos logit contributions
ocus+0.026
ets+0.025
issors+0.024
 similarities+0.024
 ind+0.023
Neg logit contributions
 Wolf-0.017
handed-0.017
Mo-0.016
rolley-0.016
 therm-0.016
Token over
Token ID625
Feature activation+1.42e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
 cub+0.002
 therm+0.002
Mo+0.002
Neg logit contributions
issors-0.004
ocus-0.004
 similarities-0.004
ets-0.004
 seventeen-0.004
Token and
Token ID290
Feature activation-3.30e-02

Pos logit contributions
handed+0.005
 Wolf+0.004
burn+0.004
rolley+0.004
 therm+0.004
Neg logit contributions
ocus-0.005
 similarities-0.005
issors-0.005
ets-0.005
 ind-0.005
Token tried
Token ID3088
Feature activation+9.82e-01

Pos logit contributions
ocus+0.001
issors+0.001
 similarities+0.001
ets+0.001
 ind+0.001
Neg logit contributions
handed-0.001
 Wolf-0.001
rolley-0.001
Mo-0.001
burn-0.001
Token coins
Token ID10796
Feature activation-1.13e-01

Pos logit contributions
issors+0.003
ocus+0.003
 similarities+0.003
ets+0.003
 seventeen+0.003
Neg logit contributions
 cub-0.003
 baby-0.003
 Wolf-0.003
 one-0.002
handed-0.002
Token that
Token ID326
Feature activation+5.17e-02

Pos logit contributions
issors+0.006
ocus+0.006
 similarities+0.006
ets+0.006
 seventeen+0.006
Neg logit contributions
 Wolf-0.001
handed-0.001
 cub-0.001
 anyway-0.001
 baby-0.001
Token people
Token ID661
Feature activation+2.42e-01

Pos logit contributions
 Wolf+0.001
handed+0.001
 baby+0.001
 cub+0.001
 therm+0.001
Neg logit contributions
ocus-0.002
issors-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token used
Token ID973
Feature activation-9.64e-01

Pos logit contributions
handed+0.007
 Wolf+0.007
 cub+0.007
 baby+0.006
 anyway+0.006
Neg logit contributions
issors-0.010
ocus-0.010
 similarities-0.010
 seventeen-0.009
ets-0.009
Token long
Token ID890
Feature activation-5.50e-01

Pos logit contributions
ocus+0.047
issors+0.046
 similarities+0.045
 seventeen+0.044
ets+0.043
Neg logit contributions
 Wolf-0.019
 baby-0.019
 cub-0.019
 anyway-0.019
handed-0.019
Token ago
Token ID2084
Feature activation-3.44e+00

Pos logit contributions
issors+0.021
 similarities+0.020
ocus+0.020
 narrative+0.019
 seventeen+0.019
Neg logit contributions
 cub-0.017
.-0.016
 Wolf-0.016
 one-0.016
 therm-0.016
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
issors+0.205
ocus+0.204
 similarities+0.202
ets+0.198
 seventeen+0.195
Neg logit contributions
 Wolf-0.034
handed-0.032
Mo-0.026
 cub-0.025
 therm-0.024
Token They
Token ID1119
Feature activation+4.55e-01

Pos logit contributions
issors+0.005
ocus+0.005
 similarities+0.005
 seventeen+0.005
ets+0.005
Neg logit contributions
handed-0.004
 Wolf-0.004
Mo-0.003
 cub-0.003
burn-0.003
Token saw
Token ID2497
Feature activation-9.08e-01

Pos logit contributions
 Wolf+0.011
handed+0.011
 cub+0.011
 baby+0.011
 anyway+0.010
Neg logit contributions
ocus-0.020
issors-0.020
 similarities-0.020
ets-0.019
 seventeen-0.019
Token paintings
Token ID21641
Feature activation-2.81e-02

Pos logit contributions
issors+0.039
ocus+0.039
 similarities+0.038
ets+0.037
 seventeen+0.036
Neg logit contributions
 Wolf-0.024
handed-0.024
 cub-0.022
 baby-0.022
Mo-0.022
Token and
Token ID290
Feature activation-2.00e-02

Pos logit contributions
issors+0.001
 similarities+0.001
ocus+0.001
ets+0.001
 seventeen+0.001
Neg logit contributions
.-0.000
 cub-0.000
 one-0.000
 baby-0.000
 Wolf-0.000
Token her
Token ID607
Feature activation+9.22e-01

Pos logit contributions
issors+0.033
 similarities+0.033
ocus+0.033
ets+0.032
 seventeen+0.031
Neg logit contributions
handed-0.011
 Wolf-0.011
 cub-0.010
Mo-0.009
seat-0.009
Token birthday
Token ID10955
Feature activation-7.96e-01

Pos logit contributions
 Wolf+0.013
handed+0.013
Mo+0.011
 cub+0.011
 therm+0.011
Neg logit contributions
issors-0.050
ocus-0.050
 similarities-0.050
ets-0.049
 seventeen-0.047
Token a
Token ID257
Feature activation+2.64e-01

Pos logit contributions
issors+0.044
ets+0.043
 similarities+0.043
ocus+0.042
 ind+0.040
Neg logit contributions
 Wolf-0.011
handed-0.011
Mo-0.010
 cub-0.009
 therm-0.009
Token few
Token ID1178
Feature activation+4.61e-01

Pos logit contributions
handed+0.008
 Wolf+0.008
Mo+0.008
rolley+0.008
seat+0.008
Neg logit contributions
 similarities-0.010
issors-0.010
ocus-0.009
ets-0.009
 seventeen-0.009
Token days
Token ID1528
Feature activation-6.08e-01

Pos logit contributions
 Wolf+0.014
handed+0.014
Mo+0.013
 cub+0.013
 therm+0.012
Neg logit contributions
issors-0.018
ocus-0.018
 similarities-0.018
ets-0.017
 seventeen-0.017
Token ago
Token ID2084
Feature activation-3.43e+00

Pos logit contributions
ocus+0.032
issors+0.032
ets+0.031
 similarities+0.030
 ind+0.029
Neg logit contributions
 Wolf-0.011
handed-0.010
Mo-0.010
 cub-0.009
 therm-0.008
Token.
Token ID13
Feature activation+3.33e-01

Pos logit contributions
issors+0.190
ocus+0.189
 similarities+0.184
ets+0.184
aces+0.179
Neg logit contributions
 Wolf-0.050
handed-0.046
Mo-0.043
 cub-0.038
 therm-0.037
Token She
Token ID1375
Feature activation+9.90e-01

Pos logit contributions
handed+0.009
 Wolf+0.009
burn+0.008
 therm+0.008
 cub+0.008
Neg logit contributions
issors-0.014
ocus-0.014
 similarities-0.014
ets-0.014
 seventeen-0.013
Token liked
Token ID8288
Feature activation+3.50e-01

Pos logit contributions
 Wolf+0.023
handed+0.022
 cub+0.021
 baby+0.021
 anyway+0.021
Neg logit contributions
issors-0.046
ocus-0.045
 similarities-0.045
ets-0.043
 seventeen-0.043
Token to
Token ID284
Feature activation+4.08e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 baby+0.006
 anyway+0.006
 cub+0.006
Neg logit contributions
issors-0.017
ocus-0.017
 similarities-0.017
ets-0.017
 seventeen-0.016
Token practice
Token ID3357
Feature activation+1.69e-01

Pos logit contributions
 Wolf+0.013
handed+0.012
 anyway+0.012
 baby+0.012
 one+0.012
Neg logit contributions
ocus-0.015
issors-0.015
 similarities-0.015
 seventeen-0.014
ets-0.014
Token of
Token ID286
Feature activation+6.02e-02

Pos logit contributions
handed+0.011
 Wolf+0.011
 cub+0.010
 anyway+0.010
 therm+0.010
Neg logit contributions
 similarities-0.027
issors-0.027
ocus-0.026
 seventeen-0.025
ets-0.025
Token animals
Token ID4695
Feature activation+2.90e-01

Pos logit contributions
 Wolf+0.002
 cub+0.002
 baby+0.002
handed+0.002
 therm+0.002
Neg logit contributions
issors-0.002
ocus-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token that
Token ID326
Feature activation-9.09e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.005
 anyway+0.005
 baby+0.005
Neg logit contributions
issors-0.014
ocus-0.014
 similarities-0.014
ets-0.013
 seventeen-0.013
Token lived
Token ID5615
Feature activation+6.37e-01

Pos logit contributions
ocus+0.043
issors+0.042
 similarities+0.041
 seventeen+0.040
ets+0.040
Neg logit contributions
 Wolf-0.021
handed-0.020
 cub-0.020
 baby-0.020
 anyway-0.019
Token long
Token ID890
Feature activation-4.87e-01

Pos logit contributions
 Wolf+0.016
handed+0.016
 cub+0.015
Mo+0.015
 therm+0.015
Neg logit contributions
ocus-0.027
issors-0.027
 similarities-0.027
ets-0.026
 seventeen-0.026
Token ago
Token ID2084
Feature activation-3.43e+00

Pos logit contributions
issors+0.024
 similarities+0.024
ocus+0.024
 seventeen+0.022
ets+0.022
Neg logit contributions
handed-0.009
 cub-0.009
 Wolf-0.009
.-0.009
 one-0.009
Token.
Token ID13
Feature activation+3.77e-02

Pos logit contributions
issors+0.189
ocus+0.189
 similarities+0.186
ets+0.184
 seventeen+0.179
Neg logit contributions
 Wolf-0.049
handed-0.046
Mo-0.043
 cub-0.039
 therm-0.038
Token They
Token ID1119
Feature activation+5.31e-01

Pos logit contributions
 Wolf+0.001
 another+0.001
 baby+0.001
handed+0.001
 anyway+0.001
Neg logit contributions
ocus-0.002
 similarities-0.002
issors-0.002
ets-0.002
 seventeen-0.002
Token saw
Token ID2497
Feature activation-8.69e-01

Pos logit contributions
 Wolf+0.013
 cub+0.013
 baby+0.013
handed+0.013
 anyway+0.012
Neg logit contributions
issors-0.023
ocus-0.023
 similarities-0.023
ets-0.022
 seventeen-0.022
Token shiny
Token ID22441
Feature activation-7.37e-02

Pos logit contributions
issors+0.037
ocus+0.037
 similarities+0.036
ets+0.035
 seventeen+0.035
Neg logit contributions
 Wolf-0.023
handed-0.023
 cub-0.021
 baby-0.021
 anyway-0.021
Token rocks
Token ID12586
Feature activation-2.79e-01

Pos logit contributions
issors+0.003
 similarities+0.003
ocus+0.003
 seventeen+0.003
 narrative+0.003
Neg logit contributions
 cub-0.002
.-0.002
 one-0.002
 baby-0.002
 therm-0.002
Token ac
Token ID936
Feature activation-8.97e-01

Pos logit contributions
ocus+0.036
 similarities+0.035
issors+0.034
ets+0.034
 ind+0.034
Neg logit contributions
 Wolf-0.026
handed-0.026
hand-0.025
seat-0.024
burn-0.024
Tokenorn
Token ID1211
Feature activation-3.33e-01

Pos logit contributions
ocus+0.036
issors+0.035
ets+0.034
 similarities+0.034
 seventeen+0.032
Neg logit contributions
 Wolf-0.026
handed-0.025
 baby-0.025
 cub-0.025
hand-0.025
Token a
Token ID257
Feature activation-3.72e-01

Pos logit contributions
issors+0.015
ocus+0.015
 similarities+0.015
ets+0.014
 seventeen+0.014
Neg logit contributions
 Wolf-0.008
handed-0.008
 cub-0.007
 anyway-0.007
Mo-0.007
Token few
Token ID1178
Feature activation+1.71e-01

Pos logit contributions
 similarities+0.014
ocus+0.014
issors+0.014
 seventeen+0.013
ets+0.013
Neg logit contributions
handed-0.012
 Wolf-0.011
hand-0.011
seat-0.011
Mo-0.010
Token days
Token ID1528
Feature activation-8.36e-01

Pos logit contributions
 Wolf+0.005
handed+0.005
Mo+0.004
burn+0.004
 cub+0.004
Neg logit contributions
ocus-0.007
issors-0.007
 similarities-0.007
ets-0.007
 seventeen-0.007
Token ago
Token ID2084
Feature activation-3.42e+00

Pos logit contributions
ocus+0.039
issors+0.039
 similarities+0.038
ets+0.037
 seventeen+0.036
Neg logit contributions
 Wolf-0.019
handed-0.019
 cub-0.017
Mo-0.017
 therm-0.017
Token so
Token ID523
Feature activation-2.98e-01

Pos logit contributions
issors+0.186
ocus+0.186
 similarities+0.184
ets+0.179
 seventeen+0.177
Neg logit contributions
 Wolf-0.049
handed-0.048
 cub-0.041
Mo-0.041
 anyway-0.040
Token I
Token ID314
Feature activation+6.24e-01

Pos logit contributions
issors+0.011
ocus+0.011
 similarities+0.010
ets+0.010
 seventeen+0.010
Neg logit contributions
 Wolf-0.010
handed-0.010
 cub-0.009
Mo-0.009
 baby-0.009
Token could
Token ID714
Feature activation-3.02e-01

Pos logit contributions
handed+0.022
 Wolf+0.022
 anyway+0.021
 cub+0.021
 baby+0.020
Neg logit contributions
issors-0.021
 similarities-0.021
ocus-0.021
 seventeen-0.020
ets-0.019
Token have
Token ID423
Feature activation+1.65e-01

Pos logit contributions
issors+0.012
ocus+0.012
 similarities+0.012
 seventeen+0.012
ets+0.012
Neg logit contributions
handed-0.009
 Wolf-0.008
 anyway-0.008
 baby-0.008
 therm-0.008
Token some
Token ID617
Feature activation+6.38e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
seat+0.004
rolley+0.004
 Wilson+0.004
Neg logit contributions
ocus-0.007
 similarities-0.007
ets-0.007
issors-0.007
 ind-0.007
Token the
Token ID262
Feature activation+5.93e-02

Pos logit contributions
 similarities+0.012
ets+0.012
issors+0.012
 differences+0.011
ocus+0.011
Neg logit contributions
handed-0.009
seat-0.009
rolley-0.008
eled-0.008
 unconscious-0.008
Token pigeon
Token ID46387
Feature activation-1.40e-01

Pos logit contributions
handed+0.001
 Wolf+0.001
Mo+0.001
seat+0.001
rolley+0.001
Neg logit contributions
 similarities-0.003
issors-0.002
ocus-0.002
ets-0.002
 ind-0.002
Token all
Token ID477
Feature activation-8.50e-02

Pos logit contributions
ets+0.006
ocus+0.006
 similarities+0.006
issors+0.005
 ind+0.005
Neg logit contributions
 Wolf-0.004
Mo-0.003
rolley-0.003
handed-0.003
 therm-0.003
Token those
Token ID883
Feature activation+1.90e-01

Pos logit contributions
ocus+0.004
 similarities+0.004
issors+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.002
handed-0.002
Mo-0.002
 cub-0.002
 therm-0.002
Token weeks
Token ID2745
Feature activation-1.02e+00

Pos logit contributions
 Wolf+0.005
handed+0.005
 cub+0.005
 baby+0.004
 anyway+0.004
Neg logit contributions
issors-0.008
ocus-0.008
 similarities-0.008
 seventeen-0.008
ets-0.008
Token ago
Token ID2084
Feature activation-3.40e+00

Pos logit contributions
ocus+0.049
ets+0.048
issors+0.048
 similarities+0.047
 ind+0.044
Neg logit contributions
 Wolf-0.022
handed-0.021
Mo-0.020
 cub-0.020
 therm-0.019
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
ocus+0.176
issors+0.176
 similarities+0.175
ets+0.173
 seventeen+0.166
Neg logit contributions
 Wolf-0.057
handed-0.055
Mo-0.052
 therm-0.048
 cub-0.048
Token<|endoftext|>
Token ID50256
Feature activation+1.82e-01

Pos logit contributions
 similarities+0.012
ocus+0.012
 Here+0.011
 ind+0.011
issors+0.011
Neg logit contributions
handed-0.011
burn-0.011
ge-0.010
 able-0.009
 anyway-0.009
TokenMike
Token ID16073
Feature activation+1.66e-01

Pos logit contributions
handed+0.004
 able+0.004
burn+0.004
 therm+0.004
 baby+0.004
Neg logit contributions
ocus-0.008
 similarities-0.007
issors-0.007
ets-0.007
 does-0.007
Token and
Token ID290
Feature activation-1.95e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
Mo+0.004
 therm+0.004
 anyway+0.004
Neg logit contributions
ocus-0.007
issors-0.007
 similarities-0.007
ets-0.007
 seventeen-0.007
Token his
Token ID465
Feature activation+3.56e-01

Pos logit contributions
issors+0.010
 similarities+0.010
ocus+0.010
ets+0.010
 seventeen+0.010
Neg logit contributions
handed-0.003
 Wolf-0.003
 anyway-0.002
 therm-0.002
Mo-0.002
Token by
Token ID416
Feature activation-5.37e-01

Pos logit contributions
issors+0.025
ocus+0.025
 similarities+0.025
ets+0.024
 seventeen+0.023
Neg logit contributions
 Wolf-0.011
handed-0.011
 cub-0.010
 baby-0.010
Mo-0.010
Token a
Token ID257
Feature activation-2.07e-01

Pos logit contributions
issors+0.024
ocus+0.024
 similarities+0.023
ets+0.022
 seventeen+0.022
Neg logit contributions
 Wolf-0.013
handed-0.013
 cub-0.013
 baby-0.012
 anyway-0.012
Token famous
Token ID5863
Feature activation-1.14e-01

Pos logit contributions
issors+0.009
ocus+0.009
 similarities+0.008
ets+0.008
 seventeen+0.008
Neg logit contributions
 Wolf-0.006
 baby-0.006
handed-0.005
 cub-0.005
 therm-0.005
Token artist
Token ID6802
Feature activation-8.11e-01

Pos logit contributions
issors+0.005
ocus+0.005
 similarities+0.005
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.003
 baby-0.003
 cub-0.003
handed-0.003
 one-0.003
Token long
Token ID890
Feature activation-6.93e-01

Pos logit contributions
ocus+0.045
issors+0.044
ets+0.044
 similarities+0.044
 ind+0.042
Neg logit contributions
 Wolf-0.012
handed-0.012
Mo-0.010
 therm-0.009
hand-0.009
Token ago
Token ID2084
Feature activation-3.39e+00

Pos logit contributions
ocus+0.031
issors+0.031
 similarities+0.031
 seventeen+0.030
ets+0.029
Neg logit contributions
 Wolf-0.016
handed-0.016
 cub-0.015
 baby-0.015
 anyway-0.015
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
issors+0.186
ocus+0.185
 similarities+0.182
ets+0.181
aces+0.175
Neg logit contributions
 Wolf-0.050
handed-0.047
Mo-0.044
 therm-0.040
 cub-0.040
Token
Token ID220
Feature activation+1.78e-01

Pos logit contributions
issors+0.007
ocus+0.007
 similarities+0.007
ets+0.007
 seventeen+0.007
Neg logit contributions
 Wolf-0.003
handed-0.003
 cub-0.002
Mo-0.002
 anyway-0.002
Token
Token ID198
Feature activation+3.15e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
 therm+0.004
burn+0.004
 cub+0.004
Neg logit contributions
issors-0.008
ocus-0.008
 similarities-0.008
ets-0.008
apes-0.008
Token
Token ID198
Feature activation+5.97e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
burn+0.006
 therm+0.006
 baby+0.006
Neg logit contributions
 similarities-0.015
issors-0.015
ocus-0.015
ets-0.014
apes-0.014
TokenOne
Token ID3198
Feature activation-4.77e-01

Pos logit contributions
 Wolf+0.011
handed+0.011
Mo+0.010
 anyway+0.010
 cub+0.010
Neg logit contributions
issors-0.030
ocus-0.030
 similarities-0.029
ets-0.029
 seventeen-0.029
Token time
Token ID640
Feature activation-1.05e+00

Pos logit contributions
 Wolf+0.024
handed+0.024
 anyway+0.023
 cub+0.023
Mo+0.023
Neg logit contributions
issors-0.025
ocus-0.025
 similarities-0.025
 seventeen-0.023
ets-0.023
Token,
Token ID11
Feature activation-4.67e-01

Pos logit contributions
issors+0.053
 similarities+0.052
ocus+0.052
ets+0.051
 seventeen+0.050
Neg logit contributions
 Wolf-0.020
handed-0.019
 cub-0.018
Mo-0.018
 baby-0.018
Token not
Token ID407
Feature activation-2.67e-01

Pos logit contributions
issors+0.023
 similarities+0.023
ocus+0.023
ets+0.022
 seventeen+0.022
Neg logit contributions
 Wolf-0.009
handed-0.009
 cub-0.008
 baby-0.008
Mo-0.008
Token so
Token ID523
Feature activation-1.38e-01

Pos logit contributions
issors+0.013
ocus+0.013
 similarities+0.013
ets+0.013
 seventeen+0.013
Neg logit contributions
 Wolf-0.005
handed-0.005
 cub-0.004
Mo-0.004
 baby-0.004
Token long
Token ID890
Feature activation+2.09e-01

Pos logit contributions
issors+0.007
ocus+0.007
 similarities+0.007
ets+0.007
 seventeen+0.007
Neg logit contributions
 Wolf-0.002
handed-0.002
 anyway-0.002
Mo-0.002
 cub-0.002
Token ago
Token ID2084
Feature activation-3.38e+00

Pos logit contributions
handed+0.005
 Wolf+0.004
 cub+0.004
Mo+0.004
 anyway+0.004
Neg logit contributions
ocus-0.010
issors-0.010
 similarities-0.010
ets-0.009
 seventeen-0.009
Token,
Token ID11
Feature activation-3.47e-01

Pos logit contributions
ocus+0.164
issors+0.162
 similarities+0.161
ets+0.157
aces+0.154
Neg logit contributions
 Wolf-0.067
handed-0.066
Mo-0.065
rolley-0.058
 therm-0.058
Token there
Token ID612
Feature activation+3.93e-02

Pos logit contributions
issors+0.019
ocus+0.019
 similarities+0.018
ets+0.018
 seventeen+0.018
Neg logit contributions
 Wolf-0.006
 baby-0.005
 cub-0.005
Mo-0.005
handed-0.005
Token was
Token ID373
Feature activation+1.30e+00

Pos logit contributions
handed+0.001
 Wolf+0.001
rolley+0.001
burn+0.001
hand+0.001
Neg logit contributions
ocus-0.002
 similarities-0.002
issors-0.002
 ind-0.002
 seventeen-0.002
Token a
Token ID257
Feature activation+1.97e-01

Pos logit contributions
handed+0.022
 Wolf+0.021
rolley+0.019
 cub+0.019
seat+0.019
Neg logit contributions
ocus-0.067
issors-0.067
 similarities-0.067
ets-0.064
 seventeen-0.064
Token big
Token ID1263
Feature activation+2.88e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
 cub+0.004
 baby+0.004
 therm+0.004
Neg logit contributions
issors-0.009
ocus-0.009
 similarities-0.009
ets-0.009
 seventeen-0.009
Token Daisy
Token ID40355
Feature activation+1.70e-02

Pos logit contributions
issors+0.002
ocus+0.002
 similarities+0.002
ets+0.002
 seventeen+0.002
Neg logit contributions
handed-0.002
burn-0.002
 Wolf-0.002
 therm-0.002
 cub-0.002
Token had
Token ID550
Feature activation-6.76e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
 cub+0.000
Mo+0.000
 therm+0.000
Neg logit contributions
ocus-0.001
issors-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Token planted
Token ID18969
Feature activation+3.08e-01

Pos logit contributions
ocus+0.031
issors+0.031
 similarities+0.031
ets+0.030
 seventeen+0.030
Neg logit contributions
 Wolf-0.015
handed-0.015
 cub-0.014
Mo-0.014
 therm-0.013
Token it
Token ID340
Feature activation-1.04e+00

Pos logit contributions
handed+0.006
 Wolf+0.006
 cub+0.005
Mo+0.005
 therm+0.005
Neg logit contributions
ocus-0.015
issors-0.015
 similarities-0.015
ets-0.015
 seventeen-0.014
Token weeks
Token ID2745
Feature activation-1.08e+00

Pos logit contributions
ocus+0.043
issors+0.043
 similarities+0.042
ets+0.041
 seventeen+0.040
Neg logit contributions
 Wolf-0.029
handed-0.029
 cub-0.026
Mo-0.026
 therm-0.026
Token ago
Token ID2084
Feature activation-3.32e+00

Pos logit contributions
ocus+0.046
issors+0.046
 similarities+0.045
ets+0.044
 seventeen+0.043
Neg logit contributions
 Wolf-0.029
handed-0.028
 cub-0.026
Mo-0.026
 therm-0.026
Token,
Token ID11
Feature activation+3.59e-02

Pos logit contributions
ocus+0.145
issors+0.144
 similarities+0.142
ets+0.140
 seventeen+0.135
Neg logit contributions
 Wolf-0.084
handed-0.082
Mo-0.077
 cub-0.075
 therm-0.074
Token but
Token ID475
Feature activation+1.01e+00

Pos logit contributions
handed+0.001
 Wolf+0.001
 anyway+0.001
 baby+0.001
 cub+0.001
Neg logit contributions
issors-0.002
ocus-0.002
 similarities-0.002
 seventeen-0.002
ets-0.002
Token now
Token ID783
Feature activation-1.42e-01

Pos logit contributions
 Wolf+0.018
handed+0.018
 cub+0.016
 anyway+0.016
 baby+0.016
Neg logit contributions
issors-0.051
ocus-0.051
 similarities-0.051
ets-0.049
 seventeen-0.049
Token she
Token ID673
Feature activation-1.23e-01

Pos logit contributions
 similarities+0.007
ocus+0.007
ets+0.007
issors+0.007
 ind+0.006
Neg logit contributions
handed-0.003
 Wolf-0.003
rolley-0.003
Mo-0.003
seat-0.003
Token could
Token ID714
Feature activation-1.04e+00

Pos logit contributions
issors+0.006
ocus+0.005
 similarities+0.005
ets+0.005
 seventeen+0.005
Neg logit contributions
 Wolf-0.003
handed-0.003
 cub-0.003
Mo-0.003
 anyway-0.003
Token But
Token ID887
Feature activation+1.37e+00

Pos logit contributions
issors+0.003
ocus+0.003
 similarities+0.003
ets+0.003
 seventeen+0.003
Neg logit contributions
handed-0.003
 Wolf-0.003
burn-0.003
 therm-0.003
Mo-0.003
Token it
Token ID340
Feature activation-6.28e-01

Pos logit contributions
 Wolf+0.024
handed+0.024
 cub+0.021
 baby+0.021
Mo+0.021
Neg logit contributions
issors-0.071
ocus-0.070
 similarities-0.070
ets-0.068
 seventeen-0.067
Token was
Token ID373
Feature activation+5.32e-01

Pos logit contributions
issors+0.033
ocus+0.032
 similarities+0.032
ets+0.031
 seventeen+0.031
Neg logit contributions
 Wolf-0.012
handed-0.011
 cub-0.010
 anyway-0.010
 baby-0.010
Token so
Token ID523
Feature activation-2.83e-01

Pos logit contributions
handed+0.013
 Wolf+0.013
rolley+0.012
Mo+0.012
seat+0.012
Neg logit contributions
ocus-0.024
issors-0.023
 similarities-0.023
 seventeen-0.023
ets-0.023
Token long
Token ID890
Feature activation-7.05e-01

Pos logit contributions
issors+0.012
ocus+0.012
 similarities+0.012
ets+0.012
 seventeen+0.012
Neg logit contributions
 Wolf-0.007
handed-0.007
 cub-0.007
Mo-0.007
 anyway-0.007
Token ago
Token ID2084
Feature activation-3.32e+00

Pos logit contributions
ocus+0.031
issors+0.031
 similarities+0.031
ets+0.030
 seventeen+0.029
Neg logit contributions
 Wolf-0.017
handed-0.017
 cub-0.016
Mo-0.016
 baby-0.015
Token that
Token ID326
Feature activation+1.39e-01

Pos logit contributions
ocus+0.149
issors+0.148
 similarities+0.145
ets+0.143
 seventeen+0.139
Neg logit contributions
 Wolf-0.079
handed-0.076
Mo-0.074
 cub-0.069
seat-0.069
Token everything
Token ID2279
Feature activation+7.77e-01

Pos logit contributions
handed+0.003
 Wolf+0.003
Mo+0.003
 cub+0.003
 therm+0.003
Neg logit contributions
ocus-0.007
 similarities-0.007
issors-0.007
ets-0.006
 seventeen-0.006
Token was
Token ID373
Feature activation+3.24e-01

Pos logit contributions
handed+0.017
 Wolf+0.017
Mo+0.015
 cub+0.015
 therm+0.015
Neg logit contributions
ocus-0.036
issors-0.036
 similarities-0.036
ets-0.035
 seventeen-0.034
Token a
Token ID257
Feature activation-1.07e-01

Pos logit contributions
handed+0.009
 Wolf+0.009
rolley+0.009
Mo+0.009
 cub+0.008
Neg logit contributions
ocus-0.013
issors-0.013
 similarities-0.013
ets-0.012
 seventeen-0.012
Token bit
Token ID1643
Feature activation+1.56e-01

Pos logit contributions
ocus+0.004
issors+0.004
 similarities+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
handed-0.003
 Wolf-0.003
Mo-0.003
 cub-0.003
 anyway-0.003
Token an
Token ID281
Feature activation-6.29e-02

Pos logit contributions
handed+0.021
 Wolf+0.021
Mo+0.018
 cub+0.018
 therm+0.018
Neg logit contributions
issors-0.068
ocus-0.068
 similarities-0.068
ets-0.066
 seventeen-0.065
Token ant
Token ID1885
Feature activation-8.39e-01

Pos logit contributions
ocus+0.003
issors+0.003
 similarities+0.003
ets+0.002
 seventeen+0.002
Neg logit contributions
 Wolf-0.002
handed-0.002
 baby-0.002
 cub-0.002
 therm-0.002
Token and
Token ID290
Feature activation-4.08e-01

Pos logit contributions
ocus+0.032
 similarities+0.031
issors+0.031
ets+0.030
 ind+0.030
Neg logit contributions
handed-0.025
hand-0.023
 Wolf-0.023
rolley-0.023
burn-0.023
Token a
Token ID257
Feature activation+2.12e-01

Pos logit contributions
 similarities+0.019
ocus+0.019
 ind+0.018
issors+0.018
 seventeen+0.017
Neg logit contributions
handed-0.010
rolley-0.009
burn-0.009
hand-0.009
 Wolf-0.008
Token grass
Token ID8701
Feature activation+4.32e-01

Pos logit contributions
handed+0.007
hand+0.006
rolley+0.006
seat+0.006
esh+0.006
Neg logit contributions
 similarities-0.008
ocus-0.008
 ind-0.008
issors-0.008
 seventeen-0.007
Tokenho
Token ID8873
Feature activation-3.31e+00

Pos logit contributions
handed+0.012
 Wolf+0.011
Mo+0.011
 Doctor+0.010
hand+0.010
Neg logit contributions
ocus-0.018
 similarities-0.017
issors-0.017
ets-0.017
 ind-0.017
Tokenpper
Token ID2848
Feature activation-3.19e-01

Pos logit contributions
ocus+0.103
issors+0.091
ets+0.088
 ind+0.087
ige+0.083
Neg logit contributions
 Wolf-0.131
seat-0.128
rolley-0.127
 Doctor-0.127
Where-0.124
Token.
Token ID13
Feature activation+5.10e-01

Pos logit contributions
 likes+0.012
ocus+0.012
 ind+0.012
 similarities+0.012
 does+0.012
Neg logit contributions
handed-0.010
burn-0.009
rolley-0.009
hand-0.009
 severe-0.008
Token The
Token ID383
Feature activation+2.34e-01

Pos logit contributions
 Wolf+0.015
 cub+0.014
 baby+0.013
handed+0.013
Mo+0.013
Neg logit contributions
ocus-0.022
issors-0.021
ets-0.021
 similarities-0.021
 seventeen-0.020
Token ant
Token ID1885
Feature activation-8.42e-01

Pos logit contributions
handed+0.007
 Wolf+0.006
 cub+0.006
hand+0.006
seat+0.006
Neg logit contributions
issors-0.010
 similarities-0.010
ocus-0.010
ets-0.009
 seventeen-0.009
Token was
Token ID373
Feature activation-1.99e-01

Pos logit contributions
issors+0.038
ocus+0.037
 similarities+0.036
 seventeen+0.036
ets+0.035
Neg logit contributions
 Wolf-0.021
 cub-0.021
 anyway-0.020
handed-0.020
 baby-0.020
Token ancestors
Token ID18668
Feature activation-3.76e-01

Pos logit contributions
handed+0.033
 Wolf+0.033
Mo+0.030
 cub+0.030
hand+0.030
Neg logit contributions
issors-0.053
ocus-0.053
 similarities-0.053
ets-0.051
 seventeen-0.049
Token who
Token ID508
Feature activation+1.90e-01

Pos logit contributions
ocus+0.019
issors+0.019
 similarities+0.019
ets+0.019
 seventeen+0.018
Neg logit contributions
handed-0.007
 Wolf-0.007
Mo-0.006
 cub-0.006
 therm-0.006
Token sang
Token ID25889
Feature activation+3.38e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.007
Mo+0.007
 baby+0.007
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
ets-0.005
 seventeen-0.005
Token it
Token ID340
Feature activation-1.24e+00

Pos logit contributions
 Wolf+0.007
 anyway+0.006
handed+0.006
 cub+0.006
 baby+0.006
Neg logit contributions
issors-0.017
ocus-0.017
 similarities-0.016
 seventeen-0.016
ets-0.016
Token long
Token ID890
Feature activation-9.91e-01

Pos logit contributions
ocus+0.057
issors+0.057
 similarities+0.057
ets+0.056
 seventeen+0.054
Neg logit contributions
 Wolf-0.028
handed-0.028
Mo-0.025
 cub-0.025
 therm-0.025
Token ago
Token ID2084
Feature activation-3.30e+00

Pos logit contributions
issors+0.052
ocus+0.052
 similarities+0.051
 seventeen+0.050
ets+0.049
Neg logit contributions
 Wolf-0.016
handed-0.016
 anyway-0.014
 cub-0.014
 baby-0.014
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
ocus+0.186
issors+0.186
 similarities+0.184
ets+0.180
 seventeen+0.176
Neg logit contributions
 Wolf-0.042
handed-0.041
Mo-0.035
 cub-0.034
 therm-0.033
Token Would
Token ID10928
Feature activation-8.69e-01

Pos logit contributions
issors+0.004
ocus+0.004
 similarities+0.004
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.004
 cub-0.004
Mo-0.004
 baby-0.004
handed-0.004
Token you
Token ID345
Feature activation-8.16e-01

Pos logit contributions
issors+0.031
ocus+0.030
 similarities+0.030
ets+0.029
 seventeen+0.028
Neg logit contributions
 Wolf-0.030
handed-0.029
 anyway-0.028
 cub-0.028
Mo-0.028
Token like
Token ID588
Feature activation-1.58e+00

Pos logit contributions
issors+0.032
ocus+0.030
 similarities+0.030
 seventeen+0.029
 ey+0.028
Neg logit contributions
 one-0.027
 another-0.026
 anyway-0.026
 soon-0.026
.-0.026
Token to
Token ID284
Feature activation-2.85e-01

Pos logit contributions
issors+0.079
ocus+0.077
 similarities+0.075
 seventeen+0.074
ets+0.073
Neg logit contributions
 Wolf-0.033
 anyway-0.031
 another-0.031
 one-0.031
 baby-0.030
Token who
Token ID508
Feature activation+5.54e-01

Pos logit contributions
handed+0.003
hand+0.002
rolley+0.002
 Wolf+0.002
Mo+0.002
Neg logit contributions
 similarities-0.005
issors-0.005
ocus-0.004
ets-0.004
 ind-0.004
Token had
Token ID550
Feature activation-3.71e-01

Pos logit contributions
 Wolf+0.018
handed+0.018
 cub+0.017
 therm+0.017
 baby+0.017
Neg logit contributions
issors-0.020
ocus-0.020
 similarities-0.020
 seventeen-0.019
ets-0.019
Token passed
Token ID3804
Feature activation+4.20e-01

Pos logit contributions
 similarities+0.016
ocus+0.015
ets+0.014
issors+0.014
 seventeen+0.014
Neg logit contributions
 Wolf-0.010
Mo-0.010
handed-0.009
rolley-0.009
 Wilson-0.009
Token away
Token ID1497
Feature activation+2.03e-01

Pos logit contributions
 Wolf+0.010
handed+0.010
Mo+0.009
 cub+0.009
burn+0.009
Neg logit contributions
issors-0.018
 similarities-0.018
ocus-0.018
ets-0.018
 seventeen-0.017
Token long
Token ID890
Feature activation+1.96e-01

Pos logit contributions
 Wolf+0.005
handed+0.005
Mo+0.005
burn+0.005
rolley+0.004
Neg logit contributions
ets-0.009
ocus-0.009
 similarities-0.009
issors-0.009
 meanings-0.008
Token ago
Token ID2084
Feature activation-3.30e+00

Pos logit contributions
handed+0.005
 Wolf+0.005
 cub+0.005
 baby+0.005
 therm+0.005
Neg logit contributions
issors-0.008
ocus-0.008
 similarities-0.008
 seventeen-0.008
ets-0.008
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
issors+0.168
ocus+0.166
ets+0.164
 similarities+0.164
aces+0.163
Neg logit contributions
 Wolf-0.060
Mo-0.057
handed-0.057
rolley-0.050
 therm-0.049
Token One
Token ID1881
Feature activation+8.31e-02

Pos logit contributions
handed+0.009
burn+0.008
 Wolf+0.008
Mo+0.008
 able+0.008
Neg logit contributions
issors-0.012
 similarities-0.012
ocus-0.011
 seventeen-0.011
ets-0.011
Token day
Token ID1110
Feature activation-2.84e-02

Pos logit contributions
handed+0.002
 Wolf+0.002
Mo+0.002
hand+0.002
 anyway+0.002
Neg logit contributions
ocus-0.003
 similarities-0.003
issors-0.003
ets-0.003
 seventeen-0.003
Token,
Token ID11
Feature activation+3.07e-01

Pos logit contributions
ocus+0.001
 similarities+0.001
issors+0.001
 seventeen+0.001
 ind+0.001
Neg logit contributions
handed-0.001
rolley-0.001
 Wolf-0.001
Mo-0.001
seat-0.001
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
handed+0.007
rolley+0.006
 Wolf+0.006
Mo+0.005
hand+0.005
Neg logit contributions
 similarities-0.014
issors-0.014
ocus-0.014
 seventeen-0.014
 ind-0.014
Token."
Token ID526
Feature activation+5.46e-03

Pos logit contributions
issors+0.011
ocus+0.011
 similarities+0.011
ets+0.011
 seventeen+0.010
Neg logit contributions
 Wolf-0.005
handed-0.005
Mo-0.005
 therm-0.005
 cub-0.005
Token Sue
Token ID26089
Feature activation+4.82e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
burn+0.000
 therm+0.000
Mo+0.000
Neg logit contributions
issors-0.000
ocus-0.000
 similarities-0.000
ets-0.000
 seventeen-0.000
Token agreed
Token ID4987
Feature activation-5.48e-01

Pos logit contributions
 Wolf+0.013
handed+0.013
 cub+0.012
 anyway+0.012
 baby+0.012
Neg logit contributions
issors-0.021
ocus-0.020
 similarities-0.020
ets-0.019
 seventeen-0.019
Token,
Token ID11
Feature activation-7.25e-01

Pos logit contributions
issors+0.021
ets+0.021
 similarities+0.021
ocus+0.021
 seventeen+0.019
Neg logit contributions
 Wolf-0.016
handed-0.016
Mo-0.016
seat-0.015
rolley-0.015
Token "
Token ID366
Feature activation-2.10e-01

Pos logit contributions
issors+0.030
ocus+0.030
 similarities+0.030
ets+0.029
 seventeen+0.028
Neg logit contributions
handed-0.020
 Wolf-0.019
Mo-0.018
 cub-0.018
 therm-0.018
TokenThat
Token ID2504
Feature activation+1.55e+00

Pos logit contributions
ocus+0.008
issors+0.008
 similarities+0.007
ets+0.007
 seventeen+0.007
Neg logit contributions
handed-0.007
 Wolf-0.007
 anyway-0.006
Mo-0.006
hand-0.006
Token's
Token ID338
Feature activation+1.90e-01

Pos logit contributions
handed+0.053
 Wolf+0.049
Mo+0.048
seat+0.048
hand+0.047
Neg logit contributions
 similarities-0.055
ocus-0.054
issors-0.053
ets-0.052
 ind-0.051
Token a
Token ID257
Feature activation+3.74e-01

Pos logit contributions
handed+0.006
 Wolf+0.006
rolley+0.005
seat+0.005
hand+0.005
Neg logit contributions
issors-0.008
 similarities-0.008
ocus-0.007
 seventeen-0.007
 ind-0.007
Token good
Token ID922
Feature activation+1.79e-01

Pos logit contributions
handed+0.012
 Wolf+0.012
hand+0.011
rolley+0.011
seat+0.011
Neg logit contributions
 similarities-0.014
issors-0.014
ocus-0.014
 seventeen-0.013
ets-0.013
Token idea
Token ID2126
Feature activation-1.08e+00

Pos logit contributions
handed+0.006
 Wolf+0.006
 cub+0.006
Mo+0.006
hand+0.006
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
ets-0.006
 seventeen-0.005
Token,
Token ID11
Feature activation-6.40e-01

Pos logit contributions
ocus+0.057
issors+0.056
 similarities+0.056
ets+0.055
 seventeen+0.054
Neg logit contributions
handed-0.018
 Wolf-0.017
Mo-0.016
 cub-0.015
seat-0.015
Token upon
Token ID2402
Feature activation-1.14e+00

Pos logit contributions
ocus+0.042
issors+0.042
 similarities+0.041
ets+0.039
 ind+0.036
Neg logit contributions
handed-0.049
 Wolf-0.048
Mo-0.045
 cub-0.045
burn-0.045
Token a
Token ID257
Feature activation+6.63e-01

Pos logit contributions
ocus+0.047
 similarities+0.047
ets+0.045
issors+0.045
aces+0.044
Neg logit contributions
 Wolf-0.029
handed-0.028
rolley-0.027
burn-0.027
Mo-0.026
Token time
Token ID640
Feature activation-1.11e+00

Pos logit contributions
 Wolf+0.022
handed+0.021
 anyway+0.021
 cub+0.021
 baby+0.020
Neg logit contributions
ocus-0.024
issors-0.024
 similarities-0.024
 seventeen-0.022
ets-0.022
Token,
Token ID11
Feature activation-5.78e-01

Pos logit contributions
issors+0.055
 similarities+0.055
ocus+0.055
ets+0.053
 seventeen+0.052
Neg logit contributions
 Wolf-0.022
handed-0.021
 cub-0.019
 baby-0.019
 anyway-0.019
Token there
Token ID612
Feature activation-2.29e-01

Pos logit contributions
issors+0.028
ocus+0.028
 similarities+0.028
ets+0.027
 seventeen+0.027
Neg logit contributions
 Wolf-0.012
handed-0.011
 cub-0.011
 baby-0.010
Mo-0.010
Token were
Token ID547
Feature activation+1.87e+00

Pos logit contributions
 similarities+0.011
ocus+0.011
issors+0.010
ets+0.010
 seventeen+0.010
Neg logit contributions
handed-0.005
 Wolf-0.005
burn-0.005
rolley-0.004
Mo-0.004
Token two
Token ID734
Feature activation+1.31e+00

Pos logit contributions
 baby+0.020
 Wolf+0.019
handed+0.016
 another+0.016
 one+0.015
Neg logit contributions
issors-0.115
ocus-0.114
ets-0.112
 similarities-0.112
 seventeen-0.107
Token friends
Token ID2460
Feature activation+1.38e-01

Pos logit contributions
 Wolf+0.028
handed+0.027
 cub+0.025
Mo+0.025
 anyway+0.024
Neg logit contributions
issors-0.062
ocus-0.062
 similarities-0.062
ets-0.060
 seventeen-0.059
Token called
Token ID1444
Feature activation-2.26e-01

Pos logit contributions
handed+0.005
rolley+0.005
 therm+0.005
burn+0.005
 Wolf+0.005
Neg logit contributions
issors-0.004
apes-0.004
 similarities-0.004
ocus-0.004
 nations-0.004
Token Tom
Token ID4186
Feature activation+5.02e-01

Pos logit contributions
issors+0.008
ocus+0.008
 similarities+0.008
ets+0.008
 seventeen+0.008
Neg logit contributions
handed-0.007
 Wolf-0.007
 therm-0.007
Mo-0.007
 cub-0.007
Token and
Token ID290
Feature activation+2.19e-01

Pos logit contributions
handed+0.018
 Wolf+0.018
Mo+0.018
 therm+0.017
hand+0.017
Neg logit contributions
ets-0.016
issors-0.016
ocus-0.016
 similarities-0.015
apes-0.015
Token He
Token ID679
Feature activation+3.49e-01

Pos logit contributions
issors+0.006
ocus+0.006
 similarities+0.006
ets+0.005
 seventeen+0.005
Neg logit contributions
handed-0.004
 Wolf-0.004
burn-0.004
Mo-0.004
 therm-0.004
Token was
Token ID373
Feature activation+1.36e-01

Pos logit contributions
handed+0.010
 Wolf+0.009
seat+0.009
burn+0.009
hand+0.008
Neg logit contributions
ocus-0.014
issors-0.014
 similarities-0.014
ets-0.014
 seventeen-0.013
Token taken
Token ID2077
Feature activation-2.66e-01

Pos logit contributions
handed+0.004
rolley+0.004
hand+0.004
Mo+0.004
seat+0.003
Neg logit contributions
ocus-0.005
 seventeen-0.005
issors-0.005
 similarities-0.005
ets-0.005
Token to
Token ID284
Feature activation+1.41e-01

Pos logit contributions
ets+0.012
issors+0.011
 similarities+0.011
ocus+0.011
 seventeen+0.011
Neg logit contributions
handed-0.006
burn-0.006
rolley-0.006
 Wolf-0.006
Mo-0.006
Token the
Token ID262
Feature activation+5.56e-02

Pos logit contributions
burn+0.004
rolley+0.004
Mo+0.004
eled+0.004
m+0.004
Neg logit contributions
 similarities-0.005
issors-0.005
ocus-0.005
 draw-0.005
 does-0.005
Token hospital
Token ID4436
Feature activation+1.45e+00

Pos logit contributions
seat+0.001
handed+0.001
burn+0.001
Mo+0.001
 Wolf+0.001
Neg logit contributions
issors-0.002
 similarities-0.002
ocus-0.002
 seventeen-0.002
 meanings-0.002
Token,
Token ID11
Feature activation+3.05e-02

Pos logit contributions
 Wolf+0.038
handed+0.037
Mo+0.036
rolley+0.035
burn+0.034
Neg logit contributions
ocus-0.061
issors-0.060
ets-0.059
 similarities-0.059
 seventeen-0.056
Token but
Token ID475
Feature activation+1.23e+00

Pos logit contributions
handed+0.001
 Wolf+0.001
Mo+0.001
 cub+0.001
hand+0.001
Neg logit contributions
issors-0.001
ocus-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Token it
Token ID340
Feature activation-1.59e-01

Pos logit contributions
handed+0.022
burn+0.020
 Wolf+0.020
Mo+0.019
rolley+0.019
Neg logit contributions
ocus-0.062
 similarities-0.061
issors-0.061
ets-0.059
 seventeen-0.059
Token was
Token ID373
Feature activation+6.27e-01

Pos logit contributions
ocus+0.007
 similarities+0.007
issors+0.007
ets+0.007
 does+0.006
Neg logit contributions
handed-0.004
seat-0.004
rolley-0.004
 Wolf-0.003
burn-0.003
Token too
Token ID1165
Feature activation-2.31e-01

Pos logit contributions
handed+0.022
rolley+0.020
hand+0.018
seat+0.018
 Wolf+0.017
Neg logit contributions
 seventeen-0.022
issors-0.022
 similarities-0.022
ocus-0.022
 ind-0.022
Token friends
Token ID2460
Feature activation+6.99e-02

Pos logit contributions
handed+0.017
 Wolf+0.016
 therm+0.015
burn+0.015
rolley+0.015
Neg logit contributions
 similarities-0.028
ocus-0.027
issors-0.027
ets-0.026
 seventeen-0.025
Token!
Token ID0
Feature activation-2.17e-01

Pos logit contributions
handed+0.002
 therm+0.001
rolley+0.001
burn+0.001
Mo+0.001
Neg logit contributions
ets-0.003
 similarities-0.003
ocus-0.003
aces-0.003
 ind-0.003
Token<|endoftext|>
Token ID50256
Feature activation+3.20e-01

Pos logit contributions
issors+0.008
 similarities+0.008
ocus+0.008
ets+0.008
ols+0.007
Neg logit contributions
handed-0.007
 therm-0.006
ge-0.006
 able-0.006
burn-0.006
TokenOnce
Token ID7454
Feature activation-1.30e+00

Pos logit contributions
handed+0.009
 able+0.009
burn+0.009
 therm+0.009
rolley+0.008
Neg logit contributions
ocus-0.012
ets-0.011
 does-0.011
 similarities-0.011
aces-0.011
Token there
Token ID612
Feature activation-3.40e-02

Pos logit contributions
ocus+0.040
issors+0.039
 similarities+0.039
ets+0.037
 ind+0.034
Neg logit contributions
handed-0.051
 Wolf-0.049
hand-0.047
Mo-0.047
 therm-0.047
Token were
Token ID547
Feature activation+1.82e+00

Pos logit contributions
 similarities+0.001
ocus+0.001
 does+0.001
 ind+0.001
 seventeen+0.001
Neg logit contributions
handed-0.001
burn-0.001
rolley-0.001
 Wolf-0.001
 therm-0.001
Token two
Token ID734
Feature activation+1.16e+00

Pos logit contributions
 Wolf+0.039
 baby+0.036
handed+0.036
 cub+0.034
 anyway+0.034
Neg logit contributions
issors-0.092
ocus-0.090
 similarities-0.089
ets-0.086
 seventeen-0.086
Token little
Token ID1310
Feature activation+3.10e-01

Pos logit contributions
handed+0.026
 Wolf+0.026
Mo+0.023
hand+0.023
 cub+0.023
Neg logit contributions
issors-0.053
ocus-0.053
 similarities-0.053
ets-0.052
 seventeen-0.051
Token girls
Token ID4813
Feature activation+7.25e-01

Pos logit contributions
handed+0.008
 Wolf+0.007
Mo+0.007
hand+0.006
 anyway+0.006
Neg logit contributions
ocus-0.014
issors-0.014
 similarities-0.014
ets-0.013
 seventeen-0.013
Token who
Token ID508
Feature activation+3.10e-01

Pos logit contributions
handed+0.021
 Wolf+0.019
rolley+0.019
Mo+0.018
burn+0.018
Neg logit contributions
ocus-0.029
issors-0.029
 similarities-0.029
ets-0.028
 ind-0.027
Token loved
Token ID6151
Feature activation+6.10e-01

Pos logit contributions
 Wolf+0.011
handed+0.011
 therm+0.011
Mo+0.011
rolley+0.010
Neg logit contributions
 similarities-0.010
ocus-0.010
issors-0.010
ets-0.010
 seventeen-0.009
Token to
Token ID284
Feature activation+2.81e-01

Pos logit contributions
 Wolf+0.020
handed+0.019
 cub+0.017
Mo+0.017
 therm+0.017
Neg logit contributions
issors-0.047
ocus-0.047
 similarities-0.046
ets-0.045
 seventeen-0.044
Token the
Token ID262
Feature activation+3.68e-01

Pos logit contributions
burn+0.007
Mo+0.007
 Wolf+0.006
rolley+0.006
 therm+0.006
Neg logit contributions
 similarities-0.012
issors-0.012
ocus-0.012
ets-0.012
 nations-0.011
Token toy
Token ID13373
Feature activation+1.21e+00

Pos logit contributions
 Wolf+0.011
handed+0.010
Mo+0.010
 cub+0.010
seat+0.010
Neg logit contributions
issors-0.015
 similarities-0.014
ocus-0.014
 seventeen-0.014
ets-0.014
Token shop
Token ID6128
Feature activation+4.18e-01

Pos logit contributions
Mo+0.029
 Wolf+0.029
burn+0.028
handed+0.026
 therm+0.026
Neg logit contributions
issors-0.053
ocus-0.052
ets-0.050
 similarities-0.050
 nations-0.047
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
 Wolf+0.011
Mo+0.011
burn+0.010
handed+0.010
 therm+0.010
Neg logit contributions
issors-0.017
ocus-0.017
 similarities-0.016
ets-0.016
 seventeen-0.016
Token But
Token ID887
Feature activation+1.81e+00

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.005
 anyway+0.005
 baby+0.005
Neg logit contributions
ocus-0.009
 similarities-0.009
issors-0.009
ets-0.009
 seventeen-0.009
Token when
Token ID618
Feature activation-1.84e-01

Pos logit contributions
 Wolf+0.027
handed+0.025
 anyway+0.023
 cub+0.023
 baby+0.023
Neg logit contributions
issors-0.099
ocus-0.099
 similarities-0.098
ets-0.096
 seventeen-0.095
Token he
Token ID339
Feature activation+3.19e-01

Pos logit contributions
ocus+0.010
 similarities+0.010
issors+0.010
ets+0.009
 seventeen+0.009
Neg logit contributions
handed-0.003
 Wolf-0.003
rolley-0.003
Mo-0.002
 cub-0.002
Token saw
Token ID2497
Feature activation-5.25e-01

Pos logit contributions
 Wolf+0.008
handed+0.008
Mo+0.007
burn+0.007
 cub+0.007
Neg logit contributions
ocus-0.014
issors-0.014
 similarities-0.014
ets-0.013
 seventeen-0.013
Token the
Token ID262
Feature activation-2.74e-02

Pos logit contributions
issors+0.023
ocus+0.023
 similarities+0.023
ets+0.023
 seventeen+0.022
Neg logit contributions
 Wolf-0.012
Mo-0.012
handed-0.012
burn-0.012
seat-0.012
Token prices
Token ID4536
Feature activation+5.72e-01

Pos logit contributions
issors+0.001
ocus+0.001
 similarities+0.001
ets+0.001
 seventeen+0.001
Neg logit contributions
 Wolf-0.001
handed-0.001
Mo-0.001
 cub-0.001
 anyway-0.001
Token.
Token ID13
Feature activation+1.72e-02

Pos logit contributions
issors+0.044
ocus+0.043
 similarities+0.042
ets+0.042
 seventeen+0.040
Neg logit contributions
 Wolf-0.022
handed-0.022
Mo-0.020
hand-0.020
rolley-0.020
Token He
Token ID679
Feature activation+1.37e-01

Pos logit contributions
 Wolf+0.000
handed+0.000
 cub+0.000
 anyway+0.000
seat+0.000
Neg logit contributions
ocus-0.001
issors-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Token never
Token ID1239
Feature activation-5.43e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
 cub+0.004
 anyway+0.004
Mo+0.004
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Token wanted
Token ID2227
Feature activation+1.99e-01

Pos logit contributions
ocus+0.021
 similarities+0.021
issors+0.021
ets+0.020
 seventeen+0.019
Neg logit contributions
 Wolf-0.016
handed-0.016
Mo-0.015
 cub-0.015
hand-0.015
Token to
Token ID284
Feature activation+4.76e-01

Pos logit contributions
 Wolf+0.005
handed+0.005
 cub+0.005
 baby+0.005
 anyway+0.005
Neg logit contributions
issors-0.009
ocus-0.009
 similarities-0.009
 seventeen-0.008
ets-0.008
Token do
Token ID466
Feature activation+5.71e-01

Pos logit contributions
 Wolf+0.017
handed+0.017
rolley+0.017
Mo+0.016
seat+0.016
Neg logit contributions
 similarities-0.015
ocus-0.015
issors-0.015
ets-0.014
 seventeen-0.013
Token any
Token ID597
Feature activation+9.27e-01

Pos logit contributions
handed+0.015
 Wolf+0.015
rolley+0.015
Mo+0.014
seat+0.014
Neg logit contributions
ocus-0.024
 similarities-0.024
ets-0.023
issors-0.023
 meanings-0.022
Token work
Token ID670
Feature activation-2.03e-01

Pos logit contributions
handed+0.028
 Wolf+0.028
Mo+0.027
hand+0.026
rolley+0.026
Neg logit contributions
 similarities-0.035
ocus-0.035
issors-0.035
ets-0.035
 seventeen-0.032
Token.
Token ID13
Feature activation+1.64e-01

Pos logit contributions
ocus+0.009
issors+0.009
 similarities+0.009
ets+0.009
 seventeen+0.009
Neg logit contributions
 Wolf-0.005
handed-0.004
Mo-0.004
 cub-0.004
 therm-0.004
Token
Token ID198
Feature activation+4.49e-01

Pos logit contributions
 Wolf+0.002
handed+0.002
 cub+0.002
 anyway+0.002
Mo+0.002
Neg logit contributions
ocus-0.009
issors-0.009
 similarities-0.009
ets-0.009
 seventeen-0.009
Token
Token ID198
Feature activation+7.56e-01

Pos logit contributions
handed+0.009
 Wolf+0.009
burn+0.008
 therm+0.008
 cub+0.008
Neg logit contributions
issors-0.021
 similarities-0.021
ocus-0.021
ets-0.020
 seventeen-0.019
Token important
Token ID1593
Feature activation-9.63e-04

Pos logit contributions
ocus+0.007
issors+0.007
 similarities+0.007
 seventeen+0.006
ets+0.006
Neg logit contributions
 Wolf-0.005
handed-0.005
 anyway-0.004
 cub-0.004
 baby-0.004
Token to
Token ID284
Feature activation-3.58e-01

Pos logit contributions
ocus+0.000
issors+0.000
 seventeen+0.000
 similarities+0.000
 ind+0.000
Neg logit contributions
 Wolf-0.000
 anyway-0.000
handed-0.000
 baby-0.000
 anyways-0.000
Token forgive
Token ID20927
Feature activation-6.18e-01

Pos logit contributions
ocus+0.016
 seventeen+0.015
issors+0.015
ets+0.014
 similarities+0.014
Neg logit contributions
 Wolf-0.010
 anyway-0.009
 baby-0.009
 one-0.009
handed-0.009
Token and
Token ID290
Feature activation+6.97e-01

Pos logit contributions
ocus+0.028
issors+0.027
 similarities+0.027
 seventeen+0.027
ets+0.026
Neg logit contributions
 Wolf-0.015
handed-0.014
 anyway-0.014
 cub-0.014
 baby-0.014
Token work
Token ID670
Feature activation+7.40e-01

Pos logit contributions
 soon+0.017
 anyway+0.017
 baby+0.017
 another+0.017
 Wolf+0.017
Neg logit contributions
ocus-0.032
issors-0.031
 seventeen-0.030
ets-0.030
aces-0.029
Token together
Token ID1978
Feature activation+6.29e-01

Pos logit contributions
 Wolf+0.017
handed+0.017
 cub+0.015
Mo+0.015
 therm+0.015
Neg logit contributions
issors-0.034
ocus-0.034
 similarities-0.034
ets-0.033
 seventeen-0.032
Token to
Token ID284
Feature activation+1.94e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.005
 anyway+0.004
Mo+0.004
Neg logit contributions
issors-0.037
ocus-0.037
 similarities-0.037
ets-0.036
 seventeen-0.036
Token make
Token ID787
Feature activation+8.17e-02

Pos logit contributions
handed+0.006
 Wolf+0.006
 anyway+0.005
 another+0.005
.+0.005
Neg logit contributions
ocus-0.008
issors-0.008
 seventeen-0.007
ets-0.007
 similarities-0.007
Token things
Token ID1243
Feature activation+8.34e-01

Pos logit contributions
 Wolf+0.002
handed+0.002
Mo+0.002
 cub+0.002
seat+0.002
Neg logit contributions
issors-0.003
 similarities-0.003
ocus-0.003
ets-0.003
 seventeen-0.003
Token better
Token ID1365
Feature activation-1.17e-01

Pos logit contributions
handed+0.012
 Wolf+0.011
 anyway+0.011
 baby+0.010
 therm+0.010
Neg logit contributions
issors-0.046
ocus-0.045
 similarities-0.045
 seventeen-0.044
ets-0.043
Token.
Token ID13
Feature activation-5.81e-01

Pos logit contributions
issors+0.007
 similarities+0.007
ocus+0.007
ets+0.007
 seventeen+0.007
Neg logit contributions
 Wolf-0.001
handed-0.001
Mo-0.001
 cub-0.001
 therm-0.001
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
 cub+0.003
Mo+0.003
 therm+0.003
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
ets-0.006
 seventeen-0.006
Token
Token ID198
Feature activation+4.75e-01

Pos logit contributions
 Wolf+0.008
handed+0.008
 cub+0.008
burn+0.008
 therm+0.007
Neg logit contributions
issors-0.015
 similarities-0.015
ocus-0.015
ets-0.014
apes-0.014
TokenSo
Token ID2396
Feature activation+8.94e-01

Pos logit contributions
 Wolf+0.012
handed+0.012
 cub+0.011
Mo+0.011
 anyway+0.011
Neg logit contributions
issors-0.020
ocus-0.020
 similarities-0.020
ets-0.020
 seventeen-0.019
Token,
Token ID11
Feature activation-1.13e-01

Pos logit contributions
 Wolf+0.020
handed+0.020
 baby+0.019
 anyway+0.019
 cub+0.018
Neg logit contributions
ocus-0.041
issors-0.041
 similarities-0.041
 seventeen-0.039
ets-0.039
Token Lily
Token ID20037
Feature activation+1.01e-01

Pos logit contributions
issors+0.005
ocus+0.005
 similarities+0.005
ets+0.004
 seventeen+0.004
Neg logit contributions
 Wolf-0.003
handed-0.003
 cub-0.003
Mo-0.003
 therm-0.003
Token and
Token ID290
Feature activation+6.62e-02

Pos logit contributions
 Wolf+0.002
handed+0.002
 anyway+0.002
 cub+0.002
 baby+0.002
Neg logit contributions
issors-0.005
 similarities-0.005
ocus-0.005
 seventeen-0.004
ets-0.004
Token her
Token ID607
Feature activation+3.15e-01

Pos logit contributions
handed+0.001
 Wolf+0.001
rolley+0.001
Mo+0.001
seat+0.001
Neg logit contributions
issors-0.003
 similarities-0.003
ocus-0.003
ets-0.003
 meanings-0.003
Token mom
Token ID1995
Feature activation-2.84e-02

Pos logit contributions
handed+0.007
 Wolf+0.007
Mo+0.006
 cub+0.006
hand+0.006
Neg logit contributions
issors-0.015
 similarities-0.015
ocus-0.015
ets-0.014
 seventeen-0.014
Token had
Token ID550
Feature activation-2.23e-01

Pos logit contributions
issors+0.001
ocus+0.001
 similarities+0.001
ets+0.001
 seventeen+0.001
Neg logit contributions
 Wolf-0.001
handed-0.001
 cub-0.001
Mo-0.001
 anyway-0.001
Token a
Token ID257
Feature activation-4.93e-01

Pos logit contributions
issors+0.012
ocus+0.012
 similarities+0.012
ets+0.012
 seventeen+0.011
Neg logit contributions
 anyway-0.003
 another-0.003
handed-0.003
 Wolf-0.003
 one-0.003
Token bath
Token ID7837
Feature activation+8.44e-01

Pos logit contributions
ocus+0.018
issors+0.018
 similarities+0.018
ets+0.017
 seventeen+0.017
Neg logit contributions
 Wolf-0.016
handed-0.016
 cub-0.015
 baby-0.015
Mo-0.015
Token're
Token ID821
Feature activation+1.11e-01

Pos logit contributions
 Wolf+0.028
handed+0.027
 cub+0.026
Mo+0.026
 baby+0.026
Neg logit contributions
issors-0.025
ocus-0.025
 similarities-0.025
ets-0.023
 seventeen-0.023
Token going
Token ID1016
Feature activation+2.32e-02

Pos logit contributions
handed+0.003
 Wolf+0.003
hand+0.003
rolley+0.003
Mo+0.002
Neg logit contributions
ocus-0.005
 similarities-0.005
issors-0.005
ets-0.005
 ind-0.005
Token to
Token ID284
Feature activation+7.64e-02

Pos logit contributions
handed+0.001
 Wolf+0.001
Mo+0.001
 cub+0.001
 therm+0.001
Neg logit contributions
ocus-0.001
issors-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Token stay
Token ID2652
Feature activation+2.71e-01

Pos logit contributions
handed+0.003
rolley+0.002
 Wolf+0.002
hand+0.002
 therm+0.002
Neg logit contributions
 similarities-0.003
ocus-0.003
 ind-0.002
issors-0.002
 seventeen-0.002
Token in
Token ID287
Feature activation-3.51e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.006
Mo+0.006
 therm+0.006
Neg logit contributions
issors-0.012
ocus-0.012
 similarities-0.012
ets-0.011
 seventeen-0.011
Token a
Token ID257
Feature activation+9.20e-01

Pos logit contributions
ocus+0.015
 similarities+0.015
ets+0.014
issors+0.014
 ind+0.014
Neg logit contributions
handed-0.009
 Wolf-0.009
Mo-0.008
burn-0.008
rolley-0.008
Token hotel
Token ID7541
Feature activation+1.01e+00

Pos logit contributions
 Wolf+0.030
handed+0.029
Mo+0.029
burn+0.029
 Wilson+0.028
Neg logit contributions
ocus-0.032
 similarities-0.031
ets-0.031
 seventeen-0.029
issors-0.029
Token!"
Token ID2474
Feature activation-5.93e-02

Pos logit contributions
 Wolf+0.024
handed+0.023
Mo+0.023
 therm+0.021
 cub+0.021
Neg logit contributions
ocus-0.046
ets-0.046
issors-0.045
 similarities-0.044
 seventeen-0.043
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
issors+0.002
ets+0.002
ocus+0.002
 similarities+0.002
 Salad+0.002
Neg logit contributions
handed-0.002
 Wolf-0.002
burn-0.001
Mo-0.001
 therm-0.001
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
burn+0.003
 therm+0.002
ting+0.002
Neg logit contributions
issors-0.004
 similarities-0.004
ocus-0.004
apes-0.004
 seventeen-0.004
TokenOnce
Token ID7454
Feature activation-1.03e+00

Pos logit contributions
 Wolf+0.007
handed+0.006
 cub+0.006
 therm+0.006
 baby+0.006
Neg logit contributions
issors-0.014
 similarities-0.014
ocus-0.014
 seventeen-0.013
ets-0.013
Token It
Token ID632
Feature activation+1.79e-01

Pos logit contributions
ocus+0.012
issors+0.012
 similarities+0.012
ets+0.012
 seventeen+0.011
Neg logit contributions
 Wolf-0.018
handed-0.017
 cub-0.017
Mo-0.017
 therm-0.016
Token has
Token ID468
Feature activation-3.72e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.005
 therm+0.005
 baby+0.005
Neg logit contributions
issors-0.007
ocus-0.007
 similarities-0.006
ets-0.006
 seventeen-0.006
Token a
Token ID257
Feature activation-3.98e-01

Pos logit contributions
issors+0.020
ocus+0.019
 similarities+0.019
ets+0.018
 seventeen+0.018
Neg logit contributions
 Wolf-0.006
handed-0.006
 baby-0.006
 cub-0.006
 therm-0.005
Token lot
Token ID1256
Feature activation+1.57e-01

Pos logit contributions
issors+0.016
ocus+0.016
 similarities+0.016
ets+0.015
apes+0.015
Neg logit contributions
 Wolf-0.012
 therm-0.012
 baby-0.012
 cub-0.011
 anyway-0.011
Token of
Token ID286
Feature activation+1.43e+00

Pos logit contributions
handed+0.004
 Wolf+0.004
 cub+0.003
 anyway+0.003
 therm+0.003
Neg logit contributions
issors-0.007
 similarities-0.007
ocus-0.007
ets-0.007
 seventeen-0.007
Token memories
Token ID9846
Feature activation+8.49e-01

Pos logit contributions
 Wolf+0.044
 therm+0.044
handed+0.043
 baby+0.043
 cub+0.043
Neg logit contributions
issors-0.054
ocus-0.054
 similarities-0.052
 seventeen-0.051
ets-0.049
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
 Wolf+0.017
handed+0.017
 cub+0.015
 anyway+0.015
 baby+0.015
Neg logit contributions
issors-0.041
 similarities-0.041
ocus-0.041
 seventeen-0.039
ets-0.039
Token But
Token ID887
Feature activation+1.72e+00

Pos logit contributions
issors+0.015
ocus+0.015
 similarities+0.015
ets+0.014
 seventeen+0.014
Neg logit contributions
 Wolf-0.021
handed-0.021
 cub-0.020
Mo-0.020
 anyway-0.019
Token it
Token ID340
Feature activation-3.92e-01

Pos logit contributions
 Wolf+0.037
 baby+0.035
 cub+0.034
 anyway+0.034
 one+0.034
Neg logit contributions
issors-0.083
ocus-0.082
ets-0.081
 similarities-0.081
 seventeen-0.078
Token is
Token ID318
Feature activation+3.33e-02

Pos logit contributions
issors+0.016
 similarities+0.015
ocus+0.015
 seventeen+0.015
ige+0.014
Neg logit contributions
 cub-0.012
 Wolf-0.012
 Bear-0.012
 therm-0.011
 baby-0.011
Token not
Token ID407
Feature activation+6.32e-01

Pos logit contributions
 Wolf+0.001
handed+0.001
 cub+0.001
Mo+0.001
 anyway+0.001
Neg logit contributions
issors-0.001
ocus-0.001
 similarities-0.001
ets-0.001
 seventeen-0.001
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 Wolf+0.014
Mo+0.013
rolley+0.012
handed+0.012
hand+0.012
Neg logit contributions
issors-0.026
ocus-0.025
 draw-0.025
ets-0.024
apes-0.024
Token
Token ID198
Feature activation-3.28e-01

Pos logit contributions
ocus+0.010
issors+0.010
 similarities+0.009
 seventeen+0.009
 ey+0.009
Neg logit contributions
handed-0.010
burn-0.010
 Wolf-0.009
 able-0.009
hand-0.009
Token
Token ID198
Feature activation-1.22e-01

Pos logit contributions
ocus+0.013
issors+0.013
 similarities+0.013
 seventeen+0.011
apes+0.011
Neg logit contributions
burn-0.010
handed-0.009
 able-0.009
ting-0.009
 cub-0.009
TokenHe
Token ID1544
Feature activation-1.78e-01

Pos logit contributions
ocus+0.005
issors+0.005
 similarities+0.005
 seventeen+0.005
ets+0.005
Neg logit contributions
 Wolf-0.003
 cub-0.003
handed-0.003
burn-0.003
 baby-0.003
Token said
Token ID531
Feature activation-2.72e-01

Pos logit contributions
issors+0.009
 similarities+0.008
ocus+0.008
ets+0.008
 seventeen+0.008
Neg logit contributions
 Wolf-0.004
 cub-0.004
handed-0.004
 baby-0.004
 therm-0.004
Token,
Token ID11
Feature activation-4.73e-01

Pos logit contributions
issors+0.015
ets+0.015
 similarities+0.015
ocus+0.015
apes+0.014
Neg logit contributions
 Wolf-0.004
 baby-0.004
 his-0.004
 another-0.004
 anyway-0.004
Token "
Token ID366
Feature activation-7.79e-02

Pos logit contributions
ocus+0.021
issors+0.021
 similarities+0.020
ets+0.019
 seventeen+0.019
Neg logit contributions
handed-0.012
 Wolf-0.012
Mo-0.011
 cub-0.011
rolley-0.011
TokenDon
Token ID3987
Feature activation-2.54e-01

Pos logit contributions
 similarities+0.003
issors+0.003
ocus+0.003
 seventeen+0.003
ets+0.003
Neg logit contributions
 Wolf-0.002
handed-0.002
 cub-0.002
 anyway-0.002
 able-0.002
Token't
Token ID470
Feature activation+1.15e-01

Pos logit contributions
issors+0.009
ocus+0.009
 similarities+0.009
ets+0.009
 seventeen+0.009
Neg logit contributions
handed-0.008
 Wolf-0.008
 cub-0.008
seat-0.008
rolley-0.008
Token worry
Token ID5490
Feature activation+3.54e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
 cub+0.003
Mo+0.003
 anyway+0.003
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Token,
Token ID11
Feature activation-4.30e-01

Pos logit contributions
handed+0.012
rolley+0.011
seat+0.010
eled+0.010
Mo+0.010
Neg logit contributions
ocus-0.014
issors-0.013
 similarities-0.013
ets-0.013
 seventeen-0.012
Token shield
Token ID7614
Feature activation+1.10e-01

Pos logit contributions
ocus+0.005
issors+0.005
 similarities+0.005
ets+0.005
apes+0.005
Neg logit contributions
 baby-0.003
 Wolf-0.003
 cub-0.003
 therm-0.003
 front-0.003
Token and
Token ID290
Feature activation-5.69e-01

Pos logit contributions
 Wolf+0.003
handed+0.003
 cub+0.003
Mo+0.003
 therm+0.002
Neg logit contributions
issors-0.005
ocus-0.005
 similarities-0.005
ets-0.005
 seventeen-0.004
Token the
Token ID262
Feature activation-3.30e-01

Pos logit contributions
ocus+0.023
 similarities+0.022
issors+0.022
ets+0.022
 seventeen+0.021
Neg logit contributions
handed-0.017
 Wolf-0.016
rolley-0.015
hand-0.015
Mo-0.015
Token scarf
Token ID36953
Feature activation+1.06e+00

Pos logit contributions
ocus+0.015
issors+0.014
 similarities+0.014
ets+0.014
 seventeen+0.013
Neg logit contributions
 Wolf-0.009
 baby-0.009
 cub-0.009
 therm-0.008
handed-0.008
Token,
Token ID11
Feature activation-5.54e-01

Pos logit contributions
handed+0.022
 Wolf+0.022
rolley+0.020
Mo+0.020
seat+0.019
Neg logit contributions
ocus-0.052
ets-0.051
issors-0.050
 similarities-0.050
 seventeen-0.049
Token making
Token ID1642
Feature activation-1.11e+00

Pos logit contributions
ocus+0.024
issors+0.024
 similarities+0.024
ets+0.023
 seventeen+0.023
Neg logit contributions
handed-0.014
 Wolf-0.014
Mo-0.012
 cub-0.012
rolley-0.012
Token holes
Token ID10421
Feature activation+3.42e-01

Pos logit contributions
ocus+0.052
 similarities+0.051
issors+0.051
ets+0.050
 seventeen+0.049
Neg logit contributions
handed-0.025
 Wolf-0.025
Mo-0.022
 cub-0.022
 therm-0.022
Token and
Token ID290
Feature activation-2.68e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.006
Mo+0.006
 therm+0.006
Neg logit contributions
ocus-0.017
issors-0.017
 similarities-0.017
ets-0.016
 seventeen-0.016
Token r
Token ID374
Feature activation+1.64e-01

Pos logit contributions
issors+0.010
ocus+0.010
 similarities+0.010
ets+0.010
 seventeen+0.009
Neg logit contributions
 Wolf-0.008
handed-0.008
 cub-0.008
 baby-0.008
 therm-0.008
Tokenips
Token ID2419
Feature activation+2.69e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.006
 baby+0.006
 therm+0.006
Neg logit contributions
ocus-0.005
issors-0.005
 similarities-0.005
ets-0.005
 seventeen-0.005
Token.
Token ID13
Feature activation-5.35e-01

Pos logit contributions
handed+0.005
 Wolf+0.005
Mo+0.004
rolley+0.004
 cub+0.004
Neg logit contributions
ocus-0.014
issors-0.014
 similarities-0.013
ets-0.013
 seventeen-0.013
Token on
Token ID319
Feature activation+9.07e-02

Pos logit contributions
 Wolf+0.006
handed+0.006
Mo+0.005
 cub+0.005
rolley+0.005
Neg logit contributions
ocus-0.009
issors-0.009
 similarities-0.008
ets-0.008
 seventeen-0.008
Token his
Token ID465
Feature activation+2.90e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
burn+0.002
rolley+0.002
Mo+0.001
Neg logit contributions
 similarities-0.004
ocus-0.004
issors-0.004
 seventeen-0.004
ets-0.004
Token journey
Token ID7002
Feature activation-6.97e-01

Pos logit contributions
 Wolf+0.009
handed+0.009
Mo+0.008
seat+0.008
rolley+0.008
Neg logit contributions
issors-0.011
 similarities-0.011
ocus-0.011
ets-0.010
 seventeen-0.010
Token home
Token ID1363
Feature activation-7.68e-01

Pos logit contributions
issors+0.030
ets+0.030
ocus+0.030
 similarities+0.029
 seventeen+0.028
Neg logit contributions
 Wolf-0.018
handed-0.017
Mo-0.016
 therm-0.016
burn-0.016
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
ocus+0.031
ets+0.030
issors+0.030
 similarities+0.029
aces+0.029
Neg logit contributions
 Wolf-0.022
Mo-0.021
burn-0.020
handed-0.020
 therm-0.019
Token Jack
Token ID3619
Feature activation-9.15e-01

Pos logit contributions
issors+0.014
ocus+0.013
 similarities+0.013
ets+0.013
 seventeen+0.012
Neg logit contributions
burn-0.009
 Wolf-0.009
handed-0.009
 therm-0.009
Mo-0.009
Token was
Token ID373
Feature activation+6.78e-03

Pos logit contributions
ocus+0.040
ets+0.039
 similarities+0.038
issors+0.038
 ind+0.037
Neg logit contributions
handed-0.023
 Wolf-0.023
 therm-0.021
burn-0.021
Mo-0.020
Token so
Token ID523
Feature activation-6.20e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
rolley+0.000
Mo+0.000
hand+0.000
Neg logit contributions
ocus-0.000
 ind-0.000
 seventeen-0.000
 similarities-0.000
ets-0.000
Token excited
Token ID6568
Feature activation-3.88e-01

Pos logit contributions
ocus+0.023
 similarities+0.022
 seventeen+0.021
issors+0.021
 ind+0.021
Neg logit contributions
 Wolf-0.021
handed-0.019
burn-0.019
Mo-0.019
 therm-0.019
Token to
Token ID284
Feature activation+1.88e-01

Pos logit contributions
ocus+0.018
issors+0.018
ets+0.018
 similarities+0.018
 seventeen+0.017
Neg logit contributions
 Wolf-0.009
handed-0.009
Mo-0.008
 cub-0.008
 therm-0.008
Token show
Token ID905
Feature activation-1.22e+00

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.006
Mo+0.006
 therm+0.006
Neg logit contributions
issors-0.006
ocus-0.006
 similarities-0.006
ets-0.006
 seventeen-0.006
Token flew
Token ID13112
Feature activation+1.01e+00

Pos logit contributions
 Wolf+0.001
handed+0.001
 cub+0.001
 baby+0.001
 anyway+0.001
Neg logit contributions
issors-0.003
ocus-0.003
 similarities-0.002
ets-0.002
 seventeen-0.002
Token to
Token ID284
Feature activation+2.33e-01

Pos logit contributions
handed+0.022
 Wolf+0.022
 cub+0.020
 therm+0.019
Mo+0.019
Neg logit contributions
ocus-0.048
issors-0.048
 similarities-0.047
ets-0.046
 seventeen-0.045
Token a
Token ID257
Feature activation+5.72e-01

Pos logit contributions
 Wolf+0.006
handed+0.005
 therm+0.005
Mo+0.005
rolley+0.005
Neg logit contributions
 similarities-0.010
ocus-0.010
issors-0.010
ets-0.009
 seventeen-0.009
Token beautiful
Token ID4950
Feature activation+3.13e-01

Pos logit contributions
 Wolf+0.018
handed+0.017
Mo+0.017
burn+0.016
hand+0.016
Neg logit contributions
ocus-0.021
 similarities-0.021
issors-0.020
ets-0.020
 seventeen-0.020
Token place
Token ID1295
Feature activation+5.75e-01

Pos logit contributions
 Wolf+0.009
handed+0.009
 cub+0.009
Mo+0.008
 anyway+0.008
Neg logit contributions
issors-0.012
ocus-0.012
 similarities-0.012
ets-0.012
 seventeen-0.012
Token far
Token ID1290
Feature activation-6.17e-01

Pos logit contributions
 Wolf+0.011
handed+0.010
Mo+0.009
 cub+0.009
 therm+0.009
Neg logit contributions
ocus-0.030
 similarities-0.029
issors-0.029
ets-0.029
 ind-0.028
Token away
Token ID1497
Feature activation+7.30e-01

Pos logit contributions
ets+0.027
issors+0.026
ocus+0.026
 similarities+0.025
ols+0.024
Neg logit contributions
 Wolf-0.016
handed-0.015
Mo-0.015
 cub-0.014
burn-0.014
Token.
Token ID13
Feature activation-1.58e-01

Pos logit contributions
 Wolf+0.015
burn+0.014
Mo+0.014
 therm+0.014
eled+0.013
Neg logit contributions
ets-0.035
ocus-0.034
 similarities-0.034
 nations-0.033
 ind-0.031
Token Jane
Token ID12091
Feature activation+4.33e-02

Pos logit contributions
ocus+0.006
issors+0.006
 similarities+0.006
 seventeen+0.006
ets+0.005
Neg logit contributions
 Wolf-0.005
handed-0.005
 baby-0.005
 anyway-0.005
 cub-0.005
Token and
Token ID290
Feature activation+3.35e-01

Pos logit contributions
handed+0.001
 Wolf+0.001
Mo+0.001
 therm+0.001
 cub+0.001
Neg logit contributions
ocus-0.002
issors-0.002
 similarities-0.002
ets-0.002
 seventeen-0.002
Token Pete
Token ID17542
Feature activation-1.52e-01

Pos logit contributions
 Wolf+0.008
handed+0.008
 baby+0.008
 cub+0.008
Mo+0.008
Neg logit contributions
ocus-0.015
issors-0.015
 similarities-0.015
 seventeen-0.015
ets-0.015
Token a
Token ID257
Feature activation+8.29e-01

Pos logit contributions
 similarities+0.045
ocus+0.044
issors+0.043
ets+0.043
aces+0.042
Neg logit contributions
 Wolf-0.022
handed-0.021
rolley-0.020
hand-0.020
Mo-0.020
Token time
Token ID640
Feature activation-1.19e+00

Pos logit contributions
 Wolf+0.025
 anyway+0.024
 cub+0.024
handed+0.024
 baby+0.024
Neg logit contributions
ocus-0.032
issors-0.032
 similarities-0.031
 seventeen-0.029
 meanings-0.029
Token there
Token ID612
Feature activation-2.79e-01

Pos logit contributions
issors+0.060
 similarities+0.059
ocus+0.059
ets+0.058
 seventeen+0.056
Neg logit contributions
 Wolf-0.023
handed-0.022
 cub-0.020
 baby-0.020
 anyway-0.020
Token was
Token ID373
Feature activation+1.01e+00

Pos logit contributions
ocus+0.010
 similarities+0.010
 does+0.010
 ind+0.009
issors+0.009
Neg logit contributions
handed-0.008
rolley-0.008
burn-0.008
 Wolf-0.007
 able-0.007
Token a
Token ID257
Feature activation+3.64e-01

Pos logit contributions
 Wolf+0.010
handed+0.009
 baby+0.009
 another+0.008
 anyway+0.008
Neg logit contributions
 similarities-0.060
issors-0.060
ocus-0.060
ets-0.058
 seventeen-0.057
Token mouse
Token ID10211
Feature activation-9.05e-01

Pos logit contributions
 Wolf+0.007
handed+0.007
 cub+0.007
 baby+0.007
Mo+0.006
Neg logit contributions
issors-0.018
ocus-0.018
 similarities-0.018
ets-0.017
 seventeen-0.017
Token who
Token ID508
Feature activation+3.12e-01

Pos logit contributions
ocus+0.035
issors+0.033
 similarities+0.033
ets+0.033
 ind+0.032
Neg logit contributions
handed-0.027
hand-0.026
 Wolf-0.025
rolley-0.025
seat-0.025
Token was
Token ID373
Feature activation+2.25e-01

Pos logit contributions
handed+0.012
 Wolf+0.012
hand+0.011
seat+0.011
rolley+0.011
Neg logit contributions
 similarities-0.009
ocus-0.009
issors-0.009
ets-0.009
 ind-0.008
Token very
Token ID845
Feature activation-6.70e-01

Pos logit contributions
handed+0.005
hand+0.004
 Wolf+0.004
rolley+0.004
seat+0.004
Neg logit contributions
ocus-0.011
issors-0.011
 similarities-0.011
ets-0.010
 ind-0.010
Token troubled
Token ID17840
Feature activation+1.13e-01

Pos logit contributions
issors+0.032
ocus+0.031
 similarities+0.031
ets+0.030
 seventeen+0.030
Neg logit contributions
 Wolf-0.015
 baby-0.015
handed-0.015
 cub-0.014
 therm-0.014
Token.
Token ID13
Feature activation+4.72e-01

Pos logit contributions
handed+0.003
Mo+0.003
rolley+0.003
hand+0.003
eled+0.003
Neg logit contributions
ets-0.005
aces-0.004
ocus-0.004
issors-0.004
 meanings-0.004
Token shared
Token ID4888
Feature activation-8.55e-01

Pos logit contributions
 Wolf+0.003
 soon+0.003
 cub+0.003
 baby+0.003
Mo+0.003
Neg logit contributions
ocus-0.006
issors-0.006
 seventeen-0.005
 similarities-0.005
ets-0.005
Token everything
Token ID2279
Feature activation+7.25e-03

Pos logit contributions
ocus+0.053
issors+0.052
 seventeen+0.050
ets+0.049
 similarities+0.048
Neg logit contributions
 another-0.011
 baby-0.009
 his-0.009
 one-0.009
.-0.009
Token,
Token ID11
Feature activation-4.76e-01

Pos logit contributions
handed+0.000
 Wolf+0.000
 anyway+0.000
 cub+0.000
 baby+0.000
Neg logit contributions
issors-0.000
ocus-0.000
 similarities-0.000
 seventeen-0.000
ets-0.000
Token even
Token ID772
Feature activation-1.01e+00

Pos logit contributions
issors+0.028
ocus+0.027
 seventeen+0.026
 meanings+0.025
ides+0.024
Neg logit contributions
 his-0.008
 soon-0.008
 anyway-0.008
 baby-0.007
 another-0.007
Token their
Token ID511
Feature activation-1.46e-01

Pos logit contributions
issors+0.059
ocus+0.059
 similarities+0.056
 seventeen+0.056
ets+0.054
Neg logit contributions
 another-0.012
 soon-0.012
 anyway-0.012
 baby-0.011
 his-0.011
Token sp
Token ID599
Feature activation-2.70e+00

Pos logit contributions
ocus+0.007
issors+0.006
 seventeen+0.006
ets+0.006
 ind+0.006
Neg logit contributions
 baby-0.004
 cub-0.004
 Wolf-0.004
 therm-0.004
 another-0.004
Tokenoons
Token ID13022
Feature activation-3.86e-01

Pos logit contributions
 similarities+0.082
issors+0.080
 ind+0.079
ocus+0.078
 seventeen+0.077
Neg logit contributions
handed-0.103
rolley-0.100
 therm-0.096
 Wolf-0.095
 anyway-0.095
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
ocus+0.017
 similarities+0.017
issors+0.016
ets+0.016
 seventeen+0.015
Neg logit contributions
 Wolf-0.010
handed-0.010
Mo-0.009
 cub-0.009
 therm-0.009
Token The
Token ID383
Feature activation-3.10e-01

Pos logit contributions
issors+0.015
ocus+0.015
 similarities+0.015
ets+0.014
 seventeen+0.014
Neg logit contributions
 Wolf-0.005
handed-0.005
 cub-0.005
Mo-0.005
 therm-0.005
Token end
Token ID886
Feature activation+2.46e-01

Pos logit contributions
ocus+0.017
issors+0.017
ets+0.017
 similarities+0.016
 seventeen+0.016
Neg logit contributions
 Wolf-0.005
 baby-0.005
 therm-0.005
 cub-0.005
handed-0.004
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
handed+0.004
 Wolf+0.004
eled+0.004
Mo+0.004
rolley+0.004
Neg logit contributions
ets-0.013
 similarities-0.013
ocus-0.013
issors-0.012
apes-0.012
Token
Token ID220
Feature activation+1.52e+00

Pos logit contributions
handed+0.035
rolley+0.033
 Wolf+0.033
burn+0.033
Mo+0.031
Neg logit contributions
issors-0.043
 similarities-0.042
ocus-0.041
 ind-0.039
apes-0.039
Token
Token ID198
Feature activation+7.17e-01

Pos logit contributions
 Wolf+0.037
handed+0.037
burn+0.037
 lamb+0.036
hand+0.036
Neg logit contributions
issors-0.069
ocus-0.064
 similarities-0.061
apes-0.060
ets-0.059
Token
Token ID198
Feature activation+8.50e-01

Pos logit contributions
 Wolf+0.018
burn+0.018
handed+0.018
 lamb+0.017
 cub+0.017
Neg logit contributions
issors-0.031
ocus-0.029
 similarities-0.029
apes-0.028
 ind-0.027
Token"
Token ID1
Feature activation-2.86e-01

Pos logit contributions
 Wolf+0.024
handed+0.023
 cub+0.022
 baby+0.021
seat+0.021
Neg logit contributions
issors-0.036
ocus-0.035
 similarities-0.035
ets-0.033
 seventeen-0.033
TokenMy
Token ID3666
Feature activation+5.20e-01

Pos logit contributions
ocus+0.016
ets+0.016
issors+0.016
 similarities+0.015
 seventeen+0.015
Neg logit contributions
handed-0.005
 Wolf-0.004
 therm-0.004
 anyway-0.004
 baby-0.004
Token sp
Token ID599
Feature activation-2.29e+00

Pos logit contributions
 Wolf+0.018
handed+0.018
 cub+0.017
 baby+0.017
 anyway+0.017
Neg logit contributions
issors-0.018
ocus-0.018
 similarities-0.017
ets-0.017
 seventeen-0.016
Tokenade
Token ID671
Feature activation+3.04e-01

Pos logit contributions
 similarities+0.092
 ind+0.088
 seventeen+0.085
 la+0.085
 culture+0.079
Neg logit contributions
us-0.066
handed-0.065
rolley-0.064
 anyway-0.062
 therm-0.062
Token is
Token ID318
Feature activation+1.41e-01

Pos logit contributions
handed+0.010
 Wolf+0.010
 therm+0.010
 anyway+0.010
 baby+0.010
Neg logit contributions
 similarities-0.011
issors-0.011
ocus-0.011
 seventeen-0.010
ets-0.010
Token broken
Token ID5445
Feature activation+8.40e-01

Pos logit contributions
 Wolf+0.004
handed+0.004
 anyway+0.004
 therm+0.004
 cub+0.004
Neg logit contributions
ocus-0.006
issors-0.006
 similarities-0.006
ets-0.006
 seventeen-0.005
Token,
Token ID11
Feature activation-8.63e-02

Pos logit contributions
handed+0.021
 Wolf+0.021
Mo+0.020
hand+0.019
 cub+0.019
Neg logit contributions
issors-0.037
ocus-0.036
ets-0.035
 similarities-0.035
 seventeen-0.034
Token Mom
Token ID11254
Feature activation+3.58e-03

Pos logit contributions
ocus+0.005
issors+0.005
ets+0.005
 similarities+0.004
 seventeen+0.004
Neg logit contributions
 baby-0.002
 Wolf-0.002
 his-0.002
 anyway-0.002
 therm-0.002
Token cal
Token ID2386
Feature activation+1.07e+00

Pos logit contributions
 Wolf+0.004
handed+0.004
Mo+0.004
 cub+0.003
hand+0.003
Neg logit contributions
ocus-0.015
ets-0.015
 similarities-0.015
issors-0.015
 seventeen-0.015
Tokenmer
Token ID647
Feature activation-1.91e+00

Pos logit contributions
 Wolf+0.037
handed+0.037
Mo+0.035
 cub+0.035
 therm+0.034
Neg logit contributions
ocus-0.037
issors-0.037
 similarities-0.036
ets-0.035
 seventeen-0.034
Token."
Token ID526
Feature activation+2.28e-01

Pos logit contributions
issors+0.092
ocus+0.092
 similarities+0.090
ets+0.090
 seventeen+0.086
Neg logit contributions
 Wolf-0.039
handed-0.038
Mo-0.036
 therm-0.035
 cub-0.034
Token
Token ID198
Feature activation+1.13e-01

Pos logit contributions
 Wolf+0.006
handed+0.006
 cub+0.006
Mo+0.006
 anyway+0.005
Neg logit contributions
issors-0.010
ocus-0.010
 similarities-0.010
ets-0.009
 seventeen-0.009
Token
Token ID198
Feature activation+4.48e-01

Pos logit contributions
handed+0.002
burn+0.002
 Wolf+0.002
rolley+0.002
 therm+0.002
Neg logit contributions
ocus-0.005
 similarities-0.005
issors-0.005
ets-0.005
 seventeen-0.005
TokenP
Token ID47
Feature activation-2.33e+00

Pos logit contributions
 Wolf+0.010
handed+0.010
 cub+0.009
 baby+0.009
 therm+0.009
Neg logit contributions
ocus-0.021
issors-0.021
 similarities-0.021
ets-0.020
 seventeen-0.020
Tokenaco
Token ID10602
Feature activation-4.08e-01

Pos logit contributions
issors+0.078
ocus+0.078
 similarities+0.077
ets+0.073
 seventeen+0.072
Neg logit contributions
 Wolf-0.083
handed-0.082
 cub-0.078
Mo-0.077
 anyway-0.076
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
ocus+0.018
issors+0.018
 similarities+0.017
ets+0.017
 seventeen+0.017
Neg logit contributions
 Wolf-0.010
handed-0.010
Mo-0.009
 cub-0.009
 therm-0.009
Token Felix
Token ID29721
Feature activation+1.15e+00

Pos logit contributions
 similarities+0.006
issors+0.006
ocus+0.006
 ind+0.005
 meanings+0.005
Neg logit contributions
handed-0.004
rolley-0.004
 anyways-0.004
 able-0.004
hand-0.004
Token ate
Token ID15063
Feature activation+9.49e-02

Pos logit contributions
 Wolf+0.033
handed+0.033
Mo+0.030
 cub+0.030
 therm+0.030
Neg logit contributions
issors-0.046
ocus-0.046
 similarities-0.046
ets-0.044
 seventeen-0.043
Token their
Token ID511
Feature activation+1.76e-01

Pos logit contributions
handed+0.002
 Wolf+0.002
Mo+0.002
rolley+0.002
seat+0.002
Neg logit contributions
 similarities-0.004
issors-0.004
ocus-0.004
 seventeen-0.004
ets-0.004
Token a
Token ID257
Feature activation-7.80e-01

Pos logit contributions
issors+0.043
 similarities+0.042
ocus+0.042
ets+0.040
 seventeen+0.039
Neg logit contributions
 another-0.009
 one-0.008
 cub-0.008
 Wolf-0.008
 baby-0.008
Token puzzle
Token ID15027
Feature activation-8.94e-01

Pos logit contributions
issors+0.033
ets+0.032
ocus+0.032
 similarities+0.032
apes+0.030
Neg logit contributions
 baby-0.023
 cub-0.022
 therm-0.022
 Wolf-0.022
 bear-0.021
Token,
Token ID11
Feature activation-9.14e-01

Pos logit contributions
 similarities+0.045
issors+0.044
ocus+0.043
 seventeen+0.041
ets+0.041
Neg logit contributions
.-0.017
handed-0.017
 cub-0.016
 Wolf-0.016
 one-0.016
Token a
Token ID257
Feature activation-7.76e-01

Pos logit contributions
issors+0.052
 similarities+0.050
ocus+0.049
ets+0.048
apes+0.046
Neg logit contributions
 one-0.015
 another-0.015
 his-0.013
 baby-0.013
 cub-0.013
Token cr
Token ID1067
Feature activation-1.49e+00

Pos logit contributions
issors+0.032
ocus+0.031
ets+0.031
 similarities+0.030
apes+0.028
Neg logit contributions
 baby-0.024
 cub-0.023
 therm-0.023
 Wolf-0.023
 bear-0.022
Tokenay
Token ID323
Feature activation-2.72e+00

Pos logit contributions
 similarities+0.046
issors+0.038
 narrative+0.037
ocus+0.037
 culture+0.036
Neg logit contributions
 Wolf-0.058
seat-0.057
!-0.057
 therm-0.057
 front-0.056
Tokenon
Token ID261
Feature activation-1.25e+00

Pos logit contributions
 similarities+0.121
issors+0.118
ocus+0.115
ets+0.111
 seventeen+0.109
Neg logit contributions
 Wolf-0.068
handed-0.066
 therm-0.065
 baby-0.064
 cub-0.064
Token,
Token ID11
Feature activation-8.22e-01

Pos logit contributions
 similarities+0.064
issors+0.063
ocus+0.062
 seventeen+0.060
ets+0.059
Neg logit contributions
 Wolf-0.022
handed-0.022
 cub-0.021
 baby-0.020
 anyway-0.020
Token a
Token ID257
Feature activation-8.27e-01

Pos logit contributions
issors+0.048
 similarities+0.047
ocus+0.046
ets+0.044
 narrative+0.043
Neg logit contributions
 one-0.013
 another-0.013
.-0.011
 his-0.011
 soon-0.011
Token dinosaur
Token ID28257
Feature activation-1.12e+00

Pos logit contributions
issors+0.033
ocus+0.032
ets+0.032
 similarities+0.032
apes+0.029
Neg logit contributions
 baby-0.027
 cub-0.026
 therm-0.025
 Wolf-0.025
 bear-0.024
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
 similarities+0.056
issors+0.056
ocus+0.054
 seventeen+0.052
ets+0.052
Neg logit contributions
 Wolf-0.021
 cub-0.020
 baby-0.020
handed-0.020
.-0.020
Token me
Token ID502
Feature activation-2.24e+00

Pos logit contributions
 similarities+0.028
ocus+0.027
issors+0.027
ets+0.026
 ind+0.025
Neg logit contributions
handed-0.021
 Wolf-0.020
rolley-0.019
seat-0.019
Mo-0.019
Token."
Token ID526
Feature activation-4.09e-01

Pos logit contributions
ocus+0.107
ets+0.107
 similarities+0.106
issors+0.102
 ind+0.097
Neg logit contributions
handed-0.048
 Wolf-0.048
Mo-0.044
 therm-0.043
rolley-0.043
Token The
Token ID383
Feature activation-3.81e-01

Pos logit contributions
ocus+0.020
issors+0.020
 similarities+0.020
ets+0.019
 seventeen+0.019
Neg logit contributions
handed-0.008
 Wolf-0.008
 cub-0.007
Mo-0.007
 therm-0.007
Token cricket
Token ID18836
Feature activation-8.23e-01

Pos logit contributions
issors+0.012
ocus+0.012
 similarities+0.012
ets+0.011
 seventeen+0.011
Neg logit contributions
handed-0.014
 Wolf-0.014
Mo-0.013
 cub-0.013
hand-0.013
Token ch
Token ID442
Feature activation-1.82e+00

Pos logit contributions
ocus+0.033
 similarities+0.033
issors+0.033
ets+0.032
 seventeen+0.031
Neg logit contributions
handed-0.023
 Wolf-0.023
Mo-0.021
 therm-0.021
 cub-0.021
Tokenir
Token ID343
Feature activation-2.44e+00

Pos logit contributions
 similarities+0.058
issors+0.058
 seventeen+0.056
ocus+0.054
ets+0.053
Neg logit contributions
 Wolf-0.064
handed-0.063
eled-0.063
Mo-0.062
 baby-0.062
Tokenped
Token ID9124
Feature activation-4.76e-01

Pos logit contributions
ocus+0.099
issors+0.099
 similarities+0.098
ets+0.094
 seventeen+0.093
Neg logit contributions
 Wolf-0.069
handed-0.069
 cub-0.064
Mo-0.063
 therm-0.063
Token and
Token ID290
Feature activation-4.69e-01

Pos logit contributions
 similarities+0.020
ocus+0.019
ets+0.019
issors+0.019
 ind+0.019
Neg logit contributions
handed-0.013
 Wolf-0.012
rolley-0.012
Mo-0.012
 therm-0.012
Token waved
Token ID26834
Feature activation+1.06e-01

Pos logit contributions
 similarities+0.018
ocus+0.018
 ind+0.017
issors+0.017
ets+0.017
Neg logit contributions
handed-0.014
 Wolf-0.013
rolley-0.013
hand-0.012
seat-0.012
Token back
Token ID736
Feature activation+4.23e-02

Pos logit contributions
handed+0.003
 Wolf+0.003
Mo+0.003
 therm+0.003
 cub+0.003
Neg logit contributions
 similarities-0.004
ocus-0.004
issors-0.004
ets-0.004
 seventeen-0.004
Token.
Token ID13
Feature activation-5.95e-01

Pos logit contributions
handed+0.001
 Wolf+0.001
rolley+0.001
Mo+0.001
Son+0.001
Neg logit contributions
ocus-0.002
 similarities-0.002
ets-0.002
issors-0.002
 ind-0.002