TOP ACTIVATIONS
MAX = 5.055

the pigeon all those weeks ago . <|endoftext|> Mike and his
by people a long time ago . Tim my was very
coins that people used long ago . They saw paintings and
flyer posted a few days ago , looking for help around
how they were used long ago . Lily was fascinated and
someone a very long time ago . The little girl thought
important person a long time ago . She was excited and
be alive a long time ago ". M
vere r and cle vere r . Eventually the rabbit figured
she made a long time ago . Rose had promised always
big farm a long time ago . Lily listened as the
She gives some neck l aces to her friends and family
had bought a long time ago . They did not know
furry , some had l aces and some had buttons .
famous artist a long time ago ." The
it away a long time ago . It is not good
do , a few days ago . He started to applaud
help me with these l aces ?" Sarah asked .
colorful sk ates with l aces . On the
velvet box all those years ago . They were glad that

MIN ACTIVATIONS
MIN = -3.934

who own it don 't actually live there . They hate
couldn â t actually hide in it like she
see what was on the other side . So , Spot
you not playing on the other side of the tunnel ?"
grandmother who lived on the other side of the wall .
even though he did not actually win the competition . <|endoftext|>
saw a cat on the other side of a wire fence
know what was on the other side of the big door
who never explores will never truly know what is around him
big banana tree on the other side of the island .
flashlight , and a magn ifying glass . As
explore what was on the other side , so he flew
see what was on the other side of the wall .
friend Tim my on the other side of the fence .
to a house on the other side of town . He
bull and play on the other side of the park .
a big box on the other side of the room ,
see what is on the other side . "
pipe and he could never truly hate it . <|endoftext|> Once
was unusual - it could actually sing words !

INTERVAL 2.808 - 5.055
CONTAINS 0.018%

had breakfast a little while ago , so I 'm not
Her grandma had a delicate v ase on the table .
. She used a m itt to take out the pan
George yelled with g lee and scrambled onto Cloud y
as the fairy asked her r iddle . Lily thought hard

INTERVAL 0.561 - 2.808
CONTAINS 17.922%

friends were proud that they had worked together to restore the
room so she started walking around . Suddenly the
It â s winter time !
my r iddles . Are you ready ?" Anna
job and he was always telling stories . And that is

INTERVAL -1.686 - 0.561
CONTAINS 81.277%

mill near his house . The mill has a wheel that
the paper into the pocket of her dress and shut the
. He knew that no matter how confused he might be
, he quickly z ipped up his fur and hopped off
something new . She would learn how to count and how

INTERVAL -3.934 - -1.686
CONTAINS 0.783%

this time it did not taste good .
. They picked the prett iest pe b bles and started
close the cabinet doors and look at the things inside .
and he was always looking forward to his next adventure .
the little girl enjoyed the rest of their day in the
Token the
Token ID262
Feature activation+2.78e-01

Pos logit contributions
iring+0.007
ind+0.007
handed+0.006
 cheaper+0.006
glers+0.006
Neg logit contributions
isel-0.004
pan-0.004
ids-0.003
 nod-0.003
 imagination-0.003
Token pigeon
Token ID46387
Feature activation-1.14e-01

Pos logit contributions
 idea+0.009
 gard+0.008
 imagination+0.008
 tul+0.008
 nod+0.007
Neg logit contributions
iring-0.012
shadow-0.012
ding-0.011
ind-0.011
awed-0.011
Token all
Token ID477
Feature activation+4.19e-02

Pos logit contributions
ind+0.005
iring+0.005
 cheaper+0.005
glers+0.004
 homeless+0.004
Neg logit contributions
isel-0.004
alk-0.003
pan-0.003
ids-0.003
kin-0.003
Token those
Token ID883
Feature activation-3.05e-01

Pos logit contributions
isel+0.002
pan+0.001
alk+0.001
kin+0.001
ids+0.001
Neg logit contributions
ind-0.002
iring-0.002
handed-0.001
 cheaper-0.001
 barking-0.001
Token weeks
Token ID2745
Feature activation+1.84e+00

Pos logit contributions
ind+0.013
iring+0.012
 barking+0.012
handed+0.012
shadow+0.012
Neg logit contributions
 lived-0.010
isel-0.010
aces-0.009
 imagination-0.009
kin-0.009
Token ago
Token ID2084
Feature activation+5.06e+00

Pos logit contributions
isel+0.054
pan+0.051
ids+0.050
kin+0.049
alk+0.048
Neg logit contributions
ind-0.089
iring-0.087
 barking-0.077
 cheaper-0.076
 nicer-0.075
Token.
Token ID13
Feature activation+5.70e-01

Pos logit contributions
isel+0.189
pan+0.161
kin+0.157
alk+0.155
ids+0.151
Neg logit contributions
ind-0.218
iring-0.215
handed-0.189
 cheaper-0.189
 barking-0.185
Token<|endoftext|>
Token ID50256
Feature activation-1.27e+00

Pos logit contributions
isel+0.025
kin+0.021
pan+0.021
alk+0.019
brush+0.019
Neg logit contributions
ind-0.022
iring-0.022
handed-0.019
 barking-0.019
 elderly-0.018
TokenMike
Token ID16073
Feature activation+5.99e-02

Pos logit contributions
ind+0.057
iring+0.056
 cheaper+0.050
handed+0.050
 homeless+0.049
Neg logit contributions
isel-0.045
pan-0.037
alk-0.037
kin-0.037
ids-0.035
Token and
Token ID290
Feature activation-6.46e-01

Pos logit contributions
isel+0.002
pan+0.002
alk+0.002
kin+0.002
ids+0.002
Neg logit contributions
iring-0.002
ind-0.002
 cheaper-0.002
handed-0.002
 faster-0.002
Token his
Token ID465
Feature activation-6.85e-01

Pos logit contributions
ind+0.022
iring+0.022
handed+0.019
 barking+0.019
 cheaper+0.019
Neg logit contributions
isel-0.030
pan-0.026
kin-0.025
alk-0.025
ids-0.025
Token by
Token ID416
Feature activation+1.97e+00

Pos logit contributions
isel+0.010
alk+0.009
 imagination+0.009
ids+0.009
pan+0.009
Neg logit contributions
ind-0.013
iring-0.013
handed-0.012
ich-0.012
 concession-0.012
Token people
Token ID661
Feature activation+8.38e-01

Pos logit contributions
isel+0.059
alk+0.049
 imagination+0.048
kin+0.044
pan+0.042
Neg logit contributions
iring-0.099
ind-0.099
 concession-0.093
glers-0.093
handed-0.091
Token a
Token ID257
Feature activation+9.89e-01

Pos logit contributions
isel+0.023
ids+0.023
 can+0.021
pan+0.021
pter+0.021
Neg logit contributions
iring-0.039
ind-0.038
 sidelines-0.034
handed-0.034
 concession-0.034
Token long
Token ID890
Feature activation+1.35e+00

Pos logit contributions
isel+0.040
 imagination+0.034
alk+0.033
pan+0.032
 cuc+0.032
Neg logit contributions
iring-0.043
ind-0.039
glers-0.036
handed-0.035
 concession-0.033
Token time
Token ID640
Feature activation+7.33e-02

Pos logit contributions
isel+0.050
pan+0.043
kin+0.041
ids+0.040
alk+0.038
Neg logit contributions
ind-0.057
 barking-0.052
iring-0.051
 faster-0.050
 cheaper-0.049
Token ago
Token ID2084
Feature activation+4.88e+00

Pos logit contributions
isel+0.002
alk+0.002
ids+0.002
pan+0.002
kin+0.002
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
 homeless-0.003
 concession-0.003
Token.
Token ID13
Feature activation+6.07e-01

Pos logit contributions
isel+0.188
pan+0.160
kin+0.158
alk+0.155
ids+0.151
Neg logit contributions
ind-0.206
iring-0.203
handed-0.178
 cheaper-0.177
 barking-0.174
Token Tim
Token ID5045
Feature activation+5.19e-01

Pos logit contributions
isel+0.020
pan+0.015
alk+0.015
ids+0.014
kin+0.014
Neg logit contributions
ind-0.030
iring-0.029
handed-0.026
 cheaper-0.026
 faster-0.026
Tokenmy
Token ID1820
Feature activation+1.45e-01

Pos logit contributions
isel+0.025
alk+0.021
kin+0.021
pan+0.021
aces+0.020
Neg logit contributions
iring-0.017
ind-0.016
 cheaper-0.015
handed-0.014
 homeless-0.014
Token was
Token ID373
Feature activation+2.93e-01

Pos logit contributions
isel+0.005
pan+0.004
kin+0.004
alk+0.004
ids+0.004
Neg logit contributions
ind-0.006
iring-0.006
handed-0.006
 cheaper-0.006
 barking-0.006
Token very
Token ID845
Feature activation-1.37e+00

Pos logit contributions
isel+0.013
pan+0.011
kin+0.011
ids+0.010
alk+0.010
Neg logit contributions
ind-0.011
iring-0.011
handed-0.009
 cheaper-0.009
glers-0.009
Token coins
Token ID10796
Feature activation+6.60e-01

Pos logit contributions
ind+0.030
iring+0.030
handed+0.026
ich+0.025
 cheaper+0.025
Neg logit contributions
isel-0.025
pan-0.021
kin-0.020
alk-0.020
ids-0.020
Token that
Token ID326
Feature activation+6.07e-02

Pos logit contributions
isel+0.018
pan+0.016
kin+0.016
ids+0.016
aces+0.015
Neg logit contributions
ind-0.035
iring-0.033
handed-0.032
 concession-0.031
 homeless-0.030
Token people
Token ID661
Feature activation-1.65e-01

Pos logit contributions
isel+0.002
kin+0.002
pan+0.002
 lived+0.002
ids+0.002
Neg logit contributions
ind-0.003
iring-0.003
handed-0.003
shadow-0.002
 cheaper-0.002
Token used
Token ID973
Feature activation-4.64e-02

Pos logit contributions
ind+0.010
iring+0.009
handed+0.009
ich+0.008
 destination+0.008
Neg logit contributions
isel-0.004
 lived-0.003
pan-0.003
kin-0.003
 are-0.003
Token long
Token ID890
Feature activation+1.21e+00

Pos logit contributions
iring+0.002
ind+0.002
handed+0.002
ich+0.002
itating+0.002
Neg logit contributions
isel-0.002
alk-0.001
pan-0.001
ids-0.001
 imagination-0.001
Token ago
Token ID2084
Feature activation+4.85e+00

Pos logit contributions
isel+0.043
pan+0.035
kin+0.034
alk+0.034
ids+0.032
Neg logit contributions
ind-0.055
iring-0.055
handed-0.049
 cheaper-0.049
 barking-0.048
Token.
Token ID13
Feature activation+1.33e-01

Pos logit contributions
isel+0.194
pan+0.163
kin+0.160
alk+0.159
ids+0.154
Neg logit contributions
ind-0.198
iring-0.196
handed-0.172
 cheaper-0.170
 barking-0.168
Token They
Token ID1119
Feature activation+4.04e-01

Pos logit contributions
isel+0.005
pan+0.004
kin+0.004
alk+0.004
ids+0.004
Neg logit contributions
iring-0.006
ind-0.006
 cheaper-0.005
handed-0.005
 barking-0.005
Token saw
Token ID2497
Feature activation+3.22e-02

Pos logit contributions
isel+0.013
pan+0.011
kin+0.011
alk+0.011
ids+0.010
Neg logit contributions
ind-0.019
iring-0.019
 cheaper-0.017
 barking-0.017
 faster-0.017
Token paintings
Token ID21641
Feature activation+8.26e-01

Pos logit contributions
isel+0.001
 imagination+0.001
 cuc+0.001
 lived+0.001
pan+0.001
Neg logit contributions
ind-0.001
iring-0.001
shadow-0.001
itating-0.001
handed-0.001
Token and
Token ID290
Feature activation-6.86e-01

Pos logit contributions
brush+0.016
isel+0.015
pan+0.014
aces+0.014
ids+0.014
Neg logit contributions
ind-0.049
handed-0.046
iring-0.045
shadow-0.044
 homeless-0.042
Token flyer
Token ID42464
Feature activation-8.86e-02

Pos logit contributions
isel+0.005
pan+0.004
 idea+0.004
kin+0.004
 imagination+0.004
Neg logit contributions
iring-0.006
ind-0.006
handed-0.006
ll-0.005
glers-0.005
Token posted
Token ID4481
Feature activation-1.50e-01

Pos logit contributions
ind+0.004
iring+0.004
handed+0.003
glers+0.003
ich+0.003
Neg logit contributions
isel-0.003
pan-0.003
kin-0.003
alk-0.003
 idea-0.003
Token a
Token ID257
Feature activation+6.19e-01

Pos logit contributions
ind+0.008
iring+0.007
ll+0.007
handed+0.007
ich+0.007
Neg logit contributions
isel-0.004
pan-0.004
brush-0.004
aces-0.004
 It-0.004
Token few
Token ID1178
Feature activation+7.59e-01

Pos logit contributions
isel+0.022
pan+0.019
brush+0.019
 imagination+0.019
kin+0.019
Neg logit contributions
iring-0.029
ind-0.027
handed-0.024
glers-0.024
ll-0.024
Token days
Token ID1528
Feature activation+1.59e+00

Pos logit contributions
isel+0.029
pan+0.023
kin+0.023
alk+0.023
 imagination+0.022
Neg logit contributions
iring-0.033
ind-0.033
handed-0.029
 barking-0.029
ich-0.028
Token ago
Token ID2084
Feature activation+4.85e+00

Pos logit contributions
isel+0.048
pan+0.042
ids+0.041
alk+0.040
aces+0.039
Neg logit contributions
ind-0.080
iring-0.075
 cheaper-0.068
 nicer-0.067
handed-0.067
Token,
Token ID11
Feature activation+9.53e-01

Pos logit contributions
isel+0.197
pan+0.164
alk+0.159
kin+0.159
ids+0.154
Neg logit contributions
ind-0.193
iring-0.192
handed-0.170
 cheaper-0.167
 barking-0.167
Token looking
Token ID2045
Feature activation+7.03e-02

Pos logit contributions
isel+0.028
 imagination+0.024
 It+0.024
pan+0.024
ids+0.023
Neg logit contributions
ind-0.050
iring-0.045
glers-0.042
handed-0.041
ll-0.041
Token for
Token ID329
Feature activation-1.65e-01

Pos logit contributions
isel+0.003
pan+0.002
 idea+0.002
ids+0.002
aces+0.002
Neg logit contributions
ind-0.003
iring-0.003
handed-0.003
ll-0.003
ich-0.003
Token help
Token ID1037
Feature activation+3.38e-02

Pos logit contributions
ind+0.008
itating+0.008
iring+0.008
ll+0.007
glers+0.007
Neg logit contributions
isel-0.005
 imagination-0.004
 lived-0.004
ids-0.004
 idea-0.004
Token around
Token ID1088
Feature activation+1.21e+00

Pos logit contributions
isel+0.001
pan+0.001
alk+0.001
 idea+0.001
ids+0.001
Neg logit contributions
ind-0.002
iring-0.002
Nice-0.002
ich-0.002
handed-0.002
Token how
Token ID703
Feature activation+3.61e-01

Pos logit contributions
isel+0.005
pan+0.004
 imagination+0.004
kin+0.004
 lived+0.004
Neg logit contributions
ind-0.006
iring-0.006
handed-0.005
ich-0.005
itating-0.005
Token they
Token ID484
Feature activation-1.44e-01

Pos logit contributions
isel+0.018
pan+0.016
kin+0.015
alk+0.015
ids+0.015
Neg logit contributions
iring-0.012
ind-0.011
 cheaper-0.010
 elderly-0.010
 new-0.009
Token were
Token ID547
Feature activation-2.59e-02

Pos logit contributions
ind+0.007
iring+0.007
 cheaper+0.006
handed+0.006
 faster+0.006
Neg logit contributions
isel-0.005
pan-0.004
kin-0.004
alk-0.004
ids-0.003
Token used
Token ID973
Feature activation+9.24e-02

Pos logit contributions
ind+0.001
iring+0.001
handed+0.001
eddy+0.001
 sidelines+0.001
Neg logit contributions
isel-0.001
aces-0.001
 lived-0.001
 idea-0.001
ids-0.001
Token long
Token ID890
Feature activation+1.31e+00

Pos logit contributions
isel+0.004
pan+0.003
alk+0.003
ids+0.003
 imagination+0.003
Neg logit contributions
ind-0.004
iring-0.004
handed-0.004
ich-0.003
 homeless-0.003
Token ago
Token ID2084
Feature activation+4.82e+00

Pos logit contributions
isel+0.053
kin+0.044
pan+0.044
alk+0.041
ids+0.041
Neg logit contributions
ind-0.051
iring-0.049
 cheaper-0.045
 faster-0.045
 barking-0.045
Token.
Token ID13
Feature activation+7.02e-01

Pos logit contributions
isel+0.184
pan+0.157
kin+0.155
alk+0.152
ids+0.148
Neg logit contributions
ind-0.204
iring-0.202
handed-0.177
 cheaper-0.175
 barking-0.173
Token Lily
Token ID20037
Feature activation+4.61e-01

Pos logit contributions
isel+0.025
pan+0.021
kin+0.020
alk+0.020
ids+0.019
Neg logit contributions
ind-0.032
iring-0.031
handed-0.028
 cheaper-0.028
 barking-0.028
Token was
Token ID373
Feature activation+5.12e-01

Pos logit contributions
isel+0.019
pan+0.017
alk+0.016
kin+0.016
ids+0.015
Neg logit contributions
ind-0.018
iring-0.017
 faster-0.016
 elderly-0.016
 cheaper-0.015
Token fascinated
Token ID30103
Feature activation+5.86e-01

Pos logit contributions
isel+0.020
pan+0.017
kin+0.017
ids+0.016
aces+0.016
Neg logit contributions
ind-0.022
iring-0.021
handed-0.019
glers-0.018
 cheaper-0.017
Token and
Token ID290
Feature activation+2.66e-01

Pos logit contributions
 idea+0.015
isel+0.015
 It+0.014
ily+0.014
 can+0.013
Neg logit contributions
shadow-0.026
 sidelines-0.025
 concession-0.025
handed-0.025
ind-0.024
Token someone
Token ID2130
Feature activation-7.88e-01

Pos logit contributions
isel+0.049
alk+0.044
kin+0.042
pan+0.042
 imagination+0.040
Neg logit contributions
ind-0.070
iring-0.069
 cheaper-0.062
 concession-0.062
handed-0.062
Token a
Token ID257
Feature activation+7.66e-01

Pos logit contributions
iring+0.039
ind+0.038
 sidelines+0.034
Nice+0.033
handed+0.033
Neg logit contributions
 can-0.021
 lived-0.020
isel-0.019
ids-0.019
 are-0.019
Token very
Token ID845
Feature activation-6.92e-01

Pos logit contributions
isel+0.025
 imagination+0.022
kin+0.022
 cuc+0.022
pan+0.022
Neg logit contributions
iring-0.038
ind-0.034
glers-0.030
handed-0.030
itating-0.030
Token long
Token ID890
Feature activation+1.04e+00

Pos logit contributions
iring+0.026
ning+0.025
ind+0.024
glers+0.023
handed+0.023
Neg logit contributions
isel-0.029
 idea-0.026
 imagination-0.025
kin-0.025
alk-0.024
Token time
Token ID640
Feature activation-1.06e-01

Pos logit contributions
isel+0.035
pan+0.028
kin+0.027
alk+0.027
ids+0.027
Neg logit contributions
ind-0.048
iring-0.046
 barking-0.043
 cheaper-0.043
handed-0.043
Token ago
Token ID2084
Feature activation+4.79e+00

Pos logit contributions
ind+0.006
iring+0.006
handed+0.006
glers+0.006
 homeless+0.006
Neg logit contributions
isel-0.002
pan-0.002
ids-0.001
alk-0.001
 imagination-0.001
Token.
Token ID13
Feature activation+5.25e-01

Pos logit contributions
isel+0.190
pan+0.157
alk+0.152
kin+0.152
ids+0.148
Neg logit contributions
ind-0.195
iring-0.193
handed-0.172
 cheaper-0.170
 barking-0.168
Token The
Token ID383
Feature activation+6.50e-01

Pos logit contributions
isel+0.017
pan+0.014
kin+0.013
alk+0.013
ids+0.013
Neg logit contributions
ind-0.026
iring-0.025
handed-0.023
 cheaper-0.023
 barking-0.022
Token little
Token ID1310
Feature activation+1.10e-01

Pos logit contributions
isel+0.025
kin+0.021
pan+0.021
alk+0.021
ids+0.020
Neg logit contributions
ind-0.027
iring-0.027
handed-0.024
 barking-0.023
 cheaper-0.023
Token girl
Token ID2576
Feature activation-3.27e-01

Pos logit contributions
isel+0.005
pan+0.005
ids+0.005
alk+0.005
kin+0.004
Neg logit contributions
iring-0.004
ind-0.003
 elderly-0.003
 cheaper-0.003
 faster-0.003
Token thought
Token ID1807
Feature activation+2.41e-01

Pos logit contributions
ind+0.014
iring+0.014
 cheaper+0.012
handed+0.012
 barking+0.012
Neg logit contributions
isel-0.012
pan-0.010
alk-0.010
kin-0.010
ids-0.010
Token important
Token ID1593
Feature activation+5.26e-01

Pos logit contributions
isel+0.009
alk+0.008
kin+0.008
pan+0.008
 imagination+0.008
Neg logit contributions
iring-0.005
ind-0.005
handed-0.004
 barking-0.004
 cheaper-0.004
Token person
Token ID1048
Feature activation-8.14e-01

Pos logit contributions
isel+0.024
pan+0.020
kin+0.020
alk+0.020
ids+0.019
Neg logit contributions
ind-0.019
iring-0.019
handed-0.016
 cheaper-0.016
 barking-0.015
Token a
Token ID257
Feature activation+8.44e-01

Pos logit contributions
iring+0.041
ind+0.041
 sidelines+0.036
handed+0.035
 homeless+0.034
Neg logit contributions
ids-0.020
 lived-0.020
isel-0.020
 can-0.020
pan-0.020
Token long
Token ID890
Feature activation+9.87e-01

Pos logit contributions
isel+0.030
 imagination+0.028
 cuc+0.026
 gard+0.026
 idea+0.026
Neg logit contributions
iring-0.039
ind-0.036
glers-0.033
ning-0.031
ized-0.031
Token time
Token ID640
Feature activation-1.88e-01

Pos logit contributions
isel+0.035
pan+0.029
kin+0.027
alk+0.027
ids+0.026
Neg logit contributions
ind-0.045
iring-0.044
 barking-0.040
handed-0.040
 cheaper-0.040
Token ago
Token ID2084
Feature activation+4.78e+00

Pos logit contributions
ind+0.011
iring+0.011
handed+0.010
 cheaper+0.010
 homeless+0.010
Neg logit contributions
isel-0.004
pan-0.003
alk-0.003
 imagination-0.003
ids-0.003
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
isel+0.194
pan+0.163
kin+0.159
alk+0.158
ids+0.154
Neg logit contributions
ind-0.191
iring-0.189
handed-0.166
 cheaper-0.165
 barking-0.163
Token She
Token ID1375
Feature activation+8.14e-01

Pos logit contributions
isel+0.009
 It+0.007
alk+0.006
pan+0.006
ids+0.006
Neg logit contributions
ind-0.021
iring-0.020
ich-0.018
 cheaper-0.018
 faster-0.017
Token was
Token ID373
Feature activation+4.27e-01

Pos logit contributions
isel+0.032
pan+0.027
kin+0.026
alk+0.026
ids+0.025
Neg logit contributions
ind-0.034
iring-0.034
handed-0.030
 cheaper-0.029
 barking-0.029
Token excited
Token ID6568
Feature activation+2.39e-01

Pos logit contributions
isel+0.016
pan+0.014
kin+0.013
 idea+0.013
ids+0.013
Neg logit contributions
ind-0.018
iring-0.018
handed-0.016
glers-0.016
ll-0.015
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
 idea+0.006
isel+0.006
 imagination+0.005
 It+0.005
 nod+0.005
Neg logit contributions
ind-0.013
iring-0.012
handed-0.011
ich-0.011
 fastest-0.011
Token be
Token ID307
Feature activation+6.84e-01

Pos logit contributions
isel+0.022
alk+0.017
 imagination+0.016
kin+0.016
pan+0.016
Neg logit contributions
iring-0.041
ind-0.041
handed-0.036
ich-0.036
 cheaper-0.036
Token alive
Token ID6776
Feature activation+3.81e-01

Pos logit contributions
isel+0.028
kin+0.024
pan+0.023
ids+0.023
 imagination+0.023
Neg logit contributions
iring-0.028
ind-0.027
handed-0.024
glers-0.023
 barking-0.023
Token a
Token ID257
Feature activation+5.81e-01

Pos logit contributions
isel+0.013
pan+0.012
kin+0.011
alk+0.011
ids+0.011
Neg logit contributions
iring-0.016
ind-0.016
handed-0.015
 cheaper-0.014
 barking-0.014
Token long
Token ID890
Feature activation+9.64e-01

Pos logit contributions
isel+0.021
 imagination+0.018
 cuc+0.018
kin+0.017
 gard+0.017
Neg logit contributions
iring-0.027
ind-0.025
glers-0.023
handed-0.022
ning-0.022
Token time
Token ID640
Feature activation-1.53e-01

Pos logit contributions
isel+0.035
pan+0.030
ids+0.028
kin+0.027
alk+0.027
Neg logit contributions
ind-0.042
iring-0.038
 barking-0.037
 faster-0.036
 cheaper-0.036
Token ago
Token ID2084
Feature activation+4.77e+00

Pos logit contributions
ind+0.007
iring+0.007
handed+0.006
 cheaper+0.006
 homeless+0.006
Neg logit contributions
isel-0.005
pan-0.004
alk-0.004
kin-0.004
ids-0.004
Token".
Token ID1911
Feature activation+8.51e-01

Pos logit contributions
isel+0.194
pan+0.163
kin+0.159
alk+0.158
ids+0.154
Neg logit contributions
ind-0.191
iring-0.188
handed-0.166
 cheaper-0.164
 barking-0.162
Token
Token ID220
Feature activation-4.59e-01

Pos logit contributions
isel+0.021
 It+0.019
 nod+0.015
ids+0.015
alk+0.015
Neg logit contributions
ind-0.049
iring-0.045
 faster-0.041
glers-0.041
 nicer-0.041
Token
Token ID198
Feature activation+3.99e-01

Pos logit contributions
ind+0.022
iring+0.021
 cheaper+0.019
handed+0.019
 faster+0.019
Neg logit contributions
isel-0.015
pan-0.012
alk-0.012
kin-0.012
ids-0.012
Token
Token ID198
Feature activation+1.39e-02

Pos logit contributions
isel+0.007
 It+0.006
 lived+0.005
kin+0.005
ily+0.005
Neg logit contributions
ind-0.024
iring-0.022
 fastest-0.021
 faster-0.021
 nicer-0.021
TokenM
Token ID44
Feature activation+4.73e-01

Pos logit contributions
isel+0.000
kin+0.000
brush+0.000
 lived+0.000
ily+0.000
Neg logit contributions
iring-0.001
ind-0.001
 barking-0.001
 faster-0.001
 fastest-0.001
Tokenvere
Token ID4119
Feature activation-4.52e-01

Pos logit contributions
ind+0.038
iring+0.038
handed+0.033
 cheaper+0.032
 faster+0.032
Neg logit contributions
isel-0.049
pan-0.042
kin-0.041
alk-0.041
ids-0.040
Tokenr
Token ID81
Feature activation+4.37e+00

Pos logit contributions
ind+0.025
iring+0.024
handed+0.022
 barking+0.022
 faster+0.022
Neg logit contributions
isel-0.012
pan-0.010
kin-0.009
ids-0.008
brush-0.008
Token and
Token ID290
Feature activation+8.44e-01

Pos logit contributions
isel+0.157
pan+0.143
alk+0.141
kin+0.139
ids+0.131
Neg logit contributions
iring-0.184
ind-0.184
 cheaper-0.169
handed-0.162
 homeless-0.161
Token cle
Token ID1190
Feature activation-5.90e-01

Pos logit contributions
isel+0.035
pan+0.029
kin+0.028
 lived+0.028
 idea+0.028
Neg logit contributions
ind-0.036
iring-0.033
handed-0.029
oma-0.029
ich-0.028
Tokenvere
Token ID4119
Feature activation-3.95e-01

Pos logit contributions
ind+0.019
iring+0.019
handed+0.016
 cheaper+0.016
 faster+0.016
Neg logit contributions
isel-0.028
pan-0.025
kin-0.024
alk-0.024
ids-0.023
Tokenr
Token ID81
Feature activation+4.75e+00

Pos logit contributions
ind+0.022
iring+0.022
handed+0.020
 barking+0.020
 faster+0.019
Neg logit contributions
isel-0.010
pan-0.008
kin-0.008
ids-0.007
brush-0.007
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
isel+0.175
pan+0.156
alk+0.154
kin+0.153
ids+0.145
Neg logit contributions
ind-0.197
iring-0.197
 cheaper-0.180
handed-0.176
 homeless-0.174
Token Eventually
Token ID16178
Feature activation+8.30e-01

Pos logit contributions
isel+0.006
alk+0.005
pan+0.004
ids+0.004
 It+0.004
Neg logit contributions
ind-0.012
iring-0.012
 cheaper-0.011
handed-0.010
 homeless-0.010
Token the
Token ID262
Feature activation+8.50e-01

Pos logit contributions
isel+0.026
pan+0.020
kin+0.020
alk+0.019
ids+0.019
Neg logit contributions
ind-0.041
iring-0.041
handed-0.037
 cheaper-0.037
 barking-0.037
Token rabbit
Token ID22746
Feature activation-2.19e-01

Pos logit contributions
isel+0.031
pan+0.025
alk+0.025
ids+0.024
kin+0.024
Neg logit contributions
ind-0.038
iring-0.038
 cheaper-0.034
 barking-0.034
 elderly-0.033
Token figured
Token ID11638
Feature activation-8.17e-01

Pos logit contributions
ind+0.012
iring+0.011
 cheaper+0.010
handed+0.010
 homeless+0.010
Neg logit contributions
isel-0.006
pan-0.005
alk-0.005
 lived-0.005
kin-0.005
Token she
Token ID673
Feature activation+6.17e-02

Pos logit contributions
ind+0.001
iring+0.001
 cheaper+0.001
 barking+0.001
handed+0.001
Neg logit contributions
isel-0.002
pan-0.002
kin-0.002
alk-0.002
ids-0.002
Token made
Token ID925
Feature activation+4.78e-01

Pos logit contributions
isel+0.002
pan+0.001
kin+0.001
alk+0.001
ids+0.001
Neg logit contributions
ind-0.003
iring-0.003
handed-0.003
 cheaper-0.003
 barking-0.003
Token a
Token ID257
Feature activation+6.01e-01

Pos logit contributions
ily+0.008
 idea+0.008
 It+0.008
isel+0.008
 understand+0.007
Neg logit contributions
ind-0.030
iring-0.027
ich-0.026
glers-0.026
handed-0.025
Token long
Token ID890
Feature activation+8.34e-01

Pos logit contributions
isel+0.030
 idea+0.027
 imagination+0.026
alk+0.026
pan+0.026
Neg logit contributions
iring-0.019
ind-0.019
handed-0.016
glers-0.015
ized-0.014
Token time
Token ID640
Feature activation-1.93e-01

Pos logit contributions
isel+0.038
ids+0.031
pan+0.030
aces+0.030
adders+0.029
Neg logit contributions
 barking-0.029
ind-0.028
 faster-0.026
 new-0.026
 cheaper-0.026
Token ago
Token ID2084
Feature activation+4.74e+00

Pos logit contributions
ind+0.008
iring+0.008
handed+0.007
 homeless+0.006
 cheaper+0.006
Neg logit contributions
isel-0.008
pan-0.007
ids-0.007
kin-0.007
 imagination-0.007
Token.
Token ID13
Feature activation+2.05e-01

Pos logit contributions
isel+0.201
pan+0.162
alk+0.160
kin+0.155
ids+0.153
Neg logit contributions
iring-0.180
ind-0.179
handed-0.161
 barking-0.161
 cheaper-0.158
Token Rose
Token ID8049
Feature activation+9.35e-01

Pos logit contributions
isel+0.007
pan+0.005
alk+0.005
kin+0.005
ids+0.005
Neg logit contributions
ind-0.010
iring-0.010
handed-0.009
 cheaper-0.009
 homeless-0.009
Token had
Token ID550
Feature activation+6.97e-01

Pos logit contributions
isel+0.037
pan+0.030
alk+0.029
kin+0.029
ids+0.028
Neg logit contributions
ind-0.039
iring-0.038
 cheaper-0.035
 faster-0.035
handed-0.035
Token promised
Token ID8072
Feature activation+6.64e-01

Pos logit contributions
isel+0.023
 imagination+0.019
alk+0.019
pan+0.018
aces+0.018
Neg logit contributions
ind-0.034
iring-0.034
handed-0.029
ich-0.029
glers-0.028
Token always
Token ID1464
Feature activation+3.43e-01

Pos logit contributions
ily+0.017
isel+0.016
 imagination+0.016
ids+0.015
 It+0.015
Neg logit contributions
ind-0.035
glers-0.032
iring-0.032
 concession-0.031
handed-0.030
Token big
Token ID1263
Feature activation+9.44e-01

Pos logit contributions
isel+0.027
 imagination+0.026
 idea+0.025
 gard+0.024
 can+0.024
Neg logit contributions
iring-0.037
ind-0.035
glers-0.031
ning-0.031
awed-0.031
Token farm
Token ID5318
Feature activation+1.11e+00

Pos logit contributions
isel+0.035
 imagination+0.029
pan+0.029
alk+0.028
kin+0.028
Neg logit contributions
iring-0.043
ind-0.042
handed-0.037
itating-0.035
glers-0.034
Token a
Token ID257
Feature activation+5.92e-01

Pos logit contributions
isel+0.030
kin+0.030
pan+0.029
brush+0.029
ids+0.027
Neg logit contributions
ind-0.055
iring-0.054
itating-0.046
Nice-0.046
shadow-0.045
Token long
Token ID890
Feature activation+8.16e-01

Pos logit contributions
isel+0.021
 imagination+0.020
 gard+0.020
 cuc+0.019
 idea+0.019
Neg logit contributions
iring-0.027
ind-0.024
handed-0.022
awed-0.021
ning-0.021
Token time
Token ID640
Feature activation-2.14e-01

Pos logit contributions
isel+0.029
pan+0.023
kin+0.022
alk+0.022
ids+0.022
Neg logit contributions
ind-0.037
iring-0.037
handed-0.033
 cheaper-0.033
 barking-0.033
Token ago
Token ID2084
Feature activation+4.73e+00

Pos logit contributions
ind+0.012
iring+0.012
handed+0.011
 homeless+0.010
 cheaper+0.010
Neg logit contributions
isel-0.005
pan-0.004
alk-0.004
ids-0.004
 imagination-0.004
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
isel+0.186
pan+0.154
alk+0.149
kin+0.149
ids+0.145
Neg logit contributions
ind-0.194
iring-0.193
handed-0.171
 cheaper-0.169
 barking-0.168
Token Lily
Token ID20037
Feature activation+3.19e-01

Pos logit contributions
isel+0.015
pan+0.012
alk+0.012
 It+0.012
kin+0.012
Neg logit contributions
ind-0.023
iring-0.022
ich-0.020
handed-0.019
 barking-0.019
Token listened
Token ID16399
Feature activation+3.14e-01

Pos logit contributions
isel+0.011
pan+0.009
kin+0.009
alk+0.009
ids+0.009
Neg logit contributions
ind-0.014
iring-0.014
handed-0.013
 cheaper-0.013
 barking-0.012
Token as
Token ID355
Feature activation+3.36e-01

Pos logit contributions
isel+0.009
pan+0.008
alk+0.008
 It+0.008
 imagination+0.007
Neg logit contributions
ind-0.015
iring-0.015
handed-0.014
glers-0.014
ich-0.014
Token the
Token ID262
Feature activation+6.22e-01

Pos logit contributions
isel+0.012
kin+0.011
pan+0.010
alk+0.010
ids+0.010
Neg logit contributions
ind-0.015
iring-0.014
handed-0.013
 cheaper-0.013
 barking-0.013
Token She
Token ID1375
Feature activation+4.45e-02

Pos logit contributions
iring+0.010
ind+0.009
 barking+0.009
 cheaper+0.009
 new+0.008
Neg logit contributions
isel-0.011
pan-0.009
kin-0.009
alk-0.009
ids-0.008
Token gives
Token ID3607
Feature activation+2.95e-01

Pos logit contributions
isel+0.002
pan+0.002
alk+0.002
kin+0.002
anish+0.002
Neg logit contributions
ind-0.002
iring-0.002
 cheaper-0.002
 faster-0.001
 elderly-0.001
Token some
Token ID617
Feature activation+1.36e+00

Pos logit contributions
isel+0.010
pan+0.008
ids+0.008
 imagination+0.008
kin+0.008
Neg logit contributions
iring-0.014
ind-0.013
handed-0.012
 homeless-0.012
 barking-0.012
Token neck
Token ID7393
Feature activation+2.91e+00

Pos logit contributions
isel+0.048
pan+0.039
kin+0.039
alk+0.038
ids+0.037
Neg logit contributions
ind-0.062
iring-0.061
handed-0.055
 cheaper-0.054
 barking-0.054
Tokenl
Token ID75
Feature activation+1.64e+00

Pos logit contributions
isel+0.133
pan+0.113
kin+0.111
alk+0.110
ids+0.107
Neg logit contributions
ind-0.104
iring-0.102
 cheaper-0.088
handed-0.088
 barking-0.086
Tokenaces
Token ID2114
Feature activation+4.72e+00

Pos logit contributions
isel+0.041
pan+0.029
kin+0.025
alk+0.025
ids+0.023
Neg logit contributions
iring-0.093
ind-0.093
 faster-0.084
 barking-0.084
 cheaper-0.083
Token to
Token ID284
Feature activation+3.40e-01

Pos logit contributions
isel+0.163
pan+0.140
alk+0.136
kin+0.135
ids+0.133
Neg logit contributions
ind-0.217
iring-0.209
handed-0.191
 barking-0.185
 homeless-0.185
Token her
Token ID607
Feature activation-2.19e-02

Pos logit contributions
isel+0.010
ids+0.009
kin+0.008
pan+0.008
alk+0.008
Neg logit contributions
iring-0.017
ind-0.017
handed-0.016
ich-0.015
 homeless-0.015
Token friends
Token ID2460
Feature activation-3.13e-01

Pos logit contributions
iring+0.001
ind+0.001
handed+0.001
 homeless+0.001
itating+0.001
Neg logit contributions
isel-0.001
kin-0.001
 imagination-0.001
ids-0.001
alk-0.001
Token and
Token ID290
Feature activation-4.55e-01

Pos logit contributions
ind+0.014
iring+0.014
handed+0.012
 cheaper+0.012
 homeless+0.012
Neg logit contributions
isel-0.012
pan-0.010
kin-0.010
alk-0.010
ids-0.009
Token family
Token ID1641
Feature activation-9.01e-01

Pos logit contributions
ind+0.018
iring+0.018
 cheaper+0.016
 barking+0.016
 faster+0.016
Neg logit contributions
isel-0.018
pan-0.015
kin-0.015
alk-0.015
ids-0.014
Token had
Token ID550
Feature activation+8.73e-01

Pos logit contributions
iring+0.037
ind+0.035
handed+0.033
 sidelines+0.033
 late+0.031
Neg logit contributions
 lived-0.014
kin-0.012
 can-0.012
ids-0.011
isel-0.011
Token bought
Token ID5839
Feature activation-7.46e-01

Pos logit contributions
isel+0.030
pan+0.027
kin+0.026
ids+0.026
 lived+0.026
Neg logit contributions
iring-0.040
ind-0.040
itating-0.035
handed-0.034
 concession-0.034
Token a
Token ID257
Feature activation+5.42e-01

Pos logit contributions
iring+0.036
ind+0.035
itating+0.033
ich+0.032
shadow+0.032
Neg logit contributions
isel-0.021
pan-0.020
kin-0.020
ids-0.019
 lived-0.019
Token long
Token ID890
Feature activation+8.48e-01

Pos logit contributions
isel+0.017
 imagination+0.017
 idea+0.015
pan+0.015
 tul+0.015
Neg logit contributions
iring-0.026
ind-0.024
handed-0.023
ups-0.021
trained-0.021
Token time
Token ID640
Feature activation-2.13e-01

Pos logit contributions
isel+0.031
pan+0.025
ids+0.024
alk+0.024
kin+0.023
Neg logit contributions
ind-0.036
 barking-0.033
iring-0.033
 cheaper-0.032
 faster-0.032
Token ago
Token ID2084
Feature activation+4.72e+00

Pos logit contributions
ind+0.011
iring+0.011
handed+0.010
 homeless+0.009
 cheaper+0.009
Neg logit contributions
isel-0.006
pan-0.005
ids-0.005
alk-0.005
kin-0.005
Token.
Token ID13
Feature activation+5.57e-02

Pos logit contributions
isel+0.189
pan+0.158
kin+0.154
alk+0.153
ids+0.149
Neg logit contributions
ind-0.191
iring-0.190
handed-0.167
 cheaper-0.166
 barking-0.164
Token They
Token ID1119
Feature activation+4.38e-01

Pos logit contributions
isel+0.001
 It+0.001
ids+0.001
alk+0.001
pan+0.001
Neg logit contributions
ind-0.003
iring-0.003
handed-0.003
 cheaper-0.003
 faster-0.003
Token did
Token ID750
Feature activation-9.01e-02

Pos logit contributions
isel+0.016
pan+0.013
alk+0.013
kin+0.013
ids+0.012
Neg logit contributions
ind-0.019
iring-0.019
 cheaper-0.017
 faster-0.017
 homeless-0.017
Token not
Token ID407
Feature activation-6.76e-01

Pos logit contributions
ind+0.004
iring+0.004
handed+0.003
 homeless+0.003
glers+0.003
Neg logit contributions
isel-0.004
pan-0.003
alk-0.003
ids-0.003
kin-0.003
Token know
Token ID760
Feature activation+1.36e-01

Pos logit contributions
ind+0.037
iring+0.035
 cheaper+0.034
 faster+0.034
 barking+0.034
Neg logit contributions
isel-0.017
pan-0.014
kin-0.013
alk-0.012
ids-0.012
Token furry
Token ID40857
Feature activation+7.32e-01

Pos logit contributions
isel+0.021
kin+0.020
brush+0.019
ids+0.019
aces+0.019
Neg logit contributions
handed-0.034
ind-0.032
iring-0.031
 concession-0.028
itating-0.027
Token,
Token ID11
Feature activation+1.31e-01

Pos logit contributions
isel+0.021
pan+0.017
kin+0.016
alk+0.016
ids+0.016
Neg logit contributions
ind-0.038
iring-0.037
handed-0.035
 homeless-0.034
 cheaper-0.033
Token some
Token ID617
Feature activation+5.04e-01

Pos logit contributions
isel+0.004
pan+0.003
brush+0.003
kin+0.003
aces+0.003
Neg logit contributions
ind-0.007
iring-0.006
handed-0.006
ich-0.006
ll-0.006
Token had
Token ID550
Feature activation+1.19e+00

Pos logit contributions
isel+0.010
kin+0.008
pan+0.008
brush+0.007
 imagination+0.007
Neg logit contributions
ind-0.030
iring-0.030
handed-0.028
ich-0.027
shadow-0.027
Token l
Token ID300
Feature activation-3.26e-01

Pos logit contributions
isel+0.034
aces+0.031
pan+0.030
brush+0.029
ids+0.029
Neg logit contributions
iring-0.060
ind-0.059
handed-0.056
itating-0.054
shadow-0.053
Tokenaces
Token ID2114
Feature activation+4.71e+00

Pos logit contributions
iring+0.020
ind+0.020
 cheaper+0.018
 faster+0.018
handed+0.018
Neg logit contributions
isel-0.006
pan-0.004
alk-0.004
kin-0.004
 imagination-0.003
Token and
Token ID290
Feature activation-7.84e-01

Pos logit contributions
isel+0.149
pan+0.125
alk+0.121
ids+0.121
kin+0.120
Neg logit contributions
ind-0.234
iring-0.223
handed-0.206
 homeless-0.201
 cheaper-0.199
Token some
Token ID617
Feature activation+3.20e-02

Pos logit contributions
ind+0.034
iring+0.034
handed+0.030
 cheaper+0.029
 homeless+0.029
Neg logit contributions
isel-0.029
pan-0.024
kin-0.024
alk-0.023
ids-0.023
Token had
Token ID550
Feature activation+9.75e-01

Pos logit contributions
isel+0.001
aces+0.001
kin+0.001
pan+0.001
brush+0.001
Neg logit contributions
ind-0.002
iring-0.001
handed-0.001
ich-0.001
shadow-0.001
Token buttons
Token ID12163
Feature activation+1.13e+00

Pos logit contributions
isel+0.029
aces+0.027
pan+0.025
brush+0.025
ids+0.025
Neg logit contributions
iring-0.048
ind-0.046
handed-0.043
itating-0.042
shadow-0.041
Token.
Token ID13
Feature activation-1.89e-02

Pos logit contributions
isel+0.034
pan+0.031
ids+0.031
aces+0.030
brush+0.029
Neg logit contributions
ind-0.056
iring-0.054
handed-0.053
 homeless-0.051
 elderly-0.049
Token famous
Token ID5863
Feature activation-1.15e-01

Pos logit contributions
isel+0.003
 idea+0.003
 cuc+0.003
 imagination+0.003
 thank+0.003
Neg logit contributions
iring-0.004
handed-0.004
ind-0.004
ll-0.004
glers-0.004
Token artist
Token ID6802
Feature activation+3.46e-01

Pos logit contributions
iring+0.005
ind+0.005
handed+0.005
itating+0.005
glers+0.005
Neg logit contributions
isel-0.004
 idea-0.003
 imagination-0.003
kin-0.003
 gard-0.003
Token a
Token ID257
Feature activation+2.45e-01

Pos logit contributions
isel+0.014
pan+0.012
kin+0.012
alk+0.012
ids+0.011
Neg logit contributions
ind-0.014
iring-0.014
handed-0.012
 cheaper-0.012
 barking-0.012
Token long
Token ID890
Feature activation+6.56e-01

Pos logit contributions
isel+0.009
 imagination+0.008
 cuc+0.008
 idea+0.008
kin+0.008
Neg logit contributions
iring-0.011
ind-0.010
handed-0.009
glers-0.009
ll-0.009
Token time
Token ID640
Feature activation-3.23e-01

Pos logit contributions
isel+0.025
pan+0.021
ids+0.020
kin+0.020
alk+0.019
Neg logit contributions
ind-0.028
iring-0.026
 barking-0.025
 cheaper-0.024
 faster-0.024
Token ago
Token ID2084
Feature activation+4.70e+00

Pos logit contributions
ind+0.015
iring+0.015
handed+0.013
 cheaper+0.013
 homeless+0.013
Neg logit contributions
isel-0.011
pan-0.009
alk-0.009
ids-0.009
kin-0.009
Token."
Token ID526
Feature activation+1.24e+00

Pos logit contributions
isel+0.206
pan+0.170
alk+0.166
kin+0.165
ids+0.161
Neg logit contributions
ind-0.174
iring-0.172
handed-0.151
 barking-0.149
 cheaper-0.149
Token
Token ID220
Feature activation-4.60e-01

Pos logit contributions
isel+0.053
kin+0.044
pan+0.043
alk+0.038
ids+0.038
Neg logit contributions
iring-0.047
handed-0.046
ind-0.045
 barking-0.045
 new-0.045
Token
Token ID198
Feature activation+2.98e-01

Pos logit contributions
iring+0.020
ind+0.020
handed+0.017
 cheaper+0.017
 barking+0.017
Neg logit contributions
isel-0.017
pan-0.015
kin-0.014
alk-0.014
ids-0.013
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
isel+0.012
pan+0.010
kin+0.010
alk+0.009
ids+0.009
Neg logit contributions
ind-0.012
iring-0.012
handed-0.011
 barking-0.011
 cheaper-0.011
TokenThe
Token ID464
Feature activation+7.49e-02

Pos logit contributions
ind+0.004
iring+0.004
handed+0.004
 cheaper+0.004
 barking+0.004
Neg logit contributions
isel-0.006
pan-0.005
kin-0.005
alk-0.005
ids-0.005
Token it
Token ID340
Feature activation+1.09e-01

Pos logit contributions
iring+0.069
ind+0.068
handed+0.061
 homeless+0.060
 barking+0.060
Neg logit contributions
isel-0.048
pan-0.040
kin-0.038
alk-0.038
ids-0.037
Token away
Token ID1497
Feature activation-3.17e-01

Pos logit contributions
pan+0.004
isel+0.004
kin+0.004
alk+0.003
brush+0.003
Neg logit contributions
ind-0.005
iring-0.005
ica-0.004
 homeless-0.004
ich-0.004
Token a
Token ID257
Feature activation+3.09e-01

Pos logit contributions
ind+0.015
iring+0.015
 barking+0.014
handed+0.014
 homeless+0.014
Neg logit contributions
isel-0.009
kin-0.009
pan-0.009
alk-0.008
aces-0.007
Token long
Token ID890
Feature activation+6.38e-01

Pos logit contributions
isel+0.010
kin+0.009
pan+0.009
 imagination+0.008
 cuc+0.008
Neg logit contributions
iring-0.016
ind-0.014
handed-0.013
ning-0.013
glers-0.013
Token time
Token ID640
Feature activation-2.27e-01

Pos logit contributions
isel+0.026
adders+0.022
aces+0.021
ids+0.021
pan+0.020
Neg logit contributions
ind-0.023
 barking-0.023
 faster-0.022
 cheaper-0.021
 homeless-0.020
Token ago
Token ID2084
Feature activation+4.68e+00

Pos logit contributions
ind+0.011
iring+0.011
handed+0.010
 homeless+0.010
 cheaper+0.010
Neg logit contributions
isel-0.007
pan-0.006
kin-0.006
alk-0.006
ids-0.006
Token.
Token ID13
Feature activation-6.97e-02

Pos logit contributions
isel+0.195
pan+0.161
alk+0.157
kin+0.157
ids+0.153
Neg logit contributions
ind-0.183
iring-0.181
handed-0.160
 cheaper-0.158
 barking-0.157
Token It
Token ID632
Feature activation+1.19e+00

Pos logit contributions
iring+0.003
ind+0.003
 barking+0.002
handed+0.002
 cheaper+0.002
Neg logit contributions
isel-0.003
pan-0.002
alk-0.002
kin-0.002
ids-0.002
Token is
Token ID318
Feature activation-4.76e-02

Pos logit contributions
isel+0.039
pan+0.033
kin+0.031
alk+0.031
ids+0.030
Neg logit contributions
ind-0.057
iring-0.056
handed-0.051
 cheaper-0.049
 homeless-0.049
Token not
Token ID407
Feature activation-4.51e-02

Pos logit contributions
iring+0.002
ind+0.002
handed+0.002
itating+0.002
glers+0.002
Neg logit contributions
isel-0.002
kin-0.002
pan-0.002
 imagination-0.002
 idea-0.002
Token good
Token ID922
Feature activation-8.37e-01

Pos logit contributions
ind+0.002
iring+0.002
handed+0.002
itating+0.002
 concession+0.002
Neg logit contributions
isel-0.002
kin-0.002
pan-0.002
 imagination-0.002
 idea-0.002
Token do
Token ID466
Feature activation-5.68e-01

Pos logit contributions
isel+0.002
pan+0.002
brush+0.002
ids+0.002
kin+0.002
Neg logit contributions
ind-0.003
iring-0.003
 cheaper-0.002
handed-0.002
glers-0.002
Token,
Token ID11
Feature activation+3.20e-01

Pos logit contributions
ind+0.024
iring+0.024
 cheaper+0.020
handed+0.020
 homeless+0.020
Neg logit contributions
isel-0.022
kin-0.019
pan-0.019
alk-0.018
ids-0.018
Token a
Token ID257
Feature activation+9.03e-02

Pos logit contributions
isel+0.010
pan+0.009
 It+0.009
brush+0.009
 lived+0.008
Neg logit contributions
ind-0.016
iring-0.015
handed-0.013
glers-0.013
ll-0.013
Token few
Token ID1178
Feature activation+4.18e-01

Pos logit contributions
isel+0.004
pan+0.003
kin+0.003
 idea+0.003
 imagination+0.003
Neg logit contributions
iring-0.004
ind-0.004
handed-0.003
glers-0.003
itating-0.003
Token days
Token ID1528
Feature activation+1.52e+00

Pos logit contributions
isel+0.017
pan+0.013
kin+0.013
alk+0.013
 imagination+0.013
Neg logit contributions
ind-0.017
iring-0.017
handed-0.015
itating-0.015
 cheaper-0.015
Token ago
Token ID2084
Feature activation+4.66e+00

Pos logit contributions
isel+0.058
pan+0.051
ids+0.048
kin+0.048
alk+0.048
Neg logit contributions
ind-0.066
iring-0.062
 cheaper-0.055
handed-0.054
 nicer-0.053
Token.
Token ID13
Feature activation+4.17e-01

Pos logit contributions
isel+0.178
pan+0.144
alk+0.141
kin+0.138
ids+0.135
Neg logit contributions
iring-0.193
ind-0.192
handed-0.174
 barking-0.173
 faster-0.170
Token He
Token ID679
Feature activation+4.39e-01

Pos logit contributions
isel+0.012
alk+0.009
pan+0.009
ids+0.009
 It+0.009
Neg logit contributions
ind-0.022
iring-0.021
 cheaper-0.019
glers-0.019
 faster-0.019
Token started
Token ID2067
Feature activation-3.00e-02

Pos logit contributions
isel+0.014
pan+0.011
kin+0.011
alk+0.010
 lived+0.010
Neg logit contributions
iring-0.022
ind-0.022
handed-0.020
 cheaper-0.019
 barking-0.019
Token to
Token ID284
Feature activation+8.01e-02

Pos logit contributions
iring+0.001
ind+0.001
handed+0.001
 cheaper+0.001
 homeless+0.001
Neg logit contributions
isel-0.001
pan-0.001
alk-0.001
 imagination-0.001
ids-0.001
Token applaud
Token ID22517
Feature activation-9.16e-01

Pos logit contributions
isel+0.003
pan+0.002
kin+0.002
alk+0.002
ids+0.002
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
 cheaper-0.003
 barking-0.003
Token help
Token ID1037
Feature activation-4.61e-01

Pos logit contributions
isel+0.033
pan+0.026
kin+0.025
alk+0.025
ids+0.024
Neg logit contributions
ind-0.057
iring-0.056
handed-0.051
 cheaper-0.050
 barking-0.050
Token me
Token ID502
Feature activation+1.15e+00

Pos logit contributions
iring+0.016
ind+0.014
handed+0.014
 barking+0.013
Nice+0.013
Neg logit contributions
isel-0.021
pan-0.019
brush-0.018
alk-0.018
kin-0.017
Token with
Token ID351
Feature activation+6.86e-01

Pos logit contributions
isel+0.039
pan+0.033
alk+0.031
brush+0.031
kin+0.031
Neg logit contributions
ind-0.054
iring-0.052
handed-0.046
 barking-0.046
 cheaper-0.045
Token these
Token ID777
Feature activation+3.75e-01

Pos logit contributions
isel+0.030
pan+0.027
 imagination+0.025
ids+0.025
kin+0.025
Neg logit contributions
iring-0.027
ind-0.024
handed-0.022
itating-0.022
glers-0.021
Token l
Token ID300
Feature activation-2.72e-01

Pos logit contributions
isel+0.012
pan+0.010
kin+0.010
alk+0.010
brush+0.010
Neg logit contributions
ind-0.018
iring-0.017
 barking-0.016
handed-0.016
 faster-0.015
Tokenaces
Token ID2114
Feature activation+4.65e+00

Pos logit contributions
iring+0.014
ind+0.014
handed+0.013
 cheaper+0.013
 elderly+0.013
Neg logit contributions
isel-0.008
pan-0.006
alk-0.005
 nod-0.005
 lived-0.005
Token?"
Token ID1701
Feature activation+8.59e-01

Pos logit contributions
isel+0.147
pan+0.127
alk+0.122
kin+0.122
brush+0.117
Neg logit contributions
ind-0.226
iring-0.218
handed-0.200
 barking-0.199
 cheaper-0.192
Token Sarah
Token ID10490
Feature activation-7.97e-01

Pos logit contributions
isel+0.030
pan+0.025
 It+0.024
 imagination+0.024
alk+0.023
Neg logit contributions
ind-0.040
iring-0.038
handed-0.033
ich-0.033
 cheaper-0.033
Token asked
Token ID1965
Feature activation+1.25e+00

Pos logit contributions
ind+0.030
iring+0.030
handed+0.026
 cheaper+0.026
 barking+0.025
Neg logit contributions
isel-0.034
pan-0.029
kin-0.029
alk-0.028
ids-0.028
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
isel+0.044
pan+0.037
kin+0.036
ids+0.035
alk+0.035
Neg logit contributions
ind-0.057
iring-0.055
handed-0.049
 cheaper-0.048
 homeless-0.048
Token
Token ID198
Feature activation+3.63e-01

Pos logit contributions
isel+0.014
pan+0.012
kin+0.012
alk+0.011
ids+0.011
Neg logit contributions
iring-0.015
ind-0.015
handed-0.013
 barking-0.013
 cheaper-0.013
Token colorful
Token ID20239
Feature activation+7.08e-01

Pos logit contributions
isel+0.009
 cuc+0.008
 idea+0.008
kin+0.008
brush+0.008
Neg logit contributions
ind-0.011
ich-0.010
iring-0.010
itating-0.010
ica-0.010
Token sk
Token ID1341
Feature activation+6.33e-01

Pos logit contributions
isel+0.030
pan+0.027
 cuc+0.026
kin+0.026
brush+0.025
Neg logit contributions
ind-0.026
iring-0.026
handed-0.023
itating-0.022
ich-0.022
Tokenates
Token ID689
Feature activation+6.63e-01

Pos logit contributions
isel+0.029
pan+0.024
alk+0.024
kin+0.023
 imagination+0.023
Neg logit contributions
ind-0.023
iring-0.022
handed-0.020
 cheaper-0.018
 barking-0.018
Token with
Token ID351
Feature activation+6.25e-01

Pos logit contributions
isel+0.020
pan+0.019
kin+0.019
ids+0.017
aces+0.017
Neg logit contributions
ind-0.033
iring-0.031
handed-0.029
 barking-0.028
 homeless-0.027
Token l
Token ID300
Feature activation-2.99e-01

Pos logit contributions
isel+0.020
 cuc+0.017
pan+0.017
 imagination+0.016
 It+0.016
Neg logit contributions
iring-0.031
ind-0.030
ich-0.028
handed-0.028
itating-0.027
Tokenaces
Token ID2114
Feature activation+4.64e+00

Pos logit contributions
ind+0.016
iring+0.016
 cheaper+0.014
handed+0.014
 faster+0.014
Neg logit contributions
isel-0.008
pan-0.006
alk-0.006
kin-0.006
 imagination-0.006
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
isel+0.139
pan+0.129
aces+0.122
ids+0.121
kin+0.119
Neg logit contributions
ind-0.230
iring-0.216
handed-0.194
 barking-0.194
 concession-0.193
Token
Token ID198
Feature activation-3.50e-01

Pos logit contributions
isel+0.005
pan+0.004
alk+0.004
kin+0.004
ids+0.004
Neg logit contributions
ind-0.006
iring-0.005
handed-0.005
 cheaper-0.005
 faster-0.005
Token
Token ID198
Feature activation-7.02e-01

Pos logit contributions
ind+0.019
iring+0.018
 cheaper+0.016
 homeless+0.016
handed+0.016
Neg logit contributions
isel-0.010
alk-0.008
pan-0.008
kin-0.007
ids-0.007
TokenOn
Token ID2202
Feature activation-6.91e-01

Pos logit contributions
ind+0.026
iring+0.025
handed+0.022
 cheaper+0.022
 barking+0.021
Neg logit contributions
isel-0.031
pan-0.027
kin-0.026
alk-0.026
ids-0.025
Token the
Token ID262
Feature activation-4.92e-01

Pos logit contributions
ind+0.034
iring+0.033
handed+0.029
ich+0.028
 barking+0.028
Neg logit contributions
isel-0.023
pan-0.020
kin-0.020
alk-0.018
ids-0.017
Token velvet
Token ID47750
Feature activation+1.32e+00

Pos logit contributions
iring+0.000
ind+0.000
glers+0.000
 barking+0.000
shadow+0.000
Neg logit contributions
isel-0.000
 imagination-0.000
 idea-0.000
kin-0.000
pan-0.000
Token box
Token ID3091
Feature activation+1.81e-01

Pos logit contributions
isel+0.043
pan+0.040
kin+0.039
alk+0.037
brush+0.036
Neg logit contributions
iring-0.060
ind-0.060
handed-0.053
 cheaper-0.053
 barking-0.052
Token all
Token ID477
Feature activation-3.26e-01

Pos logit contributions
pan+0.004
kin+0.004
isel+0.004
brush+0.004
 lived+0.004
Neg logit contributions
ind-0.010
iring-0.009
handed-0.008
Nice-0.008
 homeless-0.008
Token those
Token ID883
Feature activation-5.10e-01

Pos logit contributions
ind+0.016
iring+0.016
ich+0.015
ograph+0.014
 homeless+0.014
Neg logit contributions
isel-0.009
 lived-0.009
alk-0.008
pan-0.008
 idea-0.008
Token years
Token ID812
Feature activation+1.15e+00

Pos logit contributions
ind+0.021
 barking+0.021
iring+0.020
ich+0.020
handed+0.020
Neg logit contributions
 lived-0.017
isel-0.016
aces-0.016
 imagination-0.016
kin-0.015
Token ago
Token ID2084
Feature activation+4.64e+00

Pos logit contributions
isel+0.036
kin+0.031
alk+0.031
pan+0.031
ids+0.030
Neg logit contributions
iring-0.052
ind-0.050
handed-0.049
 barking-0.048
itating-0.047
Token.
Token ID13
Feature activation+4.19e-01

Pos logit contributions
isel+0.189
pan+0.159
kin+0.155
alk+0.154
ids+0.150
Neg logit contributions
ind-0.185
iring-0.183
handed-0.161
 cheaper-0.160
 barking-0.157
Token They
Token ID1119
Feature activation+7.32e-01

Pos logit contributions
isel+0.013
pan+0.010
alk+0.010
kin+0.009
ids+0.009
Neg logit contributions
ind-0.022
iring-0.021
handed-0.019
 cheaper-0.019
 barking-0.019
Token were
Token ID547
Feature activation+2.47e-01

Pos logit contributions
isel+0.025
pan+0.020
kin+0.020
alk+0.020
ids+0.019
Neg logit contributions
ind-0.034
iring-0.034
handed-0.030
 cheaper-0.030
 barking-0.030
Token glad
Token ID9675
Feature activation-3.06e-01

Pos logit contributions
isel+0.009
 lived+0.008
pan+0.008
kin+0.008
 imagination+0.008
Neg logit contributions
ind-0.010
iring-0.010
handed-0.009
 cheaper-0.009
glers-0.008
Token that
Token ID326
Feature activation+1.84e-01

Pos logit contributions
ind+0.016
handed+0.015
iring+0.014
 fastest+0.014
icycle+0.014
Neg logit contributions
isel-0.008
 imagination-0.008
 It-0.007
 lived-0.007
 can-0.007
Token who
Token ID508
Feature activation-9.87e-01

Pos logit contributions
isel+0.005
pan+0.004
alk+0.004
ids+0.004
 lived+0.004
Neg logit contributions
ind-0.012
iring-0.012
handed-0.011
 cheaper-0.011
 barking-0.011
Token own
Token ID898
Feature activation-1.37e+00

Pos logit contributions
iring+0.054
ind+0.053
 cheaper+0.049
 faster+0.048
 barking+0.048
Neg logit contributions
isel-0.026
alk-0.018
pan-0.018
 lived-0.018
 imagination-0.018
Token it
Token ID340
Feature activation-7.59e-02

Pos logit contributions
iring+0.061
ind+0.059
handed+0.053
 cheaper+0.053
 faster+0.053
Neg logit contributions
isel-0.048
pan-0.041
 lived-0.041
 imagination-0.040
alk-0.039
Token don
Token ID836
Feature activation+1.56e+00

Pos logit contributions
ind+0.004
iring+0.004
handed+0.004
 homeless+0.004
 cheaper+0.003
Neg logit contributions
 lived-0.002
isel-0.002
 can-0.002
 are-0.002
 imagination-0.002
Token't
Token ID470
Feature activation-5.67e-01

Pos logit contributions
isel+0.075
pan+0.065
kin+0.064
alk+0.064
ids+0.062
Neg logit contributions
ind-0.051
iring-0.050
handed-0.043
 cheaper-0.042
 barking-0.042
Token actually
Token ID1682
Feature activation-3.93e+00

Pos logit contributions
iring+0.035
ind+0.034
ning+0.031
handed+0.031
 concession+0.031
Neg logit contributions
isel-0.012
alk-0.009
 understand-0.008
kin-0.008
 idea-0.008
Token live
Token ID2107
Feature activation-7.81e-01

Pos logit contributions
iring+0.227
ind+0.223
handed+0.195
ich+0.194
itating+0.193
Neg logit contributions
isel-0.099
 imagination-0.077
alk-0.077
 lived-0.073
kin-0.072
Token there
Token ID612
Feature activation+7.83e-01

Pos logit contributions
iring+0.033
ind+0.032
 sidelines+0.031
handed+0.031
 barking+0.030
Neg logit contributions
isel-0.025
pan-0.024
kin-0.024
alk-0.023
ids-0.022
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
pan+0.017
isel+0.017
alk+0.017
 imagination+0.016
kin+0.016
Neg logit contributions
ind-0.041
iring-0.041
handed-0.037
ich-0.036
 homeless-0.036
Token They
Token ID1119
Feature activation+3.84e-01

Pos logit contributions
ind+0.007
iring+0.007
handed+0.006
 cheaper+0.006
 barking+0.006
Neg logit contributions
isel-0.003
pan-0.003
kin-0.003
alk-0.003
ids-0.002
Token hate
Token ID5465
Feature activation-3.92e-01

Pos logit contributions
isel+0.009
pan+0.007
alk+0.006
kin+0.006
ids+0.006
Neg logit contributions
ind-0.022
iring-0.022
handed-0.020
 barking-0.019
 cheaper-0.019
Token couldn
Token ID3521
Feature activation+8.07e-01

Pos logit contributions
ind+0.010
iring+0.010
handed+0.009
 cheaper+0.009
 barking+0.009
Neg logit contributions
isel-0.005
pan-0.004
kin-0.004
alk-0.004
ids-0.004
Tokenâ
Token ID22940
Feature activation-1.09e+00

Pos logit contributions
isel+0.029
pan+0.025
alk+0.024
kin+0.023
ids+0.023
Neg logit contributions
ind-0.036
iring-0.036
 cheaper-0.031
handed-0.031
 barking-0.031
Token
Token ID26391
Feature activation-1.09e-01

Pos logit contributions
ind+0.046
iring+0.045
handed+0.043
 cheaper+0.041
 faster+0.040
Neg logit contributions
isel-0.041
pan-0.035
kin-0.033
ids-0.032
 cuc-0.032
Token
Token ID8151
Feature activation+4.92e-01

Pos logit contributions
ind+0.005
iring+0.005
 cheaper+0.004
 faster+0.004
 nicer+0.004
Neg logit contributions
isel-0.004
ids-0.003
pan-0.003
alk-0.003
kin-0.003
Tokent
Token ID83
Feature activation-6.59e-01

Pos logit contributions
isel+0.013
ids+0.013
pan+0.012
brush+0.012
kin+0.012
Neg logit contributions
ind-0.025
iring-0.023
 nicer-0.022
 cheaper-0.021
 elderly-0.021
Token actually
Token ID1682
Feature activation-3.78e+00

Pos logit contributions
ind+0.032
iring+0.032
handed+0.029
 cheaper+0.029
 barking+0.028
Neg logit contributions
isel-0.021
pan-0.017
kin-0.016
alk-0.016
ids-0.016
Token hide
Token ID7808
Feature activation-1.43e-01

Pos logit contributions
ind+0.188
iring+0.187
handed+0.169
 cheaper+0.168
 barking+0.166
Neg logit contributions
isel-0.116
pan-0.093
kin-0.089
alk-0.088
ids-0.085
Token in
Token ID287
Feature activation+7.29e-01

Pos logit contributions
iring+0.006
ind+0.006
handed+0.005
glers+0.005
 barking+0.005
Neg logit contributions
isel-0.005
pan-0.005
kin-0.005
ids-0.004
alk-0.004
Token it
Token ID340
Feature activation-1.36e-01

Pos logit contributions
isel+0.025
pan+0.023
 imagination+0.022
alk+0.022
kin+0.021
Neg logit contributions
iring-0.033
ind-0.031
ich-0.029
ll-0.029
glers-0.029
Token like
Token ID588
Feature activation+3.06e-01

Pos logit contributions
ind+0.007
iring+0.007
ich+0.006
 homeless+0.006
 barking+0.006
Neg logit contributions
isel-0.004
pan-0.004
alk-0.004
kin-0.003
aces-0.003
Token she
Token ID673
Feature activation-8.36e-01

Pos logit contributions
isel+0.011
 imagination+0.010
pan+0.010
 lived+0.010
kin+0.010
Neg logit contributions
iring-0.013
ind-0.012
itating-0.011
handed-0.011
glers-0.011
Token see
Token ID766
Feature activation-8.02e-01

Pos logit contributions
iring+0.037
 elderly+0.036
 faster+0.035
 new+0.035
ind+0.034
Neg logit contributions
isel-0.040
kin-0.037
pan-0.037
ids-0.036
pter-0.034
Token what
Token ID644
Feature activation-6.63e-01

Pos logit contributions
ind+0.037
iring+0.036
handed+0.034
glers+0.032
 homeless+0.032
Neg logit contributions
isel-0.028
pan-0.022
 imagination-0.020
 lived-0.020
alk-0.020
Token was
Token ID373
Feature activation-1.27e-01

Pos logit contributions
ind+0.031
iring+0.031
handed+0.028
 homeless+0.027
 cheaper+0.027
Neg logit contributions
isel-0.022
pan-0.018
kin-0.018
 lived-0.017
alk-0.017
Token on
Token ID319
Feature activation-6.24e-01

Pos logit contributions
ind+0.005
iring+0.005
handed+0.005
 homeless+0.004
 cheaper+0.004
Neg logit contributions
isel-0.005
pan-0.004
alk-0.004
kin-0.004
ids-0.004
Token the
Token ID262
Feature activation-1.21e+00

Pos logit contributions
ind+0.025
iring+0.024
handed+0.021
 cheaper+0.021
 barking+0.021
Neg logit contributions
isel-0.026
pan-0.022
kin-0.021
alk-0.021
ids-0.021
Token other
Token ID584
Feature activation-3.51e+00

Pos logit contributions
ind+0.050
iring+0.048
handed+0.045
 cheaper+0.043
 barking+0.042
Neg logit contributions
isel-0.047
pan-0.040
alk-0.039
kin-0.038
 idea-0.037
Token side
Token ID1735
Feature activation-1.17e+00

Pos logit contributions
iring+0.112
ind+0.111
 faster+0.094
 barking+0.093
handed+0.093
Neg logit contributions
isel-0.174
pan-0.152
kin-0.149
alk-0.146
ids-0.144
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
ind+0.069
iring+0.060
 homeless+0.060
handed+0.058
ograph+0.056
Neg logit contributions
isel-0.029
alk-0.023
kin-0.023
pan-0.022
aces-0.022
Token So
Token ID1406
Feature activation-9.50e-01

Pos logit contributions
ind+0.007
iring+0.006
handed+0.006
 cheaper+0.006
 barking+0.006
Neg logit contributions
isel-0.005
pan-0.005
kin-0.004
alk-0.004
ids-0.004
Token,
Token ID11
Feature activation+4.73e-02

Pos logit contributions
iring+0.047
ind+0.047
 barking+0.043
 faster+0.042
 cheaper+0.042
Neg logit contributions
isel-0.030
pan-0.024
alk-0.023
kin-0.022
ids-0.022
Token Spot
Token ID15899
Feature activation-8.50e-01

Pos logit contributions
isel+0.002
kin+0.002
 lived+0.002
pan+0.002
 It+0.002
Neg logit contributions
ind-0.002
iring-0.002
handed-0.002
 cheaper-0.002
 homeless-0.002
Token you
Token ID345
Feature activation+1.02e+00

Pos logit contributions
ind+0.048
iring+0.045
handed+0.044
king+0.040
 destination+0.040
Neg logit contributions
isel-0.058
 imagination-0.052
 cuc-0.051
 lived-0.051
ily-0.050
Token not
Token ID407
Feature activation-3.49e-01

Pos logit contributions
isel+0.039
pan+0.038
alk+0.035
 imagination+0.035
kin+0.034
Neg logit contributions
iring-0.037
ind-0.037
handed-0.035
ups-0.034
 cheaper-0.034
Token playing
Token ID2712
Feature activation-2.89e-01

Pos logit contributions
iring+0.012
ind+0.012
handed+0.011
 concession+0.010
glers+0.010
Neg logit contributions
isel-0.016
alk-0.014
pan-0.013
kin-0.013
 imagination-0.013
Token on
Token ID319
Feature activation-7.84e-01

Pos logit contributions
ind+0.010
iring+0.010
handed+0.009
 cheaper+0.009
 homeless+0.009
Neg logit contributions
isel-0.013
kin-0.011
pan-0.011
alk-0.011
ids-0.011
Token the
Token ID262
Feature activation-1.50e+00

Pos logit contributions
iring+0.039
ind+0.037
king+0.034
ll+0.033
itating+0.033
Neg logit contributions
isel-0.022
alk-0.021
pan-0.020
 imagination-0.019
 lived-0.018
Token other
Token ID584
Feature activation-3.45e+00

Pos logit contributions
iring+0.068
ind+0.065
handed+0.061
 homeless+0.059
 cheaper+0.058
Neg logit contributions
isel-0.046
alk-0.042
 imagination-0.041
 lived-0.041
kin-0.041
Token side
Token ID1735
Feature activation-1.20e+00

Pos logit contributions
iring+0.138
ind+0.137
handed+0.124
 homeless+0.123
 cheaper+0.123
Neg logit contributions
isel-0.131
alk-0.114
kin-0.111
pan-0.108
 imagination-0.108
Token of
Token ID286
Feature activation-1.54e+00

Pos logit contributions
ind+0.062
iring+0.060
 homeless+0.056
handed+0.055
 security+0.054
Neg logit contributions
isel-0.031
alk-0.030
kin-0.027
pan-0.027
brush-0.025
Token the
Token ID262
Feature activation-4.67e-01

Pos logit contributions
iring+0.081
ind+0.079
ll+0.072
king+0.071
 cheaper+0.070
Neg logit contributions
isel-0.043
alk-0.040
pan-0.037
 imagination-0.036
kin-0.032
Token tunnel
Token ID13275
Feature activation-5.29e-01

Pos logit contributions
iring+0.024
ind+0.022
handed+0.021
 homeless+0.021
king+0.021
Neg logit contributions
isel-0.013
alk-0.012
 imagination-0.011
 lived-0.010
 idea-0.010
Token?"
Token ID1701
Feature activation+1.19e+00

Pos logit contributions
ind+0.028
iring+0.027
Mrs+0.024
 homeless+0.024
Nice+0.024
Neg logit contributions
pan-0.014
isel-0.013
alk-0.013
 can-0.012
kin-0.011
Token grandmother
Token ID18410
Feature activation-6.64e-01

Pos logit contributions
ind+0.009
iring+0.009
shadow+0.009
Nice+0.008
 sidelines+0.008
Neg logit contributions
 idea-0.007
 imagination-0.006
kin-0.005
alk-0.005
aces-0.005
Token who
Token ID508
Feature activation-7.95e-01

Pos logit contributions
ind+0.035
iring+0.034
ich+0.029
Nice+0.029
handed+0.028
Neg logit contributions
 idea-0.017
isel-0.016
pan-0.016
ids-0.016
 are-0.016
Token lived
Token ID5615
Feature activation+8.54e-01

Pos logit contributions
ind+0.048
iring+0.047
handed+0.042
king+0.042
 faster+0.041
Neg logit contributions
 lived-0.017
isel-0.015
kin-0.012
 can-0.012
 are-0.011
Token on
Token ID319
Feature activation-4.15e-01

Pos logit contributions
kin+0.024
isel+0.022
ily+0.021
pan+0.020
alk+0.020
Neg logit contributions
iring-0.038
ind-0.037
 sidelines-0.036
handed-0.035
 cheaper-0.035
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
iring+0.024
ll+0.022
ind+0.022
itating+0.021
shadow+0.021
Neg logit contributions
alk-0.008
 imagination-0.008
isel-0.008
pan-0.008
 lived-0.007
Token other
Token ID584
Feature activation-3.44e+00

Pos logit contributions
iring+0.047
ind+0.045
shadow+0.040
 cheaper+0.040
 barking+0.039
Neg logit contributions
isel-0.036
alk-0.033
pan-0.032
kin-0.031
 imagination-0.031
Token side
Token ID1735
Feature activation-1.07e+00

Pos logit contributions
ind+0.128
iring+0.126
handed+0.110
 cheaper+0.108
 barking+0.107
Neg logit contributions
isel-0.152
pan-0.129
kin-0.126
alk-0.125
ids-0.122
Token of
Token ID286
Feature activation-1.45e+00

Pos logit contributions
ind+0.061
iring+0.058
 homeless+0.054
 cheaper+0.052
shadow+0.052
Neg logit contributions
isel-0.022
kin-0.022
alk-0.022
ily-0.021
ids-0.021
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
iring+0.075
ind+0.071
ll+0.065
itating+0.065
 cheaper+0.064
Neg logit contributions
isel-0.041
alk-0.037
pan-0.037
 imagination-0.034
kin-0.033
Token wall
Token ID3355
Feature activation+1.08e+00

Pos logit contributions
iring+0.012
ind+0.011
 cheaper+0.010
shadow+0.010
handed+0.010
Neg logit contributions
isel-0.010
alk-0.009
 imagination-0.009
pan-0.009
kin-0.009
Token.
Token ID13
Feature activation-8.16e-02

Pos logit contributions
isel+0.027
pan+0.026
alk+0.025
kin+0.024
aces+0.024
Neg logit contributions
ind-0.059
iring-0.057
 homeless-0.051
ich-0.050
 cheaper-0.049
Token even
Token ID772
Feature activation+2.24e-01

Pos logit contributions
isel+0.025
 imagination+0.022
 It+0.021
brush+0.021
pan+0.020
Neg logit contributions
ind-0.040
iring-0.038
handed-0.035
glers-0.034
itating-0.032
Token though
Token ID996
Feature activation+2.00e+00

Pos logit contributions
isel+0.006
 cuc+0.005
kin+0.004
pan+0.004
 imagination+0.004
Neg logit contributions
ind-0.012
iring-0.011
handed-0.011
ich-0.011
 destination-0.010
Token he
Token ID339
Feature activation-1.04e+00

Pos logit contributions
isel+0.058
 lived+0.052
kin+0.052
 imagination+0.050
alk+0.047
Neg logit contributions
ind-0.099
iring-0.094
handed-0.090
 cheaper-0.084
itating-0.084
Token did
Token ID750
Feature activation+3.89e-01

Pos logit contributions
iring+0.059
ind+0.057
 cheaper+0.052
handed+0.051
 ours+0.051
Neg logit contributions
isel-0.025
 lived-0.022
kin-0.020
 imagination-0.018
 can-0.018
Token not
Token ID407
Feature activation-4.91e-01

Pos logit contributions
isel+0.013
pan+0.011
 imagination+0.011
alk+0.011
brush+0.010
Neg logit contributions
ind-0.018
iring-0.018
handed-0.016
ich-0.016
glers-0.015
Token actually
Token ID1682
Feature activation-3.44e+00

Pos logit contributions
ind+0.026
iring+0.025
handed+0.023
 cheaper+0.023
 barking+0.022
Neg logit contributions
isel-0.014
pan-0.011
alk-0.011
kin-0.011
ids-0.010
Token win
Token ID1592
Feature activation-1.57e+00

Pos logit contributions
ind+0.178
iring+0.177
handed+0.152
ich+0.150
 cheaper+0.149
Neg logit contributions
isel-0.108
alk-0.081
kin-0.081
 imagination-0.079
pan-0.078
Token the
Token ID262
Feature activation-3.87e-01

Pos logit contributions
ind+0.078
iring+0.075
ich+0.068
 concession+0.067
handed+0.067
Neg logit contributions
isel-0.047
aces-0.041
alk-0.041
kin-0.041
 lived-0.038
Token competition
Token ID5449
Feature activation-7.25e-01

Pos logit contributions
iring+0.018
ind+0.018
handed+0.015
 barking+0.015
glers+0.015
Neg logit contributions
isel-0.013
kin-0.011
 imagination-0.011
 idea-0.011
alk-0.011
Token.
Token ID13
Feature activation+4.32e-01

Pos logit contributions
ind+0.040
iring+0.037
 homeless+0.032
ich+0.032
handed+0.032
Neg logit contributions
isel-0.019
pan-0.017
 idea-0.017
 lived-0.017
aces-0.017
Token<|endoftext|>
Token ID50256
Feature activation-1.28e+00

Pos logit contributions
isel+0.014
alk+0.011
pan+0.010
kin+0.010
ids+0.010
Neg logit contributions
ind-0.022
iring-0.021
 cheaper-0.019
 faster-0.019
handed-0.019
Token saw
Token ID2497
Feature activation-2.21e-01

Pos logit contributions
ind+0.001
iring+0.001
 barking+0.001
 faster+0.001
handed+0.001
Neg logit contributions
isel-0.001
pan-0.001
alk-0.001
kin-0.001
ids-0.001
Token a
Token ID257
Feature activation-2.30e-01

Pos logit contributions
ind+0.009
iring+0.009
handed+0.008
 cheaper+0.008
 barking+0.008
Neg logit contributions
isel-0.008
pan-0.007
kin-0.007
alk-0.007
ids-0.007
Token cat
Token ID3797
Feature activation+4.28e-01

Pos logit contributions
iring+0.010
ind+0.009
handed+0.009
ups+0.008
shadow+0.008
Neg logit contributions
isel-0.008
kin-0.008
 gard-0.007
 idea-0.007
pan-0.007
Token on
Token ID319
Feature activation-3.33e-01

Pos logit contributions
isel+0.016
pan+0.014
kin+0.014
alk+0.014
ids+0.013
Neg logit contributions
iring-0.018
ind-0.018
 cheaper-0.016
handed-0.015
 homeless-0.015
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
iring+0.015
ind+0.015
handed+0.013
 cheaper+0.013
 homeless+0.013
Neg logit contributions
isel-0.012
pan-0.010
alk-0.010
kin-0.010
ids-0.009
Token other
Token ID584
Feature activation-3.42e+00

Pos logit contributions
iring+0.066
ind+0.063
shadow+0.059
 cheaper+0.058
handed+0.057
Neg logit contributions
pan-0.035
isel-0.034
alk-0.034
 gard-0.033
brush-0.032
Token side
Token ID1735
Feature activation-1.09e+00

Pos logit contributions
ind+0.124
iring+0.123
handed+0.106
 cheaper+0.105
 barking+0.103
Neg logit contributions
isel-0.152
pan-0.131
kin-0.128
alk-0.128
ids-0.125
Token of
Token ID286
Feature activation-1.76e+00

Pos logit contributions
ind+0.055
iring+0.052
 homeless+0.049
 cheaper+0.049
handed+0.047
Neg logit contributions
isel-0.033
alk-0.029
kin-0.028
pan-0.026
ids-0.026
Token a
Token ID257
Feature activation-5.33e-02

Pos logit contributions
iring+0.093
ind+0.092
ll+0.087
itating+0.085
 cheaper+0.082
Neg logit contributions
isel-0.045
pan-0.040
alk-0.038
 It-0.036
 soil-0.036
Token wire
Token ID6503
Feature activation-1.44e-01

Pos logit contributions
iring+0.003
ind+0.002
handed+0.002
shadow+0.002
glers+0.002
Neg logit contributions
isel-0.002
pan-0.001
brush-0.001
alk-0.001
kin-0.001
Token fence
Token ID13990
Feature activation+2.29e-01

Pos logit contributions
ind+0.007
iring+0.007
handed+0.006
 cheaper+0.006
 homeless+0.006
Neg logit contributions
isel-0.004
pan-0.004
kin-0.004
alk-0.004
 lived-0.004
Token know
Token ID760
Feature activation+3.10e-01

Pos logit contributions
ind+0.037
iring+0.036
handed+0.034
 elderly+0.033
 barking+0.033
Neg logit contributions
isel-0.033
pan-0.028
kin-0.027
ids-0.026
alk-0.025
Token what
Token ID644
Feature activation-7.44e-01

Pos logit contributions
isel+0.009
pan+0.008
 lived+0.008
 imagination+0.007
brush+0.007
Neg logit contributions
ind-0.015
handed-0.014
iring-0.014
 barking-0.013
ich-0.013
Token was
Token ID373
Feature activation-6.65e-02

Pos logit contributions
ind+0.029
iring+0.029
handed+0.025
 cheaper+0.025
 barking+0.024
Neg logit contributions
isel-0.031
pan-0.027
kin-0.026
alk-0.026
ids-0.025
Token on
Token ID319
Feature activation-4.85e-01

Pos logit contributions
iring+0.003
ind+0.003
handed+0.003
 concession+0.003
 sidelines+0.003
Neg logit contributions
isel-0.002
pan-0.002
aces-0.002
ids-0.002
ily-0.002
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
iring+0.021
ind+0.021
handed+0.019
 barking+0.018
ll+0.018
Neg logit contributions
isel-0.017
pan-0.015
alk-0.015
kin-0.014
 imagination-0.014
Token other
Token ID584
Feature activation-3.42e+00

Pos logit contributions
shadow+0.053
awed+0.049
iring+0.048
ounce+0.046
 arrested+0.046
Neg logit contributions
 gard-0.033
 idea-0.031
 soil-0.030
 cuc-0.030
 tul-0.029
Token side
Token ID1735
Feature activation-1.10e+00

Pos logit contributions
iring+0.150
ind+0.147
 cheaper+0.134
shadow+0.132
handed+0.132
Neg logit contributions
isel-0.111
 imagination-0.099
kin-0.099
alk-0.098
ids-0.097
Token of
Token ID286
Feature activation-1.46e+00

Pos logit contributions
ind+0.062
iring+0.056
 homeless+0.054
handed+0.053
 concession+0.052
Neg logit contributions
isel-0.024
brush-0.023
ids-0.023
alk-0.023
kin-0.023
Token the
Token ID262
Feature activation-4.43e-01

Pos logit contributions
iring+0.071
ind+0.070
handed+0.061
ll+0.060
 cheaper+0.060
Neg logit contributions
isel-0.047
pan-0.041
alk-0.040
kin-0.038
 imagination-0.038
Token big
Token ID1263
Feature activation-8.54e-02

Pos logit contributions
shadow+0.021
iring+0.020
king+0.020
awed+0.019
 arrested+0.019
Neg logit contributions
 imagination-0.012
isel-0.012
 soil-0.011
alk-0.011
 idea-0.011
Token door
Token ID3420
Feature activation+1.54e-01

Pos logit contributions
ind+0.003
iring+0.003
handed+0.003
 cheaper+0.003
 homeless+0.003
Neg logit contributions
isel-0.003
pan-0.003
alk-0.003
kin-0.003
ids-0.003
Token who
Token ID508
Feature activation-1.18e+00

Pos logit contributions
isel+0.008
kin+0.007
 lived+0.007
pan+0.007
alk+0.007
Neg logit contributions
iring-0.013
ind-0.013
handed-0.011
 cheaper-0.011
 homeless-0.011
Token never
Token ID1239
Feature activation-4.55e-01

Pos logit contributions
iring+0.064
ind+0.063
 cheaper+0.058
handed+0.056
 homeless+0.056
Neg logit contributions
isel-0.032
 lived-0.025
 imagination-0.025
alk-0.024
ids-0.023
Token explores
Token ID25409
Feature activation-1.11e+00

Pos logit contributions
ind+0.024
iring+0.024
handed+0.021
 cheaper+0.021
ich+0.020
Neg logit contributions
isel-0.013
alk-0.010
pan-0.010
 imagination-0.010
kin-0.010
Token will
Token ID481
Feature activation-7.97e-01

Pos logit contributions
iring+0.049
ind+0.049
handed+0.045
 homeless+0.043
 cheaper+0.043
Neg logit contributions
isel-0.036
alk-0.035
pan-0.031
 lived-0.031
 imagination-0.031
Token never
Token ID1239
Feature activation-1.22e-01

Pos logit contributions
ind+0.039
iring+0.039
 cheaper+0.034
handed+0.034
 homeless+0.033
Neg logit contributions
isel-0.024
alk-0.022
pan-0.021
kin-0.020
ids-0.019
Token truly
Token ID4988
Feature activation-3.42e+00

Pos logit contributions
ind+0.006
iring+0.006
handed+0.006
 concession+0.005
 cheaper+0.005
Neg logit contributions
isel-0.003
alk-0.003
 understand-0.003
 nod-0.003
 idea-0.003
Token know
Token ID760
Feature activation+2.08e-01

Pos logit contributions
ind+0.169
iring+0.167
 cheaper+0.149
handed+0.149
 barking+0.147
Neg logit contributions
isel-0.108
pan-0.085
alk-0.084
kin-0.083
ids-0.079
Token what
Token ID644
Feature activation-4.57e-01

Pos logit contributions
isel+0.007
pan+0.006
 imagination+0.006
 lived+0.006
aces+0.006
Neg logit contributions
ind-0.009
iring-0.009
handed-0.008
glers-0.008
 barking-0.008
Token is
Token ID318
Feature activation-1.04e-01

Pos logit contributions
ind+0.019
iring+0.018
handed+0.016
 cheaper+0.016
 homeless+0.016
Neg logit contributions
isel-0.018
alk-0.015
pan-0.015
 imagination-0.015
kin-0.015
Token around
Token ID1088
Feature activation+5.69e-01

Pos logit contributions
ind+0.004
iring+0.004
handed+0.004
glers+0.004
 concession+0.004
Neg logit contributions
isel-0.004
pan-0.003
 imagination-0.003
alk-0.003
kin-0.003
Token him
Token ID683
Feature activation-2.06e-01

Pos logit contributions
isel+0.026
alk+0.024
 lived+0.023
pan+0.023
 imagination+0.023
Neg logit contributions
iring-0.018
ind-0.017
 cheaper-0.017
handed-0.015
 homeless-0.015
Token big
Token ID1263
Feature activation+4.15e-01

Pos logit contributions
iring+0.004
ind+0.004
handed+0.003
ups+0.003
shadow+0.003
Neg logit contributions
isel-0.003
kin-0.003
 cuc-0.003
 gard-0.003
 idea-0.003
Token banana
Token ID25996
Feature activation+2.58e-02

Pos logit contributions
isel+0.015
pan+0.012
kin+0.012
alk+0.012
 imagination+0.011
Neg logit contributions
iring-0.019
ind-0.019
handed-0.017
 cheaper-0.016
 faster-0.016
Token tree
Token ID5509
Feature activation+5.51e-01

Pos logit contributions
isel+0.001
pan+0.001
kin+0.001
alk+0.001
ids+0.001
Neg logit contributions
ind-0.001
iring-0.001
handed-0.001
 cheaper-0.001
 homeless-0.001
Token on
Token ID319
Feature activation-1.52e-01

Pos logit contributions
isel+0.019
alk+0.017
pan+0.017
kin+0.017
 lived+0.016
Neg logit contributions
ind-0.023
iring-0.022
 cheaper-0.021
handed-0.021
 concession-0.020
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
ind+0.007
iring+0.007
 cheaper+0.006
handed+0.006
 homeless+0.006
Neg logit contributions
isel-0.005
pan-0.005
alk-0.004
kin-0.004
ids-0.004
Token other
Token ID584
Feature activation-3.41e+00

Pos logit contributions
iring+0.064
ind+0.062
 cheaper+0.057
 barking+0.056
shadow+0.056
Neg logit contributions
isel-0.036
pan-0.032
alk-0.032
 cuc-0.030
kin-0.030
Token side
Token ID1735
Feature activation-1.06e+00

Pos logit contributions
ind+0.121
iring+0.120
handed+0.104
 cheaper+0.101
 barking+0.101
Neg logit contributions
isel-0.156
pan-0.134
kin-0.131
alk-0.129
ids-0.127
Token of
Token ID286
Feature activation-1.58e+00

Pos logit contributions
ind+0.057
iring+0.052
 homeless+0.051
 cheaper+0.050
 nicer+0.049
Neg logit contributions
isel-0.029
alk-0.027
kin-0.025
ily-0.023
pan-0.023
Token the
Token ID262
Feature activation-5.17e-01

Pos logit contributions
ind+0.081
iring+0.080
ll+0.071
itating+0.071
 cheaper+0.071
Neg logit contributions
isel-0.047
pan-0.038
alk-0.038
 cuc-0.036
kin-0.034
Token island
Token ID7022
Feature activation-2.25e-01

Pos logit contributions
iring+0.025
shadow+0.022
king+0.022
itating+0.022
ind+0.022
Neg logit contributions
isel-0.014
alk-0.014
 lived-0.013
 soil-0.013
 cuc-0.013
Token.
Token ID13
Feature activation-3.48e-01

Pos logit contributions
ind+0.013
iring+0.012
ica+0.011
ograph+0.011
 cheaper+0.011
Neg logit contributions
 lived-0.004
isel-0.004
alk-0.004
kin-0.004
pan-0.004
Token flashlight
Token ID38371
Feature activation-2.60e-01

Pos logit contributions
isel+0.006
kin+0.005
pan+0.005
brush+0.005
 imagination+0.005
Neg logit contributions
iring-0.008
ind-0.008
handed-0.007
itating-0.006
ning-0.006
Token,
Token ID11
Feature activation+9.51e-02

Pos logit contributions
ind+0.012
iring+0.012
handed+0.011
 homeless+0.011
 cheaper+0.010
Neg logit contributions
pan-0.009
isel-0.008
brush-0.008
kin-0.007
alk-0.007
Token and
Token ID290
Feature activation-3.56e-01

Pos logit contributions
isel+0.003
pan+0.002
brush+0.002
ids+0.002
aces+0.002
Neg logit contributions
ind-0.005
iring-0.005
handed-0.004
itating-0.004
glers-0.004
Token a
Token ID257
Feature activation-2.28e-01

Pos logit contributions
ind+0.018
iring+0.017
handed+0.015
itating+0.015
ich+0.015
Neg logit contributions
isel-0.011
pan-0.010
kin-0.009
 imagination-0.009
brush-0.009
Token magn
Token ID7842
Feature activation-7.24e-01

Pos logit contributions
iring+0.011
ind+0.010
handed+0.009
itating+0.009
shadow+0.008
Neg logit contributions
isel-0.008
pan-0.007
kin-0.007
 imagination-0.007
brush-0.007
Tokenifying
Token ID4035
Feature activation-3.38e+00

Pos logit contributions
ind+0.023
iring+0.022
handed+0.020
 cheaper+0.019
 homeless+0.019
Neg logit contributions
isel-0.036
pan-0.032
ids-0.031
alk-0.030
kin-0.030
Token glass
Token ID5405
Feature activation+2.07e-01

Pos logit contributions
ind+0.150
iring+0.148
handed+0.133
 cheaper+0.132
 barking+0.130
Neg logit contributions
isel-0.123
pan-0.101
kin-0.098
alk-0.097
ids-0.095
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
isel+0.007
pan+0.007
kin+0.006
brush+0.006
alk+0.006
Neg logit contributions
ind-0.010
iring-0.010
handed-0.008
 homeless-0.008
 barking-0.008
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
isel+0.000
pan+0.000
kin+0.000
alk+0.000
ids+0.000
Neg logit contributions
ind-0.001
iring-0.001
handed-0.000
 cheaper-0.000
 barking-0.000
Token
Token ID198
Feature activation-4.01e-01

Pos logit contributions
ind+0.006
iring+0.006
handed+0.005
 cheaper+0.005
 barking+0.005
Neg logit contributions
isel-0.005
pan-0.004
kin-0.004
alk-0.004
ids-0.004
TokenAs
Token ID1722
Feature activation-4.13e-01

Pos logit contributions
ind+0.017
iring+0.017
handed+0.015
 cheaper+0.015
 faster+0.015
Neg logit contributions
isel-0.016
pan-0.013
alk-0.013
kin-0.012
ids-0.012
Token explore
Token ID7301
Feature activation-1.17e+00

Pos logit contributions
iring+0.036
ind+0.035
 elderly+0.034
 faster+0.033
handed+0.033
Neg logit contributions
isel-0.035
kin-0.031
pan-0.030
ids-0.029
alk-0.028
Token what
Token ID644
Feature activation-6.65e-01

Pos logit contributions
ind+0.060
iring+0.060
handed+0.056
 homeless+0.053
ich+0.053
Neg logit contributions
isel-0.032
pan-0.026
alk-0.025
 lived-0.024
 imagination-0.023
Token was
Token ID373
Feature activation-1.81e-03

Pos logit contributions
ind+0.036
iring+0.034
king+0.032
handed+0.032
 sidelines+0.031
Neg logit contributions
isel-0.017
 lived-0.016
 It-0.013
brush-0.013
 can-0.013
Token on
Token ID319
Feature activation-5.14e-01

Pos logit contributions
ind+0.000
iring+0.000
handed+0.000
 concession+0.000
glers+0.000
Neg logit contributions
isel-0.000
pan-0.000
alk-0.000
 idea-0.000
 lived-0.000
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
ind+0.024
iring+0.024
handed+0.022
ll+0.022
 barking+0.021
Neg logit contributions
isel-0.017
pan-0.014
alk-0.014
kin-0.013
 imagination-0.013
Token other
Token ID584
Feature activation-3.38e+00

Pos logit contributions
ind+0.040
iring+0.040
handed+0.036
glers+0.034
 barking+0.034
Neg logit contributions
isel-0.040
pan-0.035
alk-0.034
kin-0.033
 idea-0.032
Token side
Token ID1735
Feature activation-1.09e+00

Pos logit contributions
ind+0.113
iring+0.112
handed+0.094
 cheaper+0.094
 barking+0.094
Neg logit contributions
isel-0.162
pan-0.140
kin-0.137
alk-0.134
ids-0.132
Token,
Token ID11
Feature activation+3.38e-01

Pos logit contributions
ind+0.064
iring+0.057
 homeless+0.057
 concession+0.054
handed+0.054
Neg logit contributions
isel-0.026
alk-0.022
ids-0.021
kin-0.021
aces-0.020
Token so
Token ID523
Feature activation-2.35e-01

Pos logit contributions
isel+0.012
pan+0.010
 idea+0.010
 imagination+0.010
 It+0.010
Neg logit contributions
ind-0.016
iring-0.014
handed-0.014
ich-0.012
glers-0.012
Token he
Token ID339
Feature activation-5.15e-01

Pos logit contributions
ind+0.009
iring+0.008
handed+0.008
 cheaper+0.007
 barking+0.007
Neg logit contributions
isel-0.010
pan-0.008
kin-0.008
 lived-0.008
alk-0.008
Token flew
Token ID13112
Feature activation+2.29e-01

Pos logit contributions
ind+0.023
iring+0.023
 faster+0.021
 cheaper+0.021
 barking+0.021
Neg logit contributions
isel-0.018
pan-0.015
alk-0.015
kin-0.015
ids-0.014
Token see
Token ID766
Feature activation-5.84e-01

Pos logit contributions
iring+0.032
ind+0.030
 elderly+0.029
 new+0.029
 barking+0.028
Neg logit contributions
isel-0.031
kin-0.031
pan-0.029
ids-0.029
aces-0.027
Token what
Token ID644
Feature activation-4.93e-01

Pos logit contributions
ind+0.028
iring+0.027
handed+0.026
glers+0.024
 concession+0.024
Neg logit contributions
isel-0.019
pan-0.015
 imagination-0.014
 cuc-0.014
ids-0.013
Token was
Token ID373
Feature activation+6.18e-02

Pos logit contributions
ind+0.024
iring+0.023
handed+0.021
 barking+0.020
 homeless+0.020
Neg logit contributions
isel-0.016
pan-0.013
 lived-0.013
kin-0.013
alk-0.012
Token on
Token ID319
Feature activation-4.50e-01

Pos logit contributions
isel+0.003
pan+0.002
kin+0.002
alk+0.002
ids+0.002
Neg logit contributions
ind-0.002
iring-0.002
handed-0.002
 cheaper-0.002
 homeless-0.002
Token the
Token ID262
Feature activation-9.76e-01

Pos logit contributions
ind+0.019
iring+0.018
handed+0.016
 cheaper+0.016
 barking+0.016
Neg logit contributions
isel-0.018
pan-0.015
alk-0.015
kin-0.015
ids-0.014
Token other
Token ID584
Feature activation-3.35e+00

Pos logit contributions
ind+0.042
iring+0.041
handed+0.037
 cheaper+0.036
 barking+0.036
Neg logit contributions
isel-0.037
pan-0.031
alk-0.030
kin-0.029
ids-0.029
Token side
Token ID1735
Feature activation-9.81e-01

Pos logit contributions
iring+0.102
ind+0.101
 barking+0.086
 faster+0.084
 elderly+0.084
Neg logit contributions
isel-0.170
pan-0.151
kin-0.146
alk-0.140
ids-0.139
Token of
Token ID286
Feature activation-1.42e+00

Pos logit contributions
ind+0.058
iring+0.051
 homeless+0.050
handed+0.049
 concession+0.048
Neg logit contributions
isel-0.024
kin-0.019
alk-0.019
pan-0.019
brush-0.018
Token the
Token ID262
Feature activation-3.50e-01

Pos logit contributions
ind+0.059
iring+0.058
handed+0.051
 cheaper+0.050
 barking+0.050
Neg logit contributions
isel-0.057
pan-0.048
alk-0.047
kin-0.047
ids-0.045
Token wall
Token ID3355
Feature activation+1.12e+00

Pos logit contributions
ind+0.015
iring+0.015
handed+0.013
 barking+0.013
 elderly+0.013
Neg logit contributions
isel-0.013
pan-0.011
kin-0.011
ids-0.011
alk-0.010
Token.
Token ID13
Feature activation-1.70e-02

Pos logit contributions
isel+0.027
pan+0.026
kin+0.024
aces+0.024
alk+0.023
Neg logit contributions
ind-0.064
iring-0.060
 homeless-0.056
handed-0.054
ich-0.054
Token friend
Token ID1545
Feature activation-9.80e-01

Pos logit contributions
ind+0.003
handed+0.003
shadow+0.003
iring+0.003
 concession+0.003
Neg logit contributions
kin-0.002
 idea-0.002
 imagination-0.002
isel-0.002
brush-0.002
Token Tim
Token ID5045
Feature activation-2.47e-01

Pos logit contributions
ind+0.061
iring+0.058
handed+0.054
izing+0.053
 cheaper+0.052
Neg logit contributions
 lived-0.019
 nod-0.016
 It-0.016
ily-0.015
 are-0.013
Tokenmy
Token ID1820
Feature activation-2.66e-01

Pos logit contributions
iring+0.009
ind+0.009
 cheaper+0.008
handed+0.008
 homeless+0.008
Neg logit contributions
isel-0.010
pan-0.009
alk-0.009
ids-0.009
 lived-0.008
Token on
Token ID319
Feature activation-1.53e-01

Pos logit contributions
iring+0.013
ind+0.012
 cheaper+0.011
handed+0.011
 ours+0.010
Neg logit contributions
 lived-0.008
isel-0.007
pan-0.007
 nod-0.007
ids-0.007
Token the
Token ID262
Feature activation-1.22e+00

Pos logit contributions
iring+0.008
ind+0.007
 cheaper+0.007
shadow+0.007
ll+0.007
Neg logit contributions
isel-0.005
alk-0.004
pan-0.004
kin-0.004
 imagination-0.004
Token other
Token ID584
Feature activation-3.35e+00

Pos logit contributions
iring+0.059
ind+0.058
 cheaper+0.052
shadow+0.052
handed+0.051
Neg logit contributions
isel-0.034
pan-0.033
alk-0.031
 gard-0.030
kin-0.029
Token side
Token ID1735
Feature activation-1.09e+00

Pos logit contributions
ind+0.109
iring+0.106
 barking+0.093
handed+0.092
 faster+0.091
Neg logit contributions
isel-0.167
pan-0.142
kin-0.139
alk-0.136
ids-0.134
Token of
Token ID286
Feature activation-1.47e+00

Pos logit contributions
ind+0.060
iring+0.057
 homeless+0.054
 cheaper+0.053
shadow+0.051
Neg logit contributions
isel-0.026
alk-0.024
pan-0.024
kin-0.023
brush-0.022
Token the
Token ID262
Feature activation-4.65e-01

Pos logit contributions
iring+0.073
ind+0.072
 cheaper+0.063
ll+0.063
handed+0.062
Neg logit contributions
isel-0.046
pan-0.040
alk-0.039
kin-0.036
 imagination-0.035
Token fence
Token ID13990
Feature activation-3.84e-03

Pos logit contributions
iring+0.020
ind+0.019
shadow+0.018
king+0.018
 cheaper+0.017
Neg logit contributions
isel-0.015
alk-0.015
 gard-0.014
 soil-0.014
pan-0.014
Token.
Token ID13
Feature activation-2.76e-01

Pos logit contributions
ind+0.000
iring+0.000
 homeless+0.000
 cheaper+0.000
shadow+0.000
Neg logit contributions
isel-0.000
pan-0.000
alk-0.000
 lived-0.000
kin-0.000
Token to
Token ID284
Feature activation+5.07e-01

Pos logit contributions
ind+0.040
iring+0.037
Nice+0.035
handed+0.034
oma+0.033
Neg logit contributions
pan-0.020
brush-0.019
isel-0.018
kin-0.018
ids-0.016
Token a
Token ID257
Feature activation+2.50e-02

Pos logit contributions
isel+0.013
 lived+0.012
 idea+0.011
 imagination+0.011
 understand+0.011
Neg logit contributions
ind-0.027
iring-0.027
itating-0.026
king-0.025
ll-0.025
Token house
Token ID2156
Feature activation+4.29e-01

Pos logit contributions
 cuc+0.001
 can+0.001
isel+0.001
 imagination+0.001
 seed+0.001
Neg logit contributions
iring-0.001
ind-0.001
awed-0.001
itating-0.001
handed-0.001
Token on
Token ID319
Feature activation+6.75e-02

Pos logit contributions
isel+0.015
pan+0.014
brush+0.012
kin+0.012
alk+0.012
Neg logit contributions
ind-0.019
iring-0.019
handed-0.016
 cheaper-0.016
ich-0.016
Token the
Token ID262
Feature activation-1.33e+00

Pos logit contributions
isel+0.001
pan+0.001
alk+0.001
 It+0.001
 lived+0.001
Neg logit contributions
ll-0.004
iring-0.004
ind-0.004
shadow-0.004
itating-0.004
Token other
Token ID584
Feature activation-3.34e+00

Pos logit contributions
iring+0.064
shadow+0.062
rou+0.059
ounce+0.059
awed+0.059
Neg logit contributions
 roof-0.036
 gard-0.035
pan-0.034
 soil-0.033
gen-0.031
Token side
Token ID1735
Feature activation-1.10e+00

Pos logit contributions
iring+0.145
ind+0.141
 cheaper+0.126
itating+0.125
 faster+0.124
Neg logit contributions
isel-0.113
pan-0.099
 lived-0.098
alk-0.098
kin-0.094
Token of
Token ID286
Feature activation-1.50e+00

Pos logit contributions
ind+0.060
iring+0.057
 homeless+0.052
 cheaper+0.052
 nicer+0.051
Neg logit contributions
isel-0.028
alk-0.024
pan-0.024
kin-0.023
ids-0.023
Token town
Token ID3240
Feature activation+2.64e-02

Pos logit contributions
iring+0.080
ind+0.077
ll+0.074
itating+0.073
 fastest+0.070
Neg logit contributions
isel-0.040
pan-0.036
alk-0.032
 imagination-0.031
kin-0.030
Token.
Token ID13
Feature activation-3.04e-02

Pos logit contributions
isel+0.001
 lived+0.000
alk+0.000
pan+0.000
ids+0.000
Neg logit contributions
ind-0.001
iring-0.001
Nice-0.001
 nicer-0.001
 cheaper-0.001
Token He
Token ID679
Feature activation+1.29e-01

Pos logit contributions
ind+0.002
iring+0.002
handed+0.002
ich+0.002
 cheaper+0.001
Neg logit contributions
isel-0.001
 It-0.001
 imagination-0.001
ids-0.001
 lived-0.001
Token bull
Token ID6473
Feature activation-1.58e+00

Pos logit contributions
iring+0.017
shadow+0.017
handed+0.016
ind+0.016
har+0.016
Neg logit contributions
isel-0.007
 idea-0.007
 gard-0.007
 soil-0.007
 imagination-0.006
Token and
Token ID290
Feature activation-3.99e-01

Pos logit contributions
iring+0.087
ind+0.085
 cheaper+0.074
handed+0.073
 homeless+0.073
Neg logit contributions
isel-0.035
pan-0.035
alk-0.034
ids-0.034
 lived-0.032
Token play
Token ID711
Feature activation-5.39e-02

Pos logit contributions
iring+0.020
ind+0.020
handed+0.017
 cheaper+0.017
 barking+0.017
Neg logit contributions
isel-0.013
pan-0.010
kin-0.010
alk-0.010
ids-0.009
Token on
Token ID319
Feature activation-5.37e-01

Pos logit contributions
ind+0.002
iring+0.002
 cheaper+0.002
handed+0.002
 homeless+0.002
Neg logit contributions
isel-0.002
pan-0.002
kin-0.002
alk-0.002
ids-0.002
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
iring+0.031
ind+0.029
itating+0.027
ll+0.026
shadow+0.026
Neg logit contributions
isel-0.012
pan-0.011
alk-0.010
 It-0.010
 imagination-0.010
Token other
Token ID584
Feature activation-3.34e+00

Pos logit contributions
iring+0.058
ind+0.053
handed+0.051
 cheaper+0.050
itating+0.049
Neg logit contributions
isel-0.037
pan-0.036
bee-0.034
 soil-0.033
alk-0.032
Token side
Token ID1735
Feature activation-1.16e+00

Pos logit contributions
iring+0.138
ind+0.132
 cheaper+0.121
handed+0.119
 homeless+0.119
Neg logit contributions
isel-0.124
alk-0.108
pan-0.107
kin-0.103
aces-0.101
Token of
Token ID286
Feature activation-1.55e+00

Pos logit contributions
ind+0.064
iring+0.063
 homeless+0.061
shadow+0.058
ograph+0.057
Neg logit contributions
isel-0.026
kin-0.024
alk-0.024
ily-0.023
pan-0.022
Token the
Token ID262
Feature activation-5.12e-01

Pos logit contributions
iring+0.076
ind+0.074
handed+0.067
 cheaper+0.066
 homeless+0.065
Neg logit contributions
isel-0.051
pan-0.043
alk-0.042
kin-0.038
 imagination-0.038
Token park
Token ID3952
Feature activation-8.19e-01

Pos logit contributions
iring+0.025
handed+0.022
ind+0.022
shadow+0.022
itating+0.022
Neg logit contributions
isel-0.014
alk-0.013
 soil-0.013
pan-0.012
 gard-0.012
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
ind+0.046
iring+0.045
shadow+0.040
ograph+0.039
 homeless+0.039
Neg logit contributions
isel-0.017
kin-0.016
pan-0.016
 lived-0.016
alk-0.016
Token a
Token ID257
Feature activation-3.03e-01

Pos logit contributions
ind+0.024
iring+0.024
handed+0.020
 faster+0.020
 barking+0.020
Neg logit contributions
isel-0.028
pan-0.023
alk-0.023
kin-0.023
ids-0.022
Token big
Token ID1263
Feature activation+2.59e-01

Pos logit contributions
iring+0.012
ind+0.012
handed+0.011
 faster+0.010
 cheaper+0.010
Neg logit contributions
isel-0.012
kin-0.010
pan-0.010
 cuc-0.010
brush-0.010
Token box
Token ID3091
Feature activation+1.77e-01

Pos logit contributions
isel+0.010
pan+0.008
kin+0.008
ids+0.008
alk+0.008
Neg logit contributions
ind-0.011
iring-0.011
 barking-0.010
 cheaper-0.010
 faster-0.009
Token on
Token ID319
Feature activation-1.20e-01

Pos logit contributions
isel+0.007
pan+0.006
kin+0.006
alk+0.006
ids+0.006
Neg logit contributions
ind-0.007
iring-0.007
handed-0.006
 cheaper-0.006
 barking-0.006
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
ind+0.004
iring+0.004
 new+0.003
 elderly+0.003
 cheaper+0.003
Neg logit contributions
isel-0.006
pan-0.005
kin-0.005
ids-0.005
alk-0.005
Token other
Token ID584
Feature activation-3.33e+00

Pos logit contributions
iring+0.060
ind+0.057
shadow+0.056
 barking+0.054
 cheaper+0.052
Neg logit contributions
isel-0.031
pan-0.031
 soil-0.029
alk-0.028
 gard-0.028
Token side
Token ID1735
Feature activation-1.05e+00

Pos logit contributions
ind+0.107
iring+0.103
handed+0.088
 cheaper+0.085
 barking+0.085
Neg logit contributions
isel-0.170
pan-0.146
kin-0.141
alk-0.139
ids-0.138
Token of
Token ID286
Feature activation-1.63e+00

Pos logit contributions
ind+0.049
iring+0.047
 homeless+0.043
 cheaper+0.042
handed+0.042
Neg logit contributions
isel-0.036
alk-0.031
kin-0.031
pan-0.031
ids-0.030
Token the
Token ID262
Feature activation-4.83e-01

Pos logit contributions
ind+0.068
iring+0.068
handed+0.060
 cheaper+0.059
 barking+0.058
Neg logit contributions
isel-0.064
pan-0.054
alk-0.052
kin-0.052
ids-0.050
Token room
Token ID2119
Feature activation+3.84e-01

Pos logit contributions
iring+0.022
shadow+0.021
king+0.020
ind+0.020
itating+0.019
Neg logit contributions
isel-0.014
 imagination-0.013
 soil-0.013
alk-0.013
 gard-0.012
Token,
Token ID11
Feature activation-5.67e-02

Pos logit contributions
isel+0.013
pan+0.011
kin+0.011
alk+0.011
ids+0.011
Neg logit contributions
ind-0.018
iring-0.017
 cheaper-0.015
 homeless-0.015
handed-0.015
Token see
Token ID766
Feature activation-6.35e-01

Pos logit contributions
iring+0.037
ind+0.035
 faster+0.035
 elderly+0.034
 destination+0.033
Neg logit contributions
isel-0.033
pan-0.030
kin-0.030
ids-0.029
alk-0.028
Token what
Token ID644
Feature activation-5.91e-01

Pos logit contributions
ind+0.028
iring+0.027
handed+0.025
 homeless+0.024
 barking+0.024
Neg logit contributions
isel-0.024
pan-0.020
alk-0.018
kin-0.018
ids-0.018
Token is
Token ID318
Feature activation-4.42e-01

Pos logit contributions
ind+0.026
iring+0.026
 cheaper+0.023
handed+0.023
 barking+0.023
Neg logit contributions
isel-0.022
pan-0.018
kin-0.017
alk-0.017
ids-0.017
Token on
Token ID319
Feature activation-4.92e-01

Pos logit contributions
ind+0.017
iring+0.017
handed+0.015
 homeless+0.014
 cheaper+0.014
Neg logit contributions
isel-0.019
pan-0.016
kin-0.016
alk-0.016
ids-0.015
Token the
Token ID262
Feature activation-9.96e-01

Pos logit contributions
ind+0.019
iring+0.019
 cheaper+0.017
handed+0.017
 faster+0.017
Neg logit contributions
isel-0.020
pan-0.017
kin-0.017
alk-0.017
ids-0.016
Token other
Token ID584
Feature activation-3.33e+00

Pos logit contributions
ind+0.046
iring+0.044
handed+0.042
 barking+0.040
 homeless+0.040
Neg logit contributions
isel-0.033
alk-0.028
pan-0.027
kin-0.027
 idea-0.026
Token side
Token ID1735
Feature activation-1.10e+00

Pos logit contributions
ind+0.117
iring+0.116
handed+0.100
 cheaper+0.099
 barking+0.098
Neg logit contributions
isel-0.153
pan-0.132
kin-0.129
alk-0.128
ids-0.125
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
ind+0.063
iring+0.057
 homeless+0.055
handed+0.055
 concession+0.052
Neg logit contributions
isel-0.028
alk-0.024
kin-0.024
pan-0.024
ids-0.022
Token
Token ID198
Feature activation-6.29e-01

Pos logit contributions
iring+0.012
ind+0.012
 barking+0.011
 cheaper+0.011
handed+0.011
Neg logit contributions
isel-0.011
pan-0.009
kin-0.009
alk-0.009
ids-0.008
Token
Token ID198
Feature activation-9.71e-01

Pos logit contributions
ind+0.029
iring+0.029
handed+0.026
 cheaper+0.026
 homeless+0.025
Neg logit contributions
isel-0.022
pan-0.017
alk-0.017
kin-0.017
ids-0.016
Token"
Token ID1
Feature activation-7.26e-01

Pos logit contributions
ind+0.039
iring+0.038
handed+0.034
 cheaper+0.033
 barking+0.033
Neg logit contributions
isel-0.040
pan-0.033
kin-0.033
alk-0.032
ids-0.031
Token pipe
Token ID12656
Feature activation-9.57e-01

Pos logit contributions
iring+0.027
ind+0.027
 cheaper+0.023
 barking+0.023
handed+0.023
Neg logit contributions
isel-0.028
pan-0.025
kin-0.024
ids-0.023
alk-0.023
Token and
Token ID290
Feature activation-1.62e-01

Pos logit contributions
ind+0.048
iring+0.047
 homeless+0.041
handed+0.041
 cheaper+0.040
Neg logit contributions
isel-0.028
pan-0.026
brush-0.025
kin-0.025
aces-0.024
Token he
Token ID339
Feature activation-1.02e+00

Pos logit contributions
ind+0.007
iring+0.007
handed+0.006
 cheaper+0.006
 homeless+0.006
Neg logit contributions
isel-0.006
pan-0.005
kin-0.005
alk-0.005
 imagination-0.005
Token could
Token ID714
Feature activation+6.24e-02

Pos logit contributions
iring+0.053
ind+0.052
handed+0.047
 cheaper+0.046
 barking+0.046
Neg logit contributions
isel-0.030
pan-0.024
kin-0.023
 lived-0.023
alk-0.022
Token never
Token ID1239
Feature activation-2.63e-01

Pos logit contributions
isel+0.002
pan+0.002
alk+0.002
kin+0.002
ids+0.002
Neg logit contributions
ind-0.003
iring-0.003
handed-0.002
 cheaper-0.002
 homeless-0.002
Token truly
Token ID4988
Feature activation-3.32e+00

Pos logit contributions
ind+0.012
iring+0.012
handed+0.011
 cheaper+0.011
 elderly+0.010
Neg logit contributions
isel-0.009
pan-0.007
alk-0.007
kin-0.007
ids-0.007
Token hate
Token ID5465
Feature activation-4.50e-01

Pos logit contributions
ind+0.162
iring+0.161
handed+0.145
 cheaper+0.144
 barking+0.142
Neg logit contributions
isel-0.106
pan-0.085
kin-0.082
alk-0.081
ids-0.078
Token it
Token ID340
Feature activation-3.61e-01

Pos logit contributions
ind+0.022
iring+0.021
handed+0.019
 cheaper+0.019
glers+0.019
Neg logit contributions
isel-0.015
pan-0.012
alk-0.012
 imagination-0.011
kin-0.011
Token.
Token ID13
Feature activation+4.30e-01

Pos logit contributions
ind+0.019
iring+0.017
glers+0.016
ich+0.016
 concession+0.015
Neg logit contributions
kin-0.010
aces-0.009
pan-0.009
isel-0.009
 idea-0.009
Token<|endoftext|>
Token ID50256
Feature activation-1.34e+00

Pos logit contributions
isel+0.017
pan+0.014
kin+0.014
alk+0.013
ids+0.013
Neg logit contributions
ind-0.018
iring-0.018
handed-0.016
 cheaper-0.016
 barking-0.016
TokenOnce
Token ID7454
Feature activation+1.01e+00

Pos logit contributions
ind+0.060
iring+0.059
 cheaper+0.053
handed+0.052
 homeless+0.051
Neg logit contributions
isel-0.048
pan-0.040
kin-0.039
alk-0.039
ids-0.038
Token was
Token ID373
Feature activation+4.55e-01

Pos logit contributions
 lived+0.001
isel+0.001
 can+0.001
kin+0.001
pan+0.001
Neg logit contributions
iring-0.003
ind-0.003
handed-0.003
 sidelines-0.003
 cheaper-0.003
Token unusual
Token ID8468
Feature activation-5.56e-02

Pos logit contributions
isel+0.014
pan+0.014
 spr+0.013
kin+0.013
 imagination+0.013
Neg logit contributions
handed-0.021
iring-0.020
ind-0.019
 concession-0.019
 sidelines-0.018
Token -
Token ID532
Feature activation-8.39e-02

Pos logit contributions
ind+0.003
iring+0.003
handed+0.003
 homeless+0.002
Mrs+0.002
Neg logit contributions
isel-0.002
pan-0.001
 imagination-0.001
 idea-0.001
alk-0.001
Token it
Token ID340
Feature activation+2.14e-02

Pos logit contributions
ind+0.005
iring+0.004
handed+0.004
glers+0.004
ll+0.004
Neg logit contributions
isel-0.002
pan-0.002
 imagination-0.002
 It-0.002
kin-0.002
Token could
Token ID714
Feature activation+3.38e-01

Pos logit contributions
isel+0.000
 lived+0.000
kin+0.000
pan+0.000
 can+0.000
Neg logit contributions
ind-0.001
iring-0.001
handed-0.001
 cheaper-0.001
 sidelines-0.001
Token actually
Token ID1682
Feature activation-3.32e+00

Pos logit contributions
isel+0.010
pan+0.008
alk+0.008
kin+0.008
ids+0.008
Neg logit contributions
ind-0.017
iring-0.017
handed-0.016
 cheaper-0.015
 homeless-0.014
Token sing
Token ID1702
Feature activation-5.38e-01

Pos logit contributions
iring+0.166
ind+0.166
handed+0.148
 cheaper+0.146
 homeless+0.143
Neg logit contributions
isel-0.103
pan-0.082
alk-0.081
kin-0.080
ids-0.077
Token words
Token ID2456
Feature activation+1.26e+00

Pos logit contributions
ind+0.024
iring+0.024
handed+0.022
 cheaper+0.021
 homeless+0.021
Neg logit contributions
isel-0.018
kin-0.016
pan-0.016
alk-0.015
 lived-0.015
Token!
Token ID0
Feature activation-1.10e-01

Pos logit contributions
pan+0.033
isel+0.031
brush+0.031
ids+0.029
 can+0.028
Neg logit contributions
ind-0.065
iring-0.062
handed-0.061
 homeless-0.057
ich-0.055
Token
Token ID198
Feature activation+1.36e-02

Pos logit contributions
ind+0.005
iring+0.005
 cheaper+0.005
handed+0.005
 faster+0.005
Neg logit contributions
isel-0.004
pan-0.003
alk-0.003
kin-0.003
ids-0.003
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
isel+0.000
pan+0.000
kin+0.000
alk+0.000
ids+0.000
Neg logit contributions
ind-0.001
iring-0.001
handed-0.001
 cheaper-0.001
 barking-0.001
Token had
Token ID550
Feature activation+1.73e-01

Pos logit contributions
isel+0.012
pan+0.010
kin+0.009
alk+0.009
aces+0.008
Neg logit contributions
ind-0.022
iring-0.021
 cheaper-0.020
handed-0.020
 barking-0.020
Token breakfast
Token ID12607
Feature activation-3.19e-01

Pos logit contributions
isel+0.006
 imagination+0.005
 cuc+0.004
pan+0.004
brush+0.004
Neg logit contributions
iring-0.009
ind-0.008
glers-0.008
itating-0.007
handed-0.007
Token a
Token ID257
Feature activation+1.05e-01

Pos logit contributions
ind+0.014
iring+0.014
handed+0.012
 barking+0.012
 homeless+0.012
Neg logit contributions
isel-0.011
kin-0.011
pan-0.010
brush-0.010
ids-0.010
Token little
Token ID1310
Feature activation+9.14e-02

Pos logit contributions
isel+0.004
 imagination+0.003
kin+0.003
 idea+0.003
pan+0.003
Neg logit contributions
iring-0.005
ind-0.005
handed-0.004
glers-0.004
ich-0.004
Token while
Token ID981
Feature activation-6.04e-01

Pos logit contributions
isel+0.003
pan+0.003
 idea+0.003
 imagination+0.003
kin+0.003
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
ich-0.003
itating-0.003
Token ago
Token ID2084
Feature activation+4.00e+00

Pos logit contributions
ind+0.028
iring+0.027
handed+0.025
glers+0.024
 cheaper+0.023
Neg logit contributions
isel-0.020
kin-0.018
pan-0.018
ids-0.017
 imagination-0.017
Token,
Token ID11
Feature activation+2.82e-01

Pos logit contributions
isel+0.137
pan+0.111
kin+0.107
alk+0.107
ids+0.103
Neg logit contributions
ind-0.185
iring-0.183
handed-0.165
 cheaper-0.163
 barking-0.162
Token so
Token ID523
Feature activation-4.85e-01

Pos logit contributions
isel+0.011
pan+0.009
kin+0.009
 imagination+0.009
ids+0.009
Neg logit contributions
ind-0.012
iring-0.012
handed-0.010
glers-0.010
 cheaper-0.010
Token I
Token ID314
Feature activation+5.21e-01

Pos logit contributions
ind+0.020
iring+0.019
handed+0.017
 cheaper+0.017
 homeless+0.017
Neg logit contributions
isel-0.020
kin-0.016
 imagination-0.016
 lived-0.016
pan-0.015
Token'm
Token ID1101
Feature activation-8.00e-01

Pos logit contributions
isel+0.016
pan+0.013
kin+0.012
alk+0.012
ids+0.012
Neg logit contributions
ind-0.026
iring-0.025
 cheaper-0.023
handed-0.023
 barking-0.023
Token not
Token ID407
Feature activation-1.18e-01

Pos logit contributions
ind+0.029
iring+0.029
handed+0.025
glers+0.024
 cheaper+0.023
Neg logit contributions
isel-0.036
pan-0.032
ids-0.030
kin-0.030
 imagination-0.029
Token Her
Token ID2332
Feature activation-1.48e-01

Pos logit contributions
isel+0.001
 It+0.001
pan+0.001
 imagination+0.001
alk+0.001
Neg logit contributions
ind-0.003
iring-0.002
handed-0.002
 faster-0.002
 fastest-0.002
Token grandma
Token ID49890
Feature activation-2.26e-01

Pos logit contributions
iring+0.006
ind+0.006
glers+0.006
handed+0.006
itating+0.006
Neg logit contributions
 imagination-0.006
 idea-0.005
brush-0.005
kin-0.005
 nod-0.005
Token had
Token ID550
Feature activation+6.73e-01

Pos logit contributions
iring+0.012
ind+0.012
handed+0.011
 sidelines+0.011
itating+0.011
Neg logit contributions
 lived-0.006
isel-0.005
kin-0.005
pan-0.004
 can-0.004
Token a
Token ID257
Feature activation+1.46e-01

Pos logit contributions
brush+0.014
 imagination+0.014
 lived+0.014
pan+0.013
aces+0.013
Neg logit contributions
iring-0.039
ind-0.037
itating-0.034
izing-0.033
handed-0.032
Token delicate
Token ID19217
Feature activation+9.92e-01

Pos logit contributions
isel+0.006
 imagination+0.005
 idea+0.005
kin+0.005
pan+0.005
Neg logit contributions
iring-0.006
ind-0.006
handed-0.006
glers-0.005
ups-0.005
Token v
Token ID410
Feature activation+2.92e+00

Pos logit contributions
isel+0.036
pan+0.029
alk+0.028
kin+0.028
ids+0.027
Neg logit contributions
ind-0.044
iring-0.044
 cheaper-0.039
 barking-0.039
handed-0.039
Tokenase
Token ID589
Feature activation+2.03e+00

Pos logit contributions
isel+0.095
pan+0.074
alk+0.072
kin+0.069
ids+0.068
Neg logit contributions
ind-0.144
iring-0.143
handed-0.130
 cheaper-0.124
 barking-0.124
Token on
Token ID319
Feature activation-4.40e-03

Pos logit contributions
brush+0.062
kin+0.060
pan+0.059
aces+0.055
isel+0.053
Neg logit contributions
ind-0.099
iring-0.097
handed-0.083
 cheaper-0.083
Nice-0.083
Token the
Token ID262
Feature activation-9.17e-01

Pos logit contributions
iring+0.000
ind+0.000
handed+0.000
ll+0.000
 cheaper+0.000
Neg logit contributions
isel-0.000
pan-0.000
kin-0.000
alk-0.000
 imagination-0.000
Token table
Token ID3084
Feature activation+1.19e+00

Pos logit contributions
iring+0.049
shadow+0.043
itating+0.043
ind+0.041
Nice+0.041
Neg logit contributions
pan-0.023
 tul-0.022
brush-0.021
 roof-0.020
kin-0.020
Token.
Token ID13
Feature activation-6.13e-03

Pos logit contributions
pan+0.035
isel+0.034
kin+0.034
brush+0.032
ids+0.031
Neg logit contributions
ind-0.059
iring-0.057
 homeless-0.050
 cheaper-0.049
shadow-0.049
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
isel+0.008
pan+0.007
brush+0.007
ids+0.006
 It+0.006
Neg logit contributions
ind-0.019
ich-0.017
iring-0.016
 homeless-0.016
handed-0.016
Token She
Token ID1375
Feature activation+3.73e-01

Pos logit contributions
isel+0.001
pan+0.000
kin+0.000
alk+0.000
ids+0.000
Neg logit contributions
iring-0.001
ind-0.001
 barking-0.001
handed-0.001
 cheaper-0.001
Token used
Token ID973
Feature activation-7.16e-02

Pos logit contributions
isel+0.012
pan+0.009
kin+0.009
ids+0.009
 lived+0.009
Neg logit contributions
iring-0.019
ind-0.019
handed-0.017
 cheaper-0.016
 homeless-0.016
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
ind+0.003
iring+0.003
 cheaper+0.003
handed+0.003
 faster+0.003
Neg logit contributions
isel-0.003
pan-0.002
kin-0.002
alk-0.002
ids-0.002
Token m
Token ID285
Feature activation+1.41e+00

Pos logit contributions
isel+0.043
pan+0.036
kin+0.035
alk+0.035
ids+0.034
Neg logit contributions
ind-0.041
iring-0.041
handed-0.035
 barking-0.034
 cheaper-0.034
Tokenitt
Token ID715
Feature activation+3.04e+00

Pos logit contributions
isel+0.050
pan+0.042
alk+0.042
kin+0.041
ids+0.038
Neg logit contributions
iring-0.063
ind-0.063
handed-0.056
 cheaper-0.055
 homeless-0.053
Token to
Token ID284
Feature activation+1.17e+00

Pos logit contributions
isel+0.134
pan+0.114
kin+0.112
alk+0.111
ids+0.108
Neg logit contributions
ind-0.111
iring-0.110
handed-0.095
 cheaper-0.094
 barking-0.093
Token take
Token ID1011
Feature activation+2.68e-01

Pos logit contributions
isel+0.035
pan+0.028
kin+0.027
alk+0.025
ids+0.025
Neg logit contributions
ind-0.062
iring-0.061
handed-0.055
 barking-0.054
 cheaper-0.053
Token out
Token ID503
Feature activation-2.36e-01

Pos logit contributions
isel+0.009
pan+0.008
ids+0.007
kin+0.007
alk+0.007
Neg logit contributions
ind-0.012
iring-0.012
handed-0.011
 barking-0.011
 homeless-0.011
Token the
Token ID262
Feature activation+2.84e-01

Pos logit contributions
ind+0.011
iring+0.011
handed+0.010
ich+0.010
 homeless+0.010
Neg logit contributions
isel-0.008
pan-0.007
ids-0.006
brush-0.006
kin-0.006
Token pan
Token ID3425
Feature activation+8.47e-01

Pos logit contributions
isel+0.010
pan+0.009
kin+0.008
 imagination+0.008
brush+0.008
Neg logit contributions
iring-0.013
ind-0.013
 barking-0.012
handed-0.011
glers-0.011
Token
Token ID198
Feature activation-1.96e-02

Pos logit contributions
isel+0.010
pan+0.008
alk+0.008
kin+0.008
ids+0.008
Neg logit contributions
ind-0.017
iring-0.017
 cheaper-0.015
handed-0.015
 homeless-0.015
TokenGeorge
Token ID20191
Feature activation-5.10e-01

Pos logit contributions
ind+0.001
iring+0.001
 barking+0.001
 cheaper+0.001
handed+0.001
Neg logit contributions
isel-0.001
pan-0.001
kin-0.001
brush-0.001
alk-0.001
Token yelled
Token ID22760
Feature activation-1.90e-01

Pos logit contributions
iring+0.024
ind+0.024
handed+0.022
 cheaper+0.022
 homeless+0.022
Neg logit contributions
isel-0.016
kin-0.013
 lived-0.013
pan-0.013
alk-0.013
Token with
Token ID351
Feature activation+1.41e+00

Pos logit contributions
ind+0.009
iring+0.009
handed+0.008
 cheaper+0.008
 barking+0.008
Neg logit contributions
isel-0.006
pan-0.005
kin-0.005
alk-0.005
ids-0.005
Token g
Token ID308
Feature activation+4.89e-01

Pos logit contributions
isel+0.058
pan+0.052
alk+0.051
kin+0.050
ids+0.050
Neg logit contributions
iring-0.051
ind-0.051
 faster-0.050
 barking-0.046
 new-0.046
Tokenlee
Token ID7197
Feature activation+2.98e+00

Pos logit contributions
isel+0.017
pan+0.015
kin+0.014
brush+0.013
alk+0.013
Neg logit contributions
ind-0.023
iring-0.023
handed-0.019
 barking-0.019
 elderly-0.019
Token and
Token ID290
Feature activation+3.85e-01

Pos logit contributions
isel+0.092
pan+0.077
kin+0.073
alk+0.073
ids+0.072
Neg logit contributions
ind-0.148
iring-0.145
handed-0.130
 cheaper-0.130
 homeless-0.127
Token scrambled
Token ID34351
Feature activation-5.34e-01

Pos logit contributions
isel+0.012
pan+0.010
 lived+0.010
kin+0.010
brush+0.009
Neg logit contributions
ind-0.020
iring-0.019
handed-0.017
 cheaper-0.016
ich-0.016
Token onto
Token ID4291
Feature activation+2.18e-01

Pos logit contributions
ind+0.021
iring+0.021
handed+0.019
 homeless+0.018
 cheaper+0.018
Neg logit contributions
isel-0.022
pan-0.020
ids-0.019
alk-0.018
kin-0.018
Token Cloud
Token ID10130
Feature activation-7.49e-01

Pos logit contributions
isel+0.007
pan+0.006
 It+0.005
 imagination+0.005
ids+0.005
Neg logit contributions
ind-0.011
iring-0.011
ll-0.010
handed-0.010
ich-0.010
Tokeny
Token ID88
Feature activation+3.80e-01

Pos logit contributions
iring+0.032
ind+0.031
 cheaper+0.030
 homeless+0.030
handed+0.029
Neg logit contributions
isel-0.025
alk-0.022
pan-0.022
ids-0.021
kin-0.021
Token as
Token ID355
Feature activation+1.30e-01

Pos logit contributions
isel+0.013
pan+0.011
alk+0.010
kin+0.010
ids+0.010
Neg logit contributions
ind-0.017
iring-0.016
handed-0.014
 cheaper-0.014
 homeless-0.014
Token the
Token ID262
Feature activation+3.29e-01

Pos logit contributions
isel+0.005
pan+0.004
kin+0.004
alk+0.004
 imagination+0.004
Neg logit contributions
ind-0.006
iring-0.006
handed-0.005
itating-0.005
 barking-0.005
Token fairy
Token ID25607
Feature activation-2.72e-01

Pos logit contributions
isel+0.013
pan+0.010
kin+0.010
alk+0.010
ids+0.010
Neg logit contributions
ind-0.014
iring-0.014
handed-0.012
 cheaper-0.012
 barking-0.012
Token asked
Token ID1965
Feature activation+1.90e+00

Pos logit contributions
ind+0.014
iring+0.013
handed+0.012
 homeless+0.012
 cheaper+0.012
Neg logit contributions
isel-0.008
pan-0.007
ids-0.007
kin-0.007
alk-0.007
Token her
Token ID607
Feature activation+1.50e+00

Pos logit contributions
isel+0.064
pan+0.055
ids+0.053
kin+0.053
alk+0.052
Neg logit contributions
ind-0.087
iring-0.085
handed-0.077
ich-0.075
 fastest-0.074
Token r
Token ID374
Feature activation+3.04e+00

Pos logit contributions
isel+0.055
pan+0.047
ids+0.045
kin+0.045
alk+0.045
Neg logit contributions
ind-0.066
iring-0.063
handed-0.058
 homeless-0.055
 barking-0.055
Tokeniddle
Token ID2509
Feature activation+1.54e+00

Pos logit contributions
isel+0.102
pan+0.085
kin+0.083
alk+0.079
ids+0.076
Neg logit contributions
iring-0.147
ind-0.145
handed-0.126
 elderly-0.124
 cheaper-0.123
Token.
Token ID13
Feature activation+3.72e-01

Pos logit contributions
isel+0.047
pan+0.044
kin+0.043
ids+0.042
alk+0.042
Neg logit contributions
ind-0.075
iring-0.071
handed-0.066
 homeless-0.063
ich-0.063
Token Lily
Token ID20037
Feature activation+3.06e-01

Pos logit contributions
isel+0.006
 It+0.006
pan+0.006
ids+0.005
 cuc+0.005
Neg logit contributions
ind-0.023
iring-0.022
 fastest-0.020
ich-0.020
glers-0.020
Token thought
Token ID1807
Feature activation+3.79e-01

Pos logit contributions
isel+0.011
pan+0.009
kin+0.009
alk+0.009
ids+0.009
Neg logit contributions
ind-0.013
iring-0.013
handed-0.012
 cheaper-0.012
 barking-0.012
Token hard
Token ID1327
Feature activation-6.05e-03

Pos logit contributions
isel+0.014
pan+0.012
kin+0.012
ids+0.012
alk+0.011
Neg logit contributions
ind-0.017
iring-0.016
handed-0.015
ich-0.014
 barking-0.014
Token friends
Token ID2460
Feature activation-1.26e-01

Pos logit contributions
isel+0.008
pan+0.006
kin+0.006
alk+0.006
ids+0.006
Neg logit contributions
ind-0.007
iring-0.007
handed-0.006
 cheaper-0.006
 barking-0.006
Token were
Token ID547
Feature activation+2.05e-01

Pos logit contributions
ind+0.006
iring+0.006
handed+0.005
 faster+0.005
 cheaper+0.005
Neg logit contributions
isel-0.004
pan-0.004
alk-0.004
kin-0.004
ids-0.003
Token proud
Token ID6613
Feature activation-1.30e+00

Pos logit contributions
isel+0.009
pan+0.008
kin+0.008
ids+0.008
alk+0.008
Neg logit contributions
ind-0.007
iring-0.007
handed-0.006
 barking-0.006
 cheaper-0.006
Token that
Token ID326
Feature activation+4.43e-01

Pos logit contributions
ind+0.070
handed+0.064
iring+0.060
ich+0.058
shadow+0.057
Neg logit contributions
isel-0.037
 imagination-0.030
pan-0.029
 idea-0.029
 cuc-0.028
Token they
Token ID484
Feature activation+3.72e-01

Pos logit contributions
isel+0.016
kin+0.013
pan+0.013
alk+0.013
 imagination+0.013
Neg logit contributions
ind-0.020
iring-0.019
handed-0.017
 cheaper-0.017
 barking-0.016
Token had
Token ID550
Feature activation+9.14e-01

Pos logit contributions
isel+0.012
pan+0.010
alk+0.010
kin+0.009
ids+0.009
Neg logit contributions
iring-0.018
ind-0.018
 cheaper-0.016
handed-0.016
 faster-0.016
Token worked
Token ID3111
Feature activation-1.29e-01

Pos logit contributions
isel+0.033
pan+0.027
alk+0.026
kin+0.026
ids+0.025
Neg logit contributions
ind-0.042
iring-0.041
handed-0.036
 barking-0.036
 cheaper-0.035
Token together
Token ID1978
Feature activation+4.77e-01

Pos logit contributions
ind+0.005
iring+0.005
ich+0.005
 concession+0.005
 barking+0.005
Neg logit contributions
isel-0.005
 idea-0.004
alk-0.004
 imagination-0.004
kin-0.004
Token to
Token ID284
Feature activation-4.49e-02

Pos logit contributions
isel+0.016
pan+0.014
alk+0.014
kin+0.013
 imagination+0.013
Neg logit contributions
ind-0.023
iring-0.022
handed-0.020
glers-0.019
 homeless-0.019
Token restore
Token ID11169
Feature activation-1.19e+00

Pos logit contributions
ind+0.002
iring+0.002
handed+0.002
 cheaper+0.002
 faster+0.002
Neg logit contributions
isel-0.002
pan-0.001
kin-0.001
alk-0.001
ids-0.001
Token the
Token ID262
Feature activation+3.75e-01

Pos logit contributions
ind+0.060
iring+0.060
ich+0.055
handed+0.053
ll+0.053
Neg logit contributions
isel-0.036
 imagination-0.029
alk-0.029
 idea-0.028
kin-0.027
Token room
Token ID2119
Feature activation+6.98e-01

Pos logit contributions
isel+0.005
 imagination+0.005
 idea+0.005
 lived+0.004
kin+0.004
Neg logit contributions
ind-0.005
iring-0.005
king-0.005
ich-0.005
glers-0.005
Token so
Token ID523
Feature activation-2.99e-01

Pos logit contributions
pan+0.014
kin+0.014
 lived+0.013
isel+0.013
ids+0.013
Neg logit contributions
ind-0.042
iring-0.038
 homeless-0.035
ich-0.035
shadow-0.034
Token she
Token ID673
Feature activation-1.45e-01

Pos logit contributions
ind+0.016
handed+0.015
king+0.015
ograph+0.015
 barking+0.015
Neg logit contributions
isel-0.007
 lived-0.006
kin-0.006
 It-0.006
ily-0.006
Token started
Token ID2067
Feature activation+3.26e-01

Pos logit contributions
ind+0.007
iring+0.007
handed+0.007
 cheaper+0.007
 barking+0.007
Neg logit contributions
isel-0.004
pan-0.003
kin-0.003
alk-0.003
ids-0.003
Token walking
Token ID6155
Feature activation-3.90e-01

Pos logit contributions
isel+0.014
pan+0.013
alk+0.012
ids+0.012
 imagination+0.012
Neg logit contributions
ind-0.012
iring-0.012
handed-0.010
 cheaper-0.010
 homeless-0.010
Token around
Token ID1088
Feature activation+6.49e-01

Pos logit contributions
ind+0.018
iring+0.018
handed+0.016
 homeless+0.016
 cheaper+0.016
Neg logit contributions
isel-0.013
pan-0.011
alk-0.011
kin-0.011
ids-0.010
Token.
Token ID13
Feature activation+3.60e-01

Pos logit contributions
isel+0.024
pan+0.021
alk+0.020
kin+0.020
ids+0.019
Neg logit contributions
ind-0.028
iring-0.028
handed-0.025
 cheaper-0.025
 homeless-0.024
Token
Token ID198
Feature activation-1.23e-01

Pos logit contributions
isel+0.015
kin+0.014
pan+0.013
alk+0.012
bee+0.011
Neg logit contributions
iring-0.015
ind-0.014
 barking-0.013
handed-0.013
 elderly-0.013
Token
Token ID198
Feature activation-4.42e-01

Pos logit contributions
ind+0.006
iring+0.005
handed+0.005
 cheaper+0.005
 barking+0.005
Neg logit contributions
isel-0.004
pan-0.004
alk-0.003
kin-0.003
ids-0.003
TokenSuddenly
Token ID38582
Feature activation-1.47e-01

Pos logit contributions
iring+0.014
ind+0.014
handed+0.012
 faster+0.012
 barking+0.011
Neg logit contributions
isel-0.023
pan-0.020
kin-0.020
alk-0.019
ids-0.019
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
iring+0.006
ind+0.006
 new+0.006
 faster+0.006
 barking+0.005
Neg logit contributions
isel-0.006
alk-0.005
pan-0.005
kin-0.005
aces-0.004
Token
Token ID26391
Feature activation+7.20e-01

Pos logit contributions
ind+0.005
iring+0.005
handed+0.004
 cheaper+0.004
 barking+0.004
Neg logit contributions
isel-0.005
pan-0.004
kin-0.004
alk-0.004
ids-0.004
Token
Token ID129
Feature activation+1.15e+00

Pos logit contributions
isel+0.031
pan+0.027
alk+0.026
kin+0.026
ids+0.024
Neg logit contributions
ind-0.027
iring-0.026
handed-0.024
 barking-0.023
ich-0.023
Token
Token ID241
Feature activation+4.05e-01

Pos logit contributions
isel+0.041
alk+0.033
pan+0.033
kin+0.032
ids+0.032
Neg logit contributions
iring-0.051
ind-0.050
 cheaper-0.045
handed-0.045
 homeless-0.044
TokenIt
Token ID1026
Feature activation+2.16e-01

Pos logit contributions
isel+0.015
kin+0.012
 It+0.012
ids+0.012
alk+0.011
Neg logit contributions
ind-0.018
iring-0.018
handed-0.016
 cheaper-0.015
 nicer-0.015
Tokenâ
Token ID22940
Feature activation-6.02e-01

Pos logit contributions
isel+0.008
pan+0.006
kin+0.006
alk+0.006
ids+0.006
Neg logit contributions
ind-0.010
iring-0.010
handed-0.009
 cheaper-0.009
 barking-0.008
Token
Token ID26391
Feature activation+7.13e-01

Pos logit contributions
ind+0.025
iring+0.025
handed+0.023
 cheaper+0.022
 faster+0.022
Neg logit contributions
isel-0.023
pan-0.020
kin-0.019
alk-0.018
ids-0.018
Token
Token ID8151
Feature activation+1.56e+00

Pos logit contributions
isel+0.029
pan+0.026
alk+0.024
kin+0.024
 cuc+0.022
Neg logit contributions
ind-0.027
iring-0.027
handed-0.025
 barking-0.025
ich-0.024
Tokens
Token ID82
Feature activation+1.85e-01

Pos logit contributions
isel+0.055
kin+0.052
ids+0.050
alk+0.049
 lived+0.048
Neg logit contributions
ind-0.069
iring-0.062
 nicer-0.059
 cheaper-0.058
 homeless-0.056
Token winter
Token ID7374
Feature activation-2.04e-01

Pos logit contributions
isel+0.007
pan+0.006
kin+0.006
alk+0.006
ids+0.005
Neg logit contributions
ind-0.008
iring-0.008
handed-0.007
 cheaper-0.007
 barking-0.007
Tokentime
Token ID2435
Feature activation-5.60e-01

Pos logit contributions
ind+0.009
iring+0.009
handed+0.008
 homeless+0.008
 cheaper+0.008
Neg logit contributions
isel-0.007
kin-0.006
pan-0.006
alk-0.006
brush-0.006
Token!
Token ID0
Feature activation-6.05e-01

Pos logit contributions
ind+0.027
iring+0.027
handed+0.024
ich+0.023
king+0.023
Neg logit contributions
isel-0.017
kin-0.016
 lived-0.015
 idea-0.015
pan-0.015
Token my
Token ID616
Feature activation+7.73e-02

Pos logit contributions
iring+0.012
ind+0.011
handed+0.011
 homeless+0.010
glers+0.010
Neg logit contributions
isel-0.010
 imagination-0.009
ids-0.009
pan-0.008
kin-0.008
Token r
Token ID374
Feature activation+2.59e+00

Pos logit contributions
isel+0.003
pan+0.002
kin+0.002
alk+0.002
ids+0.002
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
 cheaper-0.003
 homeless-0.003
Tokeniddles
Token ID29319
Feature activation+1.16e+00

Pos logit contributions
isel+0.107
pan+0.094
 cuc+0.091
kin+0.089
 lived+0.087
Neg logit contributions
iring-0.107
ind-0.105
 elderly-0.086
ich-0.085
handed-0.084
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
isel+0.043
pan+0.037
kin+0.037
alk+0.036
ids+0.036
Neg logit contributions
ind-0.050
iring-0.049
handed-0.043
 cheaper-0.043
 homeless-0.042
Token Are
Token ID4231
Feature activation+1.61e+00

Pos logit contributions
ind+0.008
iring+0.008
handed+0.007
 cheaper+0.007
 barking+0.007
Neg logit contributions
isel-0.007
pan-0.006
kin-0.006
alk-0.006
ids-0.005
Token you
Token ID345
Feature activation+1.68e+00

Pos logit contributions
isel+0.087
kin+0.077
ids+0.077
pan+0.077
 imagination+0.076
Neg logit contributions
iring-0.041
ind-0.041
handed-0.035
 cheaper-0.031
 homeless-0.031
Token ready
Token ID3492
Feature activation-1.32e+00

Pos logit contributions
isel+0.062
 imagination+0.053
kin+0.052
pan+0.052
ids+0.052
Neg logit contributions
ind-0.075
iring-0.074
handed-0.066
glers-0.063
 cheaper-0.061
Token?"
Token ID1701
Feature activation+1.08e+00

Pos logit contributions
iring+0.072
ind+0.072
handed+0.069
Nice+0.063
 homeless+0.061
Neg logit contributions
isel-0.034
pan-0.031
ids-0.029
kin-0.029
 imagination-0.029
Token
Token ID198
Feature activation+2.63e-01

Pos logit contributions
isel+0.028
 It+0.022
alk+0.022
pan+0.022
ids+0.021
Neg logit contributions
ind-0.060
iring-0.058
handed-0.051
 cheaper-0.051
glers-0.051
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
isel+0.008
pan+0.006
kin+0.006
alk+0.006
ids+0.006
Neg logit contributions
ind-0.013
iring-0.013
handed-0.012
 cheaper-0.012
 barking-0.011
TokenAnna
Token ID31160
Feature activation-2.22e-01

Pos logit contributions
iring+0.007
ind+0.007
 barking+0.006
handed+0.006
 cheaper+0.006
Neg logit contributions
isel-0.006
kin-0.005
pan-0.005
brush-0.005
alk-0.005
Token job
Token ID1693
Feature activation-1.52e+00

Pos logit contributions
ind+0.027
iring+0.027
handed+0.023
glers+0.023
 cheaper+0.023
Neg logit contributions
isel-0.025
 imagination-0.024
 idea-0.023
kin-0.022
alk-0.021
Token and
Token ID290
Feature activation+4.99e-01

Pos logit contributions
ind+0.083
iring+0.078
handed+0.072
ich+0.072
shadow+0.071
Neg logit contributions
isel-0.037
 imagination-0.034
kin-0.033
 idea-0.032
pan-0.032
Token he
Token ID339
Feature activation-8.76e-01

Pos logit contributions
isel+0.018
pan+0.015
 imagination+0.014
kin+0.014
alk+0.014
Neg logit contributions
ind-0.023
iring-0.022
handed-0.020
 cheaper-0.020
 homeless-0.019
Token was
Token ID373
Feature activation+3.07e-01

Pos logit contributions
iring+0.044
ind+0.043
handed+0.039
 cheaper+0.039
 barking+0.038
Neg logit contributions
isel-0.027
pan-0.021
kin-0.021
alk-0.021
 lived-0.020
Token always
Token ID1464
Feature activation-1.17e-02

Pos logit contributions
isel+0.012
pan+0.010
kin+0.010
ids+0.009
 lived+0.009
Neg logit contributions
ind-0.013
iring-0.013
handed-0.011
 cheaper-0.011
glers-0.011
Token telling
Token ID5149
Feature activation+8.46e-01

Pos logit contributions
ind+0.001
iring+0.001
glers+0.000
handed+0.000
 cheaper+0.000
Neg logit contributions
isel-0.000
kin-0.000
pan-0.000
 imagination-0.000
 idea-0.000
Token stories
Token ID3923
Feature activation+5.40e-01

Pos logit contributions
isel+0.029
 imagination+0.024
pan+0.023
alk+0.022
 idea+0.022
Neg logit contributions
ind-0.039
iring-0.039
ich-0.035
handed-0.035
 cheaper-0.034
Token.
Token ID13
Feature activation+5.45e-01

Pos logit contributions
pan+0.014
brush+0.014
aces+0.013
isel+0.013
 can+0.013
Neg logit contributions
ind-0.029
iring-0.025
handed-0.024
 homeless-0.024
ich-0.024
Token And
Token ID843
Feature activation-5.86e-01

Pos logit contributions
isel+0.022
pan+0.019
kin+0.018
ids+0.017
alk+0.017
Neg logit contributions
iring-0.022
ind-0.022
handed-0.019
 barking-0.019
 cheaper-0.019
Token that
Token ID326
Feature activation+5.04e-01

Pos logit contributions
ind+0.028
iring+0.025
handed+0.024
 cheaper+0.022
 homeless+0.022
Neg logit contributions
isel-0.021
 imagination-0.018
 lived-0.017
kin-0.017
alk-0.017
Token is
Token ID318
Feature activation+1.01e-01

Pos logit contributions
isel+0.016
kin+0.013
alk+0.013
pan+0.013
 imagination+0.013
Neg logit contributions
ind-0.024
iring-0.024
handed-0.022
 cheaper-0.021
 homeless-0.021
Token mill
Token ID3939
Feature activation+6.73e-01

Pos logit contributions
isel+0.015
pan+0.012
kin+0.012
alk+0.012
 imagination+0.012
Neg logit contributions
iring-0.018
ind-0.018
handed-0.017
 cheaper-0.016
 homeless-0.015
Token near
Token ID1474
Feature activation+2.92e-01

Pos logit contributions
isel+0.025
pan+0.024
kin+0.022
brush+0.022
alk+0.021
Neg logit contributions
ind-0.028
iring-0.027
handed-0.024
 cheaper-0.023
 homeless-0.023
Token his
Token ID465
Feature activation-8.66e-01

Pos logit contributions
isel+0.006
 It+0.005
 idea+0.005
alk+0.005
 lived+0.004
Neg logit contributions
ll-0.017
ind-0.016
iring-0.016
itating-0.016
shadow-0.015
Token house
Token ID2156
Feature activation+1.29e-01

Pos logit contributions
iring+0.041
ind+0.039
shadow+0.038
glers+0.038
 cheaper+0.036
Neg logit contributions
isel-0.025
 imagination-0.024
alk-0.023
 ear-0.022
kin-0.021
Token.
Token ID13
Feature activation-5.10e-01

Pos logit contributions
isel+0.004
pan+0.003
kin+0.003
alk+0.003
brush+0.003
Neg logit contributions
ind-0.007
iring-0.006
handed-0.006
 homeless-0.006
 cheaper-0.006
Token The
Token ID383
Feature activation+1.98e-01

Pos logit contributions
ind+0.023
iring+0.023
handed+0.020
 cheaper+0.020
 barking+0.020
Neg logit contributions
isel-0.018
pan-0.015
kin-0.014
alk-0.014
ids-0.014
Token mill
Token ID3939
Feature activation+4.00e-01

Pos logit contributions
isel+0.009
pan+0.008
alk+0.008
kin+0.008
ids+0.007
Neg logit contributions
ind-0.007
iring-0.007
 cheaper-0.006
 elderly-0.006
 homeless-0.006
Token has
Token ID468
Feature activation+1.36e-01

Pos logit contributions
isel+0.014
pan+0.012
kin+0.011
alk+0.011
ids+0.011
Neg logit contributions
ind-0.018
iring-0.018
handed-0.016
 cheaper-0.016
 barking-0.016
Token a
Token ID257
Feature activation+9.08e-02

Pos logit contributions
isel+0.005
pan+0.004
alk+0.004
ids+0.004
kin+0.004
Neg logit contributions
ind-0.006
iring-0.006
handed-0.005
 barking-0.005
 cheaper-0.005
Token wheel
Token ID7825
Feature activation+7.61e-01

Pos logit contributions
isel+0.004
pan+0.003
kin+0.003
alk+0.003
brush+0.003
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
 cheaper-0.003
 faster-0.003
Token that
Token ID326
Feature activation+1.26e-01

Pos logit contributions
isel+0.024
brush+0.022
pan+0.022
aces+0.021
ids+0.021
Neg logit contributions
ind-0.037
iring-0.034
handed-0.034
 homeless-0.032
 cheaper-0.030
Token the
Token ID262
Feature activation+3.11e-01

Pos logit contributions
isel+0.006
pan+0.005
kin+0.005
ily+0.005
ids+0.005
Neg logit contributions
ind-0.011
iring-0.011
 barking-0.010
 cheaper-0.010
handed-0.010
Token paper
Token ID3348
Feature activation+8.71e-01

Pos logit contributions
kin+0.009
pan+0.009
isel+0.009
brush+0.009
 imagination+0.008
Neg logit contributions
iring-0.015
ind-0.014
 barking-0.012
shadow-0.012
itating-0.012
Token into
Token ID656
Feature activation+6.95e-01

Pos logit contributions
isel+0.037
pan+0.034
kin+0.033
alk+0.032
ids+0.031
Neg logit contributions
iring-0.032
ind-0.032
handed-0.028
 cheaper-0.028
 homeless-0.027
Token the
Token ID262
Feature activation-2.28e-01

Pos logit contributions
isel+0.020
pan+0.018
kin+0.017
 imagination+0.016
alk+0.016
Neg logit contributions
ind-0.035
iring-0.035
ll-0.032
itating-0.032
ich-0.031
Token pocket
Token ID10000
Feature activation-7.45e-01

Pos logit contributions
iring+0.011
ind+0.010
ll+0.009
shadow+0.009
itating+0.009
Neg logit contributions
isel-0.007
pan-0.007
kin-0.007
brush-0.006
 imagination-0.006
Token of
Token ID286
Feature activation-1.40e+00

Pos logit contributions
ind+0.037
iring+0.036
 barking+0.033
 homeless+0.031
Nice+0.031
Neg logit contributions
isel-0.021
pan-0.021
kin-0.020
brush-0.019
alk-0.019
Token her
Token ID607
Feature activation+2.79e-01

Pos logit contributions
iring+0.070
ind+0.069
itating+0.062
handed+0.062
ll+0.059
Neg logit contributions
isel-0.044
kin-0.038
 imagination-0.037
pan-0.036
alk-0.035
Token dress
Token ID6576
Feature activation+1.47e-01

Pos logit contributions
isel+0.009
kin+0.009
 imagination+0.008
alk+0.008
ids+0.008
Neg logit contributions
iring-0.013
ind-0.013
itating-0.012
glers-0.011
handed-0.011
Token and
Token ID290
Feature activation-1.56e-01

Pos logit contributions
pan+0.004
kin+0.004
brush+0.004
isel+0.004
aces+0.004
Neg logit contributions
ind-0.007
iring-0.007
 barking-0.006
 homeless-0.006
handed-0.006
Token shut
Token ID4423
Feature activation-3.55e-02

Pos logit contributions
ind+0.008
iring+0.008
handed+0.007
 cheaper+0.007
itating+0.007
Neg logit contributions
isel-0.005
kin-0.004
pan-0.004
 imagination-0.004
ids-0.004
Token the
Token ID262
Feature activation+2.41e-01

Pos logit contributions
iring+0.002
ind+0.002
handed+0.002
 homeless+0.002
glers+0.002
Neg logit contributions
isel-0.001
pan-0.001
ids-0.001
kin-0.001
brush-0.001
Token.
Token ID13
Feature activation+4.37e-01

Pos logit contributions
isel+0.025
kin+0.023
alk+0.022
pan+0.021
 cuc+0.021
Neg logit contributions
iring-0.040
ind-0.040
 fastest-0.035
ich-0.035
handed-0.034
Token He
Token ID679
Feature activation+8.04e-01

Pos logit contributions
isel+0.014
pan+0.011
kin+0.011
alk+0.011
ids+0.011
Neg logit contributions
ind-0.021
iring-0.021
handed-0.019
 cheaper-0.019
 barking-0.018
Token knew
Token ID2993
Feature activation+9.80e-01

Pos logit contributions
isel+0.026
kin+0.021
pan+0.020
alk+0.020
 lived+0.020
Neg logit contributions
ind-0.039
iring-0.039
handed-0.035
 cheaper-0.034
 barking-0.034
Token that
Token ID326
Feature activation+1.80e-01

Pos logit contributions
isel+0.035
pan+0.029
 lived+0.028
kin+0.028
 imagination+0.027
Neg logit contributions
ind-0.045
iring-0.040
handed-0.038
 barking-0.038
glers-0.038
Token no
Token ID645
Feature activation+3.78e-02

Pos logit contributions
isel+0.006
pan+0.005
kin+0.005
 imagination+0.005
alk+0.005
Neg logit contributions
ind-0.008
iring-0.008
handed-0.007
 cheaper-0.007
 barking-0.007
Token matter
Token ID2300
Feature activation-8.24e-01

Pos logit contributions
isel+0.001
 idea+0.001
 imagination+0.001
kin+0.001
 nod+0.001
Neg logit contributions
iring-0.002
ind-0.002
 concession-0.002
glers-0.002
handed-0.002
Token how
Token ID703
Feature activation+1.36e+00

Pos logit contributions
ind+0.042
iring+0.041
handed+0.040
 homeless+0.038
 cheaper+0.038
Neg logit contributions
isel-0.024
alk-0.019
 lived-0.018
 imagination-0.018
pan-0.018
Token confused
Token ID10416
Feature activation+1.08e+00

Pos logit contributions
isel+0.058
alk+0.049
 imagination+0.046
pan+0.044
 cuc+0.044
Neg logit contributions
ind-0.052
iring-0.049
handed-0.045
 barking-0.045
glers-0.044
Token he
Token ID339
Feature activation-3.91e-01

Pos logit contributions
isel+0.036
pan+0.030
kin+0.029
alk+0.028
 imagination+0.028
Neg logit contributions
ind-0.051
iring-0.050
handed-0.046
 cheaper-0.044
 barking-0.043
Token might
Token ID1244
Feature activation+5.12e-02

Pos logit contributions
ind+0.022
iring+0.021
 barking+0.019
handed+0.019
 cheaper+0.019
Neg logit contributions
isel-0.010
 lived-0.008
kin-0.008
alk-0.007
aces-0.007
Token be
Token ID307
Feature activation-1.90e-01

Pos logit contributions
isel+0.002
alk+0.001
pan+0.001
kin+0.001
ids+0.001
Neg logit contributions
ind-0.003
iring-0.003
handed-0.002
 cheaper-0.002
 barking-0.002
Token,
Token ID11
Feature activation+8.38e-01

Pos logit contributions
isel+0.025
pan+0.023
kin+0.022
 idea+0.020
 lived+0.019
Neg logit contributions
ind-0.093
iring-0.087
handed-0.086
ograph-0.084
 homeless-0.083
Token he
Token ID339
Feature activation-3.21e-01

Pos logit contributions
isel+0.028
pan+0.023
 It+0.022
 imagination+0.022
 lived+0.022
Neg logit contributions
ind-0.043
iring-0.038
handed-0.036
 cheaper-0.035
glers-0.033
Token quickly
Token ID2952
Feature activation+6.25e-01

Pos logit contributions
iring+0.017
ind+0.017
handed+0.016
 cheaper+0.015
 homeless+0.015
Neg logit contributions
isel-0.009
 lived-0.007
kin-0.007
pan-0.007
ids-0.007
Token z
Token ID1976
Feature activation+9.27e-01

Pos logit contributions
isel+0.020
pan+0.016
kin+0.015
alk+0.015
ids+0.015
Neg logit contributions
iring-0.032
ind-0.032
handed-0.028
 cheaper-0.027
 homeless-0.027
Tokenipped
Token ID3949
Feature activation+3.64e-01

Pos logit contributions
isel+0.043
pan+0.037
alk+0.036
kin+0.036
ids+0.035
Neg logit contributions
ind-0.032
iring-0.032
handed-0.027
 cheaper-0.027
 barking-0.027
Token up
Token ID510
Feature activation-2.81e-01

Pos logit contributions
isel+0.013
pan+0.011
 It+0.011
 imagination+0.010
 idea+0.010
Neg logit contributions
ind-0.017
iring-0.017
handed-0.015
ich-0.015
 homeless-0.015
Token his
Token ID465
Feature activation+1.89e-01

Pos logit contributions
ind+0.015
iring+0.015
ich+0.014
handed+0.013
ograph+0.013
Neg logit contributions
isel-0.007
pan-0.007
alk-0.006
 imagination-0.006
kin-0.006
Token fur
Token ID9230
Feature activation+1.10e+00

Pos logit contributions
 imagination+0.006
kin+0.005
isel+0.005
 idea+0.005
aces+0.005
Neg logit contributions
iring-0.010
ind-0.009
handed-0.009
itating-0.008
 homeless-0.008
Token and
Token ID290
Feature activation+3.34e-01

Pos logit contributions
pan+0.034
isel+0.033
kin+0.032
brush+0.031
aces+0.030
Neg logit contributions
ind-0.054
iring-0.051
 homeless-0.047
 cheaper-0.046
handed-0.046
Token hopped
Token ID45230
Feature activation-2.48e-01

Pos logit contributions
isel+0.009
pan+0.008
 lived+0.008
 imagination+0.007
kin+0.007
Neg logit contributions
ind-0.019
iring-0.018
handed-0.016
 homeless-0.015
 cheaper-0.015
Token off
Token ID572
Feature activation+3.32e-02

Pos logit contributions
ind+0.010
iring+0.010
handed+0.009
 homeless+0.009
ich+0.009
Neg logit contributions
isel-0.010
pan-0.009
kin-0.009
ids-0.008
alk-0.008
Token something
Token ID1223
Feature activation-3.24e-01

Pos logit contributions
ind+0.014
iring+0.013
handed+0.013
ich+0.013
 sidelines+0.012
Neg logit contributions
isel-0.010
pan-0.010
alk-0.010
 imagination-0.010
 idea-0.010
Token new
Token ID649
Feature activation-1.01e+00

Pos logit contributions
ind+0.009
handed+0.008
 sidelines+0.008
ich+0.007
iring+0.007
Neg logit contributions
 idea-0.016
isel-0.015
 imagination-0.015
 can-0.015
alk-0.014
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
ind+0.044
iring+0.042
handed+0.038
 homeless+0.037
 cheaper+0.037
Neg logit contributions
isel-0.038
alk-0.032
pan-0.032
kin-0.032
ids-0.030
Token She
Token ID1375
Feature activation+3.88e-01

Pos logit contributions
iring+0.006
ind+0.006
 elderly+0.005
 cheaper+0.005
 barking+0.005
Neg logit contributions
isel-0.005
kin-0.005
pan-0.004
ids-0.004
brush-0.004
Token would
Token ID561
Feature activation-1.12e+00

Pos logit contributions
isel+0.014
pan+0.011
kin+0.011
alk+0.011
ids+0.010
Neg logit contributions
ind-0.018
iring-0.017
 cheaper-0.016
 faster-0.015
 barking-0.015
Token learn
Token ID2193
Feature activation-3.39e-01

Pos logit contributions
ind+0.048
iring+0.046
 barking+0.042
 cheaper+0.042
 faster+0.042
Neg logit contributions
isel-0.042
kin-0.035
pan-0.034
alk-0.033
ids-0.032
Token how
Token ID703
Feature activation+4.11e-01

Pos logit contributions
ind+0.015
handed+0.014
iring+0.013
ich+0.013
 concession+0.013
Neg logit contributions
isel-0.011
alk-0.010
 imagination-0.010
pan-0.010
 idea-0.010
Token to
Token ID284
Feature activation-3.69e-01

Pos logit contributions
isel+0.018
alk+0.015
pan+0.015
 imagination+0.015
ids+0.014
Neg logit contributions
ind-0.015
iring-0.015
handed-0.013
 barking-0.012
 cheaper-0.012
Token count
Token ID954
Feature activation-5.16e-01

Pos logit contributions
ind+0.017
iring+0.017
handed+0.015
 cheaper+0.015
 barking+0.015
Neg logit contributions
isel-0.012
pan-0.010
kin-0.010
alk-0.010
ids-0.009
Token and
Token ID290
Feature activation+7.06e-01

Pos logit contributions
handed+0.024
ind+0.024
iring+0.023
 homeless+0.022
 concession+0.021
Neg logit contributions
isel-0.016
alk-0.014
pan-0.014
ids-0.014
aces-0.014
Token how
Token ID703
Feature activation+7.20e-01

Pos logit contributions
isel+0.025
pan+0.020
alk+0.020
 imagination+0.019
ids+0.019
Neg logit contributions
ind-0.033
iring-0.032
handed-0.029
 homeless-0.028
 cheaper-0.028
Token this
Token ID428
Feature activation+1.06e+00

Pos logit contributions
ind+0.037
iring+0.034
handed+0.031
 barking+0.030
glers+0.030
Neg logit contributions
isel-0.028
kin-0.024
pan-0.022
 lived-0.022
 imagination-0.021
Token time
Token ID640
Feature activation-5.39e-01

Pos logit contributions
isel+0.035
pan+0.028
kin+0.028
alk+0.027
ids+0.026
Neg logit contributions
ind-0.051
iring-0.051
handed-0.045
 cheaper-0.045
 barking-0.045
Token it
Token ID340
Feature activation+1.31e-01

Pos logit contributions
ind+0.028
iring+0.026
handed+0.023
itating+0.023
ich+0.023
Neg logit contributions
isel-0.017
kin-0.014
 lived-0.014
pan-0.014
ids-0.013
Token did
Token ID750
Feature activation+5.66e-01

Pos logit contributions
isel+0.004
kin+0.003
pan+0.003
 lived+0.003
alk+0.003
Neg logit contributions
ind-0.007
iring-0.007
handed-0.006
 cheaper-0.006
 barking-0.006
Token not
Token ID407
Feature activation-2.32e-01

Pos logit contributions
isel+0.023
kin+0.020
pan+0.020
alk+0.019
 imagination+0.018
Neg logit contributions
ind-0.024
iring-0.023
handed-0.020
ich-0.019
 elderly-0.019
Token taste
Token ID6938
Feature activation-2.63e+00

Pos logit contributions
ind+0.012
iring+0.012
handed+0.010
 cheaper+0.010
 barking+0.010
Neg logit contributions
isel-0.007
pan-0.006
kin-0.006
alk-0.006
ids-0.005
Token good
Token ID922
Feature activation-5.76e-01

Pos logit contributions
ind+0.123
iring+0.118
ich+0.115
handed+0.112
 concession+0.107
Neg logit contributions
isel-0.090
kin-0.073
 idea-0.072
alk-0.072
 cuc-0.071
Token.
Token ID13
Feature activation+4.90e-01

Pos logit contributions
ind+0.025
iring+0.024
handed+0.022
 homeless+0.021
ich+0.021
Neg logit contributions
isel-0.022
pan-0.018
alk-0.018
kin-0.018
 imagination-0.017
Token
Token ID220
Feature activation-8.07e-01

Pos logit contributions
isel+0.018
pan+0.015
kin+0.014
alk+0.014
ids+0.014
Neg logit contributions
ind-0.022
iring-0.022
handed-0.019
 cheaper-0.019
 barking-0.019
Token
Token ID198
Feature activation+1.79e-01

Pos logit contributions
ind+0.038
iring+0.037
 cheaper+0.033
handed+0.033
 barking+0.033
Neg logit contributions
isel-0.027
pan-0.022
alk-0.022
kin-0.021
ids-0.021
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
isel+0.006
pan+0.005
kin+0.005
alk+0.005
ids+0.005
Neg logit contributions
ind-0.008
iring-0.008
handed-0.007
 cheaper-0.007
 barking-0.007
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
isel+0.019
pan+0.017
kin+0.016
alk+0.016
ids+0.015
Neg logit contributions
ind-0.021
iring-0.021
handed-0.018
 cheaper-0.018
 homeless-0.018
Token They
Token ID1119
Feature activation+3.30e-01

Pos logit contributions
ind+0.010
iring+0.010
handed+0.009
 homeless+0.009
 cheaper+0.008
Neg logit contributions
isel-0.006
pan-0.005
kin-0.005
alk-0.005
ids-0.005
Token picked
Token ID6497
Feature activation+3.58e-02

Pos logit contributions
isel+0.016
alk+0.014
pan+0.013
kin+0.013
ids+0.013
Neg logit contributions
iring-0.010
ind-0.010
 cheaper-0.010
 elderly-0.009
glers-0.009
Token the
Token ID262
Feature activation-1.03e-01

Pos logit contributions
isel+0.001
pan+0.001
kin+0.001
alk+0.001
ids+0.001
Neg logit contributions
ind-0.001
iring-0.001
handed-0.001
 barking-0.001
 cheaper-0.001
Token prett
Token ID46442
Feature activation-7.25e-01

Pos logit contributions
ind+0.004
iring+0.004
 cheaper+0.004
 faster+0.003
 elderly+0.003
Neg logit contributions
isel-0.004
pan-0.004
alk-0.004
kin-0.004
ids-0.003
Tokeniest
Token ID6386
Feature activation-1.94e+00

Pos logit contributions
iring+0.025
ind+0.023
 cheaper+0.021
 faster+0.020
glers+0.020
Neg logit contributions
isel-0.033
pan-0.029
alk-0.028
AAAA-0.027
 imagination-0.027
Token pe
Token ID613
Feature activation+1.65e+00

Pos logit contributions
ind+0.084
iring+0.083
 cheaper+0.074
handed+0.073
 faster+0.072
Neg logit contributions
isel-0.073
pan-0.061
alk-0.059
kin-0.059
ids-0.057
Tokenb
Token ID65
Feature activation+1.00e+00

Pos logit contributions
isel+0.088
pan+0.078
alk+0.076
kin+0.076
 imagination+0.073
Neg logit contributions
ind-0.045
iring-0.045
 cheaper-0.037
 faster-0.035
handed-0.034
Tokenbles
Token ID7689
Feature activation+7.21e-01

Pos logit contributions
isel+0.048
pan+0.042
alk+0.041
 imagination+0.040
kin+0.039
Neg logit contributions
iring-0.034
ind-0.031
ich-0.027
 faster-0.026
 cheaper-0.026
Token and
Token ID290
Feature activation+3.11e-02

Pos logit contributions
isel+0.026
pan+0.023
kin+0.023
alk+0.022
ids+0.022
Neg logit contributions
ind-0.032
iring-0.031
handed-0.028
 barking-0.027
 homeless-0.027
Token started
Token ID2067
Feature activation+7.65e-02

Pos logit contributions
isel+0.001
pan+0.001
kin+0.001
alk+0.001
ids+0.001
Neg logit contributions
ind-0.002
iring-0.001
handed-0.001
 barking-0.001
 cheaper-0.001
Token close
Token ID1969
Feature activation-5.31e-01

Pos logit contributions
ind+0.019
iring+0.018
 cheaper+0.017
 faster+0.017
 barking+0.017
Neg logit contributions
isel-0.016
pan-0.013
alk-0.013
kin-0.013
aces-0.012
Token the
Token ID262
Feature activation-3.69e-01

Pos logit contributions
ind+0.023
iring+0.023
handed+0.021
 homeless+0.020
 cheaper+0.020
Neg logit contributions
isel-0.020
pan-0.017
alk-0.016
ids-0.016
kin-0.016
Token cabinet
Token ID13447
Feature activation+3.64e-01

Pos logit contributions
iring+0.012
ind+0.012
 cheaper+0.010
handed+0.010
 barking+0.010
Neg logit contributions
isel-0.018
pan-0.015
kin-0.015
alk-0.015
ids-0.014
Token doors
Token ID8215
Feature activation+9.21e-01

Pos logit contributions
isel+0.014
pan+0.012
kin+0.012
alk+0.012
ids+0.011
Neg logit contributions
ind-0.015
iring-0.015
handed-0.013
 homeless-0.013
 barking-0.013
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
isel+0.035
pan+0.030
kin+0.029
alk+0.029
ids+0.028
Neg logit contributions
ind-0.040
iring-0.038
handed-0.035
 homeless-0.034
 barking-0.034
Token look
Token ID804
Feature activation-1.94e+00

Pos logit contributions
iring+0.020
ind+0.020
 cheaper+0.018
 faster+0.018
 homeless+0.018
Neg logit contributions
isel-0.017
pan-0.014
alk-0.013
kin-0.013
ids-0.013
Token at
Token ID379
Feature activation+4.07e-01

Pos logit contributions
ind+0.077
iring+0.075
handed+0.070
 barking+0.065
 homeless+0.065
Neg logit contributions
isel-0.079
pan-0.066
kin-0.064
ids-0.064
alk-0.063
Token the
Token ID262
Feature activation-8.04e-01

Pos logit contributions
isel+0.013
pan+0.011
 imagination+0.011
kin+0.010
alk+0.010
Neg logit contributions
ind-0.019
iring-0.019
handed-0.018
shadow-0.018
 barking-0.017
Token things
Token ID1243
Feature activation-3.85e-02

Pos logit contributions
ind+0.034
iring+0.032
handed+0.030
 barking+0.030
shadow+0.030
Neg logit contributions
isel-0.029
pan-0.026
kin-0.025
brush-0.025
 idea-0.024
Token inside
Token ID2641
Feature activation-5.59e-01

Pos logit contributions
ind+0.002
iring+0.002
handed+0.002
 barking+0.002
 homeless+0.002
Neg logit contributions
isel-0.001
pan-0.001
kin-0.001
brush-0.001
ids-0.001
Token.
Token ID13
Feature activation-6.43e-02

Pos logit contributions
ind+0.030
iring+0.028
shadow+0.027
handed+0.027
ich+0.027
Neg logit contributions
isel-0.014
kin-0.012
 are-0.012
pan-0.012
 lived-0.012
Token and
Token ID290
Feature activation-4.07e-01

Pos logit contributions
ich+0.042
iring+0.041
ind+0.040
 sidelines+0.039
handed+0.039
Neg logit contributions
 idea-0.022
 lived-0.020
isel-0.020
 imagination-0.019
 It-0.018
Token he
Token ID339
Feature activation-1.39e+00

Pos logit contributions
ind+0.018
iring+0.018
handed+0.016
 cheaper+0.016
 barking+0.016
Neg logit contributions
isel-0.015
pan-0.012
kin-0.012
alk-0.012
ids-0.011
Token was
Token ID373
Feature activation-8.70e-02

Pos logit contributions
ind+0.067
iring+0.065
 cheaper+0.059
handed+0.059
 barking+0.059
Neg logit contributions
isel-0.046
pan-0.037
alk-0.036
kin-0.036
ids-0.034
Token always
Token ID1464
Feature activation-3.93e-01

Pos logit contributions
iring+0.003
ind+0.003
handed+0.003
 cheaper+0.003
 barking+0.003
Neg logit contributions
isel-0.004
pan-0.003
kin-0.003
ids-0.003
 imagination-0.003
Token looking
Token ID2045
Feature activation-8.69e-01

Pos logit contributions
ind+0.017
iring+0.017
handed+0.017
glers+0.016
 sidelines+0.015
Neg logit contributions
isel-0.012
kin-0.011
 lived-0.010
 idea-0.010
pan-0.010
Token forward
Token ID2651
Feature activation-2.10e+00

Pos logit contributions
ind+0.037
handed+0.036
iring+0.036
glers+0.035
ich+0.035
Neg logit contributions
isel-0.030
 imagination-0.024
 idea-0.024
 cuc-0.022
ids-0.022
Token to
Token ID284
Feature activation+3.72e-02

Pos logit contributions
ind+0.093
iring+0.089
handed+0.088
glers+0.087
 homeless+0.085
Neg logit contributions
isel-0.068
 imagination-0.060
alk-0.059
pan-0.058
ids-0.058
Token his
Token ID465
Feature activation-7.53e-01

Pos logit contributions
isel+0.001
 imagination+0.001
 lived+0.001
 idea+0.001
alk+0.001
Neg logit contributions
iring-0.002
ind-0.002
handed-0.001
glers-0.001
itating-0.001
Token next
Token ID1306
Feature activation+7.62e-01

Pos logit contributions
handed+0.031
iring+0.030
shadow+0.029
glers+0.029
 sidelines+0.029
Neg logit contributions
 imagination-0.026
 idea-0.024
 lived-0.022
 gard-0.021
 name-0.021
Token adventure
Token ID8855
Feature activation-1.99e-01

Pos logit contributions
isel+0.026
 imagination+0.024
alk+0.022
 idea+0.022
pan+0.021
Neg logit contributions
iring-0.034
ind-0.031
handed-0.030
 homeless-0.029
shadow-0.028
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
iring+0.012
ind+0.012
itating+0.012
shadow+0.012
iqu+0.012
Neg logit contributions
aces-0.002
 idea-0.002
 lived-0.002
ily-0.001
 guys-0.001
Token the
Token ID262
Feature activation+1.69e-01

Pos logit contributions
isel+0.001
pan+0.001
kin+0.001
alk+0.001
ids+0.001
Neg logit contributions
ind-0.002
iring-0.002
handed-0.001
 cheaper-0.001
 barking-0.001
Token little
Token ID1310
Feature activation+7.37e-02

Pos logit contributions
isel+0.005
kin+0.004
 imagination+0.004
pan+0.004
 cuc+0.004
Neg logit contributions
iring-0.009
ind-0.009
handed-0.008
 barking-0.007
shadow-0.007
Token girl
Token ID2576
Feature activation-2.54e-01

Pos logit contributions
isel+0.002
pan+0.002
kin+0.002
 imagination+0.002
 idea+0.002
Neg logit contributions
ind-0.004
iring-0.004
handed-0.003
 barking-0.003
shadow-0.003
Token enjoyed
Token ID8359
Feature activation+3.86e-01

Pos logit contributions
iring+0.014
ind+0.014
handed+0.012
 cheaper+0.012
 homeless+0.012
Neg logit contributions
isel-0.007
 lived-0.006
pan-0.005
 imagination-0.005
ids-0.005
Token the
Token ID262
Feature activation-1.32e-01

Pos logit contributions
isel+0.014
kin+0.012
pan+0.012
 imagination+0.011
alk+0.011
Neg logit contributions
iring-0.017
ind-0.017
handed-0.015
 cheaper-0.015
itating-0.014
Token rest
Token ID1334
Feature activation-2.15e+00

Pos logit contributions
ind+0.005
iring+0.005
shadow+0.004
 barking+0.004
handed+0.004
Neg logit contributions
isel-0.005
 idea-0.005
kin-0.005
 imagination-0.005
 nod-0.005
Token of
Token ID286
Feature activation-1.13e+00

Pos logit contributions
ind+0.105
iring+0.098
handed+0.093
 homeless+0.093
 cheaper+0.092
Neg logit contributions
kin-0.065
isel-0.063
pan-0.059
aces-0.054
alk-0.053
Token their
Token ID511
Feature activation+2.34e-01

Pos logit contributions
iring+0.057
ind+0.055
handed+0.049
itating+0.048
 cheaper+0.048
Neg logit contributions
isel-0.036
pan-0.031
kin-0.030
alk-0.030
 imagination-0.029
Token day
Token ID1110
Feature activation-1.04e+00

Pos logit contributions
 imagination+0.007
isel+0.007
kin+0.006
 lived+0.006
 idea+0.006
Neg logit contributions
iring-0.011
ind-0.010
itating-0.010
handed-0.010
shadow-0.010
Token in
Token ID287
Feature activation+7.63e-01

Pos logit contributions
ind+0.050
iring+0.050
handed+0.047
 cheaper+0.046
oma+0.045
Neg logit contributions
isel-0.026
kin-0.025
 imagination-0.025
alk-0.024
aces-0.024
Token the
Token ID262
Feature activation-3.29e-01

Pos logit contributions
isel+0.023
 imagination+0.021
pan+0.021
alk+0.020
kin+0.020
Neg logit contributions
iring-0.039
ind-0.038
ich-0.033
handed-0.033
shadow-0.032