INDEX
Explanations
verbs related to physical movement, particularly running
instances of the word "ran" indicating movement or escape
New Auto-Interp
Negative Logits
ortium
-0.84
Lauder
-0.70
olia
-0.67
matured
-0.65
omical
-0.65
ongyang
-0.65
immature
-0.64
artisan
-0.62
yet
-0.62
afort
-0.61
POSITIVE LOGITS
Runner
0.85
running
0.84
swick
0.84
rampant
0.81
escape
0.79
ners
0.77
gs
0.76
Running
0.75
NING
0.74
RUN
0.74
Activations Density 0.043%