INDEX
Explanations
the name "Arnold"
mentions of the name "Arnold," particularly in contexts related to prominent individuals
New Auto-Interp
Negative Logits
phis
-0.79
orthy
-0.76
meet
-0.74
keeper
-0.72
ban
-0.72
rieve
-0.68
fal
-0.68
erald
-0.68
keepers
-0.67
awks
-0.67
POSITIVE LOGITS
Schwarzenegger
1.45
enegger
1.09
Arnold
0.85
Recall
0.75
ingly
0.73
horizont
0.72
Muscle
0.70
Rove
0.70
Reloaded
0.70
sson
0.69
Activations Density 0.062%