INDEX
Explanations
adjectives related to height
references to "tall" in various contexts
New Auto-Interp
Negative Logits
lde
-0.84
eering
-0.83
eer
-0.81
vous
-0.73
vernment
-0.73
Wonderland
-0.72
actionDate
-0.71
ller
-0.70
eers
-0.70
IRO
-0.70
POSITIVE LOGITS
stature
1.09
taller
0.93
tallest
0.93
ies
0.89
itect
0.84
Tall
0.84
towers
0.82
itude
0.82
tales
0.81
owed
0.78
Activations Density 0.024%