INDEX
Explanations
phrases describing individuals or groups that have been impacted or affected by various events
New Auto-Interp
Negative Logits
'gc
-0.18
respondsToSelector
-0.15
impse
-0.15
okie
-0.15
Greater
-0.14
ech
-0.14
peat
-0.14
PARSE
-0.14
bru
-0.13
Battery
-0.13
POSITIVE LOGITS
tob
0.16
Sesso
0.15
such
0.14
fed
0.14
agine
0.14
icos
0.14
Tob
0.13
Pron
0.13
tok
0.13
abyrin
0.13
Activations Density 0.023%