INDEX
Explanations
phrases indicating contrast or opposing perspectives
the word "as" used in various contexts
New Auto-Interp
Negative Logits
constitu
-0.74
OY
-0.71
Ess
-0.68
Republic
-0.65
eri
-0.65
asus
-0.64
OE
-0.64
uko
-0.63
ondo
-0.63
utical
-0.62
POSITIVE LOGITS
pired
0.85
regards
0.67
opposed
0.66
brates
0.66
tensions
0.65
sparing
0.64
contrasted
0.63
intensely
0.62
acknowledging
0.61
evidenced
0.60
Activations Density 0.025%