INDEX
Explanations
references to congressional representatives and their party affiliations
New Auto-Interp
Negative Logits
صوتيه
-0.77
.}\
-0.70
","\
-0.66
__":
-0.64
]**
-0.63
malink
-0.60
الحره
-0.60
]--;
-0.60
istible
-0.60
]='\
-0.60
POSITIVE LOGITS
&___
0.64
permett
0.60
ProtoMessage
0.58
commerciaux
0.57
sonore
0.57
featureID
0.55
WaitForSeconds
0.55
Erfolge
0.54
brev
0.52
gambe
0.52
Activations Density 0.004%