Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to Senate procedures and political maneuvering

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disagre
    -1.51
     impra
    -1.51
     unspeak
    -1.48
     unwarran
    -1.45
     reluct
    -1.44
     ecru
    -1.43
     indestru
    -1.42
     swarovski
    -1.41
     Ename
    -1.40
     indescri
    -1.39
    POSITIVE LOGITS
     Demokrat
    0.78
     legislat
    0.72
     Demok
    0.71
     Republi
    0.69
     parlamentar
    0.69
     Ukraina
    0.69
     Parlament
    0.67
     fisk
    0.66
     parlament
    0.65
     Senat
    0.65
    Act Density 0.662%

    No Known Activations