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

    Neuronpedia

    INDEX
    Explanations

    political action groups and organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     probabilities
    -0.80
     rumours
    -0.80
     circumst
    -0.78
     humour
    -0.75
    gue
    -0.74
     simulator
    -0.73
     lapse
    -0.70
     disg
    -0.69
     puzz
    -0.69
     landfall
    -0.68
    POSITIVE LOGITS
     Coalition
    1.09
     Alliance
    0.98
     Fund
    0.98
    Choice
    0.94
     Initiative
    0.94
     Caucus
    0.92
     Solutions
    0.90
     Advoc
    0.89
     Voters
    0.89
     Agenda
    0.88
    Act Density 0.255%

    No Known Activations