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

    Neuronpedia

    INDEX
    Explanations

    official announcements or information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.80
    esville
    -0.80
    bane
    -0.72
    ï¸
    -0.71
    ertodd
    -0.70
    lust
    -0.69
    rums
    -0.69
    ulz
    -0.68
    =-=-
    -0.68
    Phones
    -0.66
    POSITIVE LOGITS
    dom
    1.04
     sanctioned
    0.99
    ities
    0.91
     confirmation
    0.81
     announcement
    0.80
     sanction
    0.79
    ised
    0.78
     acknowledgement
    0.77
    achable
    0.77
     documentation
    0.73
    Act Density 0.587%

    No Known Activations