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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter usernames or handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Enabled
    -0.71
     LIMITED
    -0.71
     ACTIONS
    -0.68
     CONTROL
    -0.67
     Islamists
    -0.66
     AFB
    -0.63
     FAC
    -0.61
     Ninth
    -0.61
     excess
    -0.60
     Scheme
    -0.59
    POSITIVE LOGITS
    rentice
    0.93
    yp
    0.92
    veyard
    0.88
    _
    0.83
    rick
    0.82
    CBC
    0.79
    Bow
    0.79
    onge
    0.78
    anie
    0.77
    neys
    0.77
    Act Density 0.088%

    No Known Activations