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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant events or actions related to various groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to crises or severe societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pocket
    -0.77
    yt
    -0.73
     purs
    -0.69
    èĢħ
    -0.65
    ettings
    -0.65
     DV
    -0.65
     Dek
    -0.63
     Hollow
    -0.63
     Mew
    -0.63
     Xan
    -0.63
    POSITIVE LOGITS
    FILE
    1.00
    PASS
    0.85
    Asked
    0.82
    ussed
    0.80
    Specifically
    0.79
    Id
    0.79
    illed
    0.78
    ccording
    0.77
    Ur
    0.75
    Its
    0.73
    Act Density 0.113%

    No Known Activations