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

    Neuronpedia

    INDEX
    Explanations

    ellipses and phrases indicating further reading or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Graves
    -0.18
    ield
    -0.16
    bidden
    -0.14
    ousel
    -0.13
     Alfred
    -0.13
    :Boolean
    -0.13
    Ñīи
    -0.13
    atee
    -0.13
    lag
    -0.13
    üf
    -0.13
    POSITIVE LOGITS
    GetMethod
    0.15
    yor
    0.15
    UIScreen
    0.15
    izza
    0.15
    abr
    0.14
     mastur
    0.14
    SOLE
    0.14
    abler
    0.14
    etler
    0.14
     Gle
    0.14
    Act Density 0.014%

    No Known Activations