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

    Neuronpedia

    INDEX
    Explanations

    names related to different people

    oai_token-act-pair · gpt-3.5-turbo

    elements related to specific names or titles in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.67
    Versions
    -0.64
    ascript
    -0.63
    tyard
    -0.61
    itutes
    -0.60
    rique
    -0.60
    theless
    -0.60
    ancial
    -0.60
     mantle
    -0.58
     silence
    -0.58
    POSITIVE LOGITS
    ikuman
    1.16
     Lumpur
    1.05
    EStreamFrame
    1.04
    lyak
    1.00
    enei
    0.88
    etsu
    0.87
    waukee
    0.86
    oha
    0.83
    hid
    0.81
    zie
    0.81
    Act Density 0.118%

    No Known Activations