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

    Neuronpedia

    INDEX
    Explanations

    patterns of data processing and memory manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.28
    h
    -0.25
    in
    -0.23
    d
    -0.21
    n
    -0.20
    M
    -0.20
    z
    -0.20
    T
    -0.19
    S
    -0.19
    B
    -0.19
    POSITIVE LOGITS
    //
    0.17
    ONSE
    0.16
    {↵
    0.15
    VML
    0.15
    UEL
    0.14
    cid
    0.14
    .tc
    0.14
    ÄĽt
    0.14
    à¥ĩà¤
    0.14
    olean
    0.14
    Act Density 0.136%

    No Known Activations