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

    Neuronpedia

    INDEX
    Explanations

    variables associated with temporary or intermediate values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hang
    -0.16
    pag
    -0.16
    vat
    -0.15
    ecta
    -0.15
    iful
    -0.14
     neutral
    -0.14
    bij
    -0.14
     Fil
    -0.14
    pie
    -0.14
    zig
    -0.14
    POSITIVE LOGITS
    orarily
    0.18
    ylon
    0.15
    _references
    0.15
    à¥ĩप
    0.15
     omas
    0.15
    år
    0.15
    ORTH
    0.15
    /generated
    0.14
    /temp
    0.14
    OTOR
    0.14
    Act Density 0.011%

    No Known Activations