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

    Neuronpedia

    INDEX
    Explanations

    placeholders and specific identifiers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPH
    -0.18
    pawn
    -0.15
    aml
    -0.15
    kus
    -0.15
    .FETCH
    -0.14
    zin
    -0.14
    ÙĪÙĬر
    -0.14
    à¥įतन
    -0.14
    hang
    -0.13
    ITED
    -0.13
    POSITIVE LOGITS
    <?↵
    0.16
    à¤Ĥà¤ľ
    0.14
    ingers
    0.14
     Separate
    0.14
    aters
    0.14
    aus
    0.14
    565
    0.14
    mez
    0.13
     Wolfe
    0.13
    öh
    0.13
    Act Density 0.394%

    No Known Activations