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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly in a sequence or list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peg
    -0.17
    ereg
    -0.16
    ago
    -0.15
    prox
    -0.15
    uhl
    -0.15
    umper
    -0.14
    .kr
    -0.14
    rush
    -0.13
    qui
    -0.13
    ź
    -0.13
    POSITIVE LOGITS
    olv
    0.16
    .EventHandler
    0.15
    unks
    0.15
    OMEM
    0.14
    ettes
    0.14
    ROKE
    0.14
    VarChar
    0.14
    ÷
    0.13
    GMEM
    0.13
    rowsable
    0.13
    Act Density 0.004%

    No Known Activations