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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and numerical codes relevant to processes or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Descriptors
    -0.17
    cce
    -0.15
    itness
    -0.15
    .schema
    -0.15
    arrass
    -0.15
    ArgumentException
    -0.15
     Duty
    -0.14
     itch
    -0.14
    askell
    -0.14
    à¥įतव
    -0.14
    POSITIVE LOGITS
     Ba
    0.18
    ba
    0.17
    _OT
    0.16
     Faith
    0.16
    baum
    0.15
     settle
    0.15
     ba
    0.15
    NÄ°
    0.15
    Ba
    0.15
    (Logger
    0.15
    Act Density 0.028%

    No Known Activations