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

    Neuronpedia

    INDEX
    Explanations

    various numerical values or timestamps in a log or system output context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehr
    -0.15
    ascus
    -0.15
    ture
    -0.15
    ниÑĩ
    -0.14
    eeper
    -0.14
     royalty
    -0.14
    IJľ
    -0.14
    omba
    -0.14
    .cz
    -0.14
    ters
    -0.14
    POSITIVE LOGITS
    olley
    0.15
    leh
    0.15
    BJ
    0.15
     UNUSED
    0.14
    cntl
    0.14
    ampa
    0.14
     paci
    0.14
    ç¨ĭ
    0.13
     Licht
    0.13
    anson
    0.13
    Act Density 0.008%

    No Known Activations