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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving conditional probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.17
    276
    -0.14
    ADER
    -0.14
    eka
    -0.13
    uje
    -0.13
    olec
    -0.13
    ADF
    -0.13
    lom
    -0.13
    ErrorHandler
    -0.13
    coles
    -0.13
    POSITIVE LOGITS
    erken
    0.17
    λÏī
    0.16
    YST
    0.15
    zelf
    0.15
    er
    0.15
    OLOR
    0.15
    ipsis
    0.15
    -divider
    0.14
    /$
    0.14
    erne
    0.14
    Act Density 0.108%

    No Known Activations