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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific nouns and their associated actions or characteristics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aten
    -0.17
    ļ
    -0.16
    chein
    -0.15
    oref
    -0.14
    é¼ĵ
    -0.14
     ty
    -0.13
     refill
    -0.13
    arken
    -0.13
    _until
    -0.13
    ARGIN
    -0.13
    POSITIVE LOGITS
    .ErrorMessage
    0.15
    .cms
    0.14
    ElementType
    0.14
     Sabha
    0.14
    expert
    0.14
     Playboy
    0.14
    ital
    0.14
    imizer
    0.14
    ëĮĢ
    0.13
     Vul
    0.13
    Act Density 0.004%

    No Known Activations