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

    Neuronpedia

    INDEX
    Explanations

    significant numerical data and connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aal
    -0.17
    enment
    -0.15
    lou
    -0.14
    odal
    -0.14
     count
    -0.14
    еи
    -0.14
    odega
    -0.13
    ingleton
    -0.13
    onth
    -0.13
    arl
    -0.13
    POSITIVE LOGITS
    ξε
    0.17
    estar
    0.17
     denn
    0.15
    urance
    0.15
    013
    0.14
    ائÙģ
    0.14
    eness
    0.14
    050
    0.14
     Ã
    0.14
    _mot
    0.14
    Act Density 0.003%

    No Known Activations