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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions pertaining to abstraction and abstract ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unta
    -0.18
    лаÑģ
    -0.17
    ermo
    -0.17
    ÑĥÑĩа
    -0.16
    /inet
    -0.16
     -------------------------------------------------------------------------↵
    -0.15
    isters
    -0.15
    ÙĦاÙĨ
    -0.15
    одо
    -0.15
    tha
    -0.15
    POSITIVE LOGITS
    edly
    0.28
    ed
    0.28
    s
    0.20
    edImage
    0.19
    STRACT
    0.19
    -syntax
    0.19
    ly
    0.18
    ively
    0.18
    OLUTE
    0.18
    ing
    0.17
    Act Density 0.012%

    No Known Activations