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

    Neuronpedia

    INDEX
    Explanations

    processes of breaking down or dividing concepts and elements into smaller parts or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jen
    -0.17
    keit
    -0.14
    quam
    -0.14
    orge
    -0.14
    æŁĵ
    -0.14
    orough
    -0.14
     Bare
    -0.14
    jin
    -0.13
    ius
    -0.13
    intage
    -0.13
    POSITIVE LOGITS
     pieces
    0.21
     piece
    0.18
    (components
    0.17
     Piece
    0.17
    _pieces
    0.17
    -piece
    0.16
    orz
    0.16
    ç¢İ
    0.16
    -parts
    0.15
     breakdown
    0.15
    Act Density 0.170%

    No Known Activations