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

    Neuronpedia

    INDEX
    Explanations

    connections between characters and their relationships in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     îł
    -0.16
    ulti
    -0.15
    insky
    -0.15
     tá»ĭch
    -0.14
    ãĤ¯ãĤ»
    -0.14
    reff
    -0.14
    alties
    -0.14
    ç·Ĵ
    -0.14
    pong
    -0.13
    éı
    -0.13
    POSITIVE LOGITS
     Chapters
    0.16
     Quarter
    0.15
    eya
    0.15
    anford
    0.15
     Bolton
    0.15
     quarter
    0.15
     Dow
    0.14
     sparing
    0.14
    uka
    0.14
     Crane
    0.14
    Act Density 0.002%

    No Known Activations