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

    Neuronpedia

    INDEX
    Explanations

    questions regarding character engagement and believability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.67
     Италијани
    -0.65
    DockStyle
    -0.65
    Autoritní
    -0.64
     kasarigan
    -0.63
    ніципа
    -0.60
    出版年
    -0.58
    setCellStyle
    -0.57
    المناصب
    -0.57
     estekak
    -0.56
    POSITIVE LOGITS
     characters
    1.64
     character
    1.54
     Characters
    1.40
    characters
    1.33
    Characters
    1.27
     Character
    1.25
    character
    1.25
     CHARACTERS
    1.25
    Character
    1.23
     personajes
    1.19
    Act Density 0.229%

    No Known Activations