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

    Neuronpedia

    INDEX
    Explanations

    words related to comic books

    oai_token-act-pair · gpt-3.5-turbo

    references to comic books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achev
    -0.74
    lain
    -0.73
    ldon
    -0.72
    edIn
    -0.71
    holm
    -0.71
    ntil
    -0.70
    ĪĴ
    -0.70
    ª
    -0.69
    aband
    -0.68
    qv
    -0.67
    POSITIVE LOGITS
     book
    1.13
    strip
    1.05
     strip
    1.00
     relief
    0.98
     books
    0.96
    book
    0.96
     Comics
    0.96
     adaptation
    0.96
     comics
    0.92
     strips
    0.91
    Act Density 0.039%

    No Known Activations