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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "gin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gypt
    -0.69
     elapsed
    -0.68
     Wonderful
    -0.64
     EDITION
    -0.64
     creep
    -0.62
     odds
    -0.61
     Immunity
    -0.60
     complication
    -0.60
     unintended
    -0.60
     Difficulty
    -0.59
    POSITIVE LOGITS
    gin
    1.32
    uine
    1.13
    fo
    0.99
    ovie
    0.96
    uin
    0.96
    forth
    0.96
    ners
    0.96
    Ò
    0.93
    osure
    0.91
    court
    0.90
    Act Density 0.008%

    No Known Activations