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

    Neuronpedia

    INDEX
    Explanations

    terms related to typography, specifically typefaces

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "face" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.89
    ateurs
    -0.78
    rie
    -0.78
    alid
    -0.73
    rd
    -0.72
    sburgh
    -0.72
    ary
    -0.70
    artisan
    -0.70
    ucky
    -0.69
    nesota
    -0.68
    POSITIVE LOGITS
    BOOK
    0.92
    face
    0.91
    lihood
    0.90
    forth
    0.88
    fur
    0.77
    faces
    0.74
    xus
    0.70
    breakers
    0.69
    faced
    0.68
    Book
    0.68
    Act Density 0.024%

    No Known Activations