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

    Neuronpedia

    INDEX
    Explanations

    sections related to references, authorship, and publication details in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HUD
    -0.78
     morp
    -0.72
     mascara
    -0.69
     figur
    -0.67
     rhy
    -0.66
    ĸļ
    -0.65
    orney
    -0.64
    stro
    -0.62
     syll
    -0.62
     overtime
    -0.62
    POSITIVE LOGITS
    debian
    1.31
     Debian
    1.05
     debian
    0.97
    gnu
    0.87
    kernel
    0.80
    untu
    0.75
    lists
    0.74
     Ubuntu
    0.72
     GCC
    0.71
    archives
    0.71
    Act Density 0.174%

    No Known Activations