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

    Neuronpedia

    INDEX
    Explanations

    ASCII characters interspersed with special characters and numerals, potentially indicating computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    numeric sequences and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "$:/
    -0.77
    20439
    -0.68
    natureconservancy
    -0.62
    DragonMagazine
    -0.61
     Gutenberg
    -0.61
    ewitness
    -0.57
     âĸ
    -0.56
    âĸĵ
    -0.55
     Healthcare
    -0.53
    ritz
    -0.53
    POSITIVE LOGITS
    ensis
    0.58
    quad
    0.57
    strip
    0.56
    pointer
    0.55
     turret
    0.55
    offset
    0.53
    amboo
    0.53
    inqu
    0.53
    full
    0.53
    ord
    0.52
    Act Density 0.476%

    No Known Activations