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

    Neuronpedia

    INDEX
    Explanations

    key points, important takeaways, and essential facts in written content

    oai_token-act-pair · gpt-3.5-turbo

    key points and significant pieces of information in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.77
    psc
    -0.74
    raid
    -0.73
    raph
    -0.71
    heid
    -0.66
    Untitled
    -0.66
    thouse
    -0.65
    yss
    -0.63
    onement
    -0.63
     Tsukuyomi
    -0.63
    POSITIVE LOGITS
     pertaining
    0.90
     relating
    0.84
     regarding
    0.82
     emerge
    0.81
    ":[{"
    0.79
     related
    0.78
     glean
    0.78
     surrounding
    0.78
     relate
    0.76
    uits
    0.76
    Act Density 0.229%

    No Known Activations