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

    Neuronpedia

    INDEX
    Explanations

    references, notes, edits, and other metadata in a text document

    oai_token-act-pair · gpt-3.5-turbo

    references and citations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶æ
    -0.65
     doub
    -0.62
     guts
    -0.61
     killing
    -0.57
     ele
    -0.57
     Strongh
    -0.57
     slapping
    -0.56
    aunting
    -0.56
    rily
    -0.56
    hement
    -0.56
    POSITIVE LOGITS
    âĨij
    0.89
    Footnote
    0.81
    pmwiki
    0.74
    agascar
    0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.73
    eger
    0.69
    ====
    0.69
    */
    0.68
    English
    0.68
    Resources
    0.66
    Act Density 0.165%

    No Known Activations