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

    Neuronpedia

    INDEX
    Explanations

    words related to writing, such as "writes," "wrote," "writing," and "writings."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "wrote in" followed by context or details about writings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.76
    ahime
    -0.73
    adi
    -0.71
    HUD
    -0.67
    ItemThumbnailImage
    -0.67
    OF
    -0.66
    Kids
    -0.66
    htar
    -0.65
    heim
    -0.64
    ãĥ¯ãĥ³
    -0.63
    POSITIVE LOGITS
     Bulletin
    0.71
     Gazette
    0.70
    mail
    0.70
    pmwiki
    0.70
     ah
    0.66
    letters
    0.66
     Journal
    0.66
     Slate
    0.65
    issance
    0.64
     Paste
    0.62
    Act Density 0.127%

    No Known Activations