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

    Neuronpedia

    INDEX
    Explanations

    references to recent changes or items related to literature and specific details about procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quantitative or specific numerical information and technical terms.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi

    temporal references and adverbs related to time (like "recently", "currently", "most recently").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     Dapper
    -0.45
     CURIAM
    -0.41
    writeFieldEnd
    -0.40
     Lumin
    -0.40
    Handlung
    -0.40
    XtraReports
    -0.39
     Wikimedijinoj
    -0.39
     Sequ
    -0.39
    њи
    -0.39
     inoculation
    -0.39
    POSITIVE LOGITS
    QMetaType
    0.55
     farlo
    0.54
     ones
    0.50
     noDo
    0.48
     hacerlo
    0.47
     melakukannya
    0.46
     particularmente
    0.46
     especialmente
    0.44
     particularly
    0.44
    -------------</
    0.43
    Act Density 0.659%

    No Known Activations