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

    Neuronpedia

    INDEX
    Explanations

    references to and mentions of PDF documents

    oai_token-act-pair · gpt-3.5-turbo

    references to PDF documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    places
    -0.94
    dinand
    -0.81
    acha
    -0.76
    powers
    -0.75
    ffen
    -0.74
    venge
    -0.74
    allow
    -0.74
    ĪĴ
    -0.73
    inence
    -0.73
    inent
    -0.72
    POSITIVE LOGITS
    PDF
    1.18
    pdf
    1.01
     PDF
    0.91
    DragonMagazine
    0.86
     pdf
    0.84
    TeX
    0.82
    clip
    0.77
     transcript
    0.76
    clips
    0.76
     Copy
    0.74
    Act Density 0.016%

    No Known Activations