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

    Neuronpedia

    INDEX
    Explanations

    names of companies and organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subdu
    -0.64
    EStream
    -0.61
     pier
    -0.56
     toile
    -0.54
     saline
    -0.54
     restraint
    -0.54
     Seym
    -0.53
     hypert
    -0.53
    leans
    -0.53
    icter
    -0.53
    POSITIVE LOGITS
    ources
    0.94
    wered
    0.93
    ourced
    0.85
    ayers
    0.80
    ensible
    0.79
    edition
    0.78
    ourcing
    0.78
    atisf
    0.77
    pecially
    0.76
    essions
    0.75
    Act Density 0.310%

    No Known Activations