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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Text"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Textbooks" or "Text" in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.80
    uckland
    -0.72
    thur
    -0.71
    CVE
    -0.68
     CVE
    -0.67
     Forbes
    -0.66
    deen
    -0.66
    dinand
    -0.65
     Kashmir
    -0.64
    izons
    -0.63
    POSITIVE LOGITS
    uality
    1.04
    ured
    1.00
    text
    0.98
    ual
    0.97
     Text
    0.97
    escription
    0.90
    speak
    0.90
    books
    0.88
    Text
    0.88
    ures
    0.88
    Act Density 0.010%

    No Known Activations