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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to the term 'IX' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rats
    -0.74
     inspiration
    -0.70
     Campbell
    -0.64
     bapt
    -0.62
     Ger
    -0.62
     Penal
    -0.62
     takeaway
    -0.61
     Pel
    -0.60
     Bruce
    -0.60
     Kimber
    -0.60
    POSITIVE LOGITS
    IX
    4.55
    ix
    2.27
    VII
    1.61
    UX
    1.60
    ixt
    1.48
    VI
    1.41
     IX
    1.32
    II
    1.32
    IV
    1.30
    XX
    1.30
    Act Density 0.008%

    No Known Activations