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

    Neuronpedia

    INDEX
    Explanations

    abbreviations related to various units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements and quantities in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cecil
    -0.66
     Ragnarok
    -0.65
     Bir
    -0.63
     Metatron
    -0.63
     Pirates
    -0.62
     Sailor
    -0.60
     Fu
    -0.60
     Ridley
    -0.60
     Aval
    -0.60
     Odin
    -0.59
    POSITIVE LOGITS
     apiece
    1.13
     increments
    1.04
    Hz
    0.93
    poons
    0.88
    illion
    0.87
    ilion
    0.87
     EDT
    0.86
    elsius
    0.85
    renheit
    0.82
    imeter
    0.79
    Act Density 0.256%

    No Known Activations