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

    Neuronpedia

    INDEX
    Explanations

    words related to quantities or categorizations

    oai_token-act-pair · gpt-3.5-turbo

    references to whole concepts or significant quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.93
    expression
    -0.87
    antry
    -0.85
    urgy
    -0.80
    uber
    -0.77
    anship
    -0.75
    brance
    -0.74
    leness
    -0.73
    externalActionCode
    -0.72
    cture
    -0.72
    POSITIVE LOGITS
     categories
    1.23
     fronts
    1.21
     paragraphs
    1.13
     continents
    1.11
     pairs
    1.10
     occasions
    1.09
     pillars
    1.08
     versions
    1.08
     instances
    1.07
     finalists
    1.07
    Act Density 0.248%

    No Known Activations