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

    Neuronpedia

    INDEX
    Explanations

    specific nouns related to groups or categories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categories and entities in social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stage
    -0.63
    BG
    -0.61
     Palestin
    -0.61
     Arrows
    -0.60
     Strat
    -0.60
     Contracts
    -0.59
     contrace
    -0.59
    ogens
    -0.59
    nance
    -0.59
    aeda
    -0.58
    POSITIVE LOGITS
     apiece
    0.86
    undred
    0.69
    inkle
    0.67
    anooga
    0.66
     parcel
    0.66
    hander
    0.65
    paio
    0.64
     accuser
    0.64
     stroke
    0.63
    stroke
    0.62
    Act Density 0.155%

    No Known Activations