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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    different forms of punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.73
     inver
    -0.72
     transact
    -0.67
     herds
    -0.67
     herd
    -0.67
     cradle
    -0.67
     ferment
    -0.63
     vegetarian
    -0.63
    ¥ŀ
    -0.62
     omn
    -0.62
    POSITIVE LOGITS
    assetsadobe
    0.80
     Afterwards
    0.72
     Lauder
    0.71
     Macedonia
    0.70
     Borders
    0.69
     Madness
    0.68
     Forth
    0.67
     Kessler
    0.67
     Sands
    0.67
     externalToEVAOnly
    0.67
    Act Density 0.062%

    No Known Activations