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

    Neuronpedia

    INDEX
    Explanations

    large numbers or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the quantity or count of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.88
     Piercing
    -0.71
    heid
    -0.68
    endon
    -0.67
    ashtra
    -0.65
     majesty
    -0.64
    raught
    -0.62
     deepest
    -0.62
    artisan
    -0.61
    ataka
    -0.61
    POSITIVE LOGITS
    metry
    0.80
    number
    0.75
     of
    0.74
    enance
    0.72
     numbers
    0.71
    NUM
    0.69
    ones
    0.68
     (~
    0.66
     (<
    0.66
     802
    0.65
    Act Density 0.033%

    No Known Activations