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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities of something

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hall
    -0.69
    NPR
    -0.67
     Tid
    -0.66
     Seat
    -0.66
    ··
    -0.65
     Frontier
    -0.65
     Tribune
    -0.62
     Shades
    -0.62
     Kor
    -0.61
     cradle
    -0.60
    POSITIVE LOGITS
     amounts
    1.13
     amount
    1.08
    entially
    0.89
    ngth
    0.86
     quantities
    0.84
     sums
    0.82
     quantity
    0.77
    ume
    0.76
    encies
    0.76
    uated
    0.75
    Act Density 0.022%

    No Known Activations