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

    Neuronpedia

    INDEX
    Explanations

    quantitative values expressed as percentages or proportions in a scientific context

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and data regarding quantities or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rike
    -0.66
    venge
    -0.61
    ettings
    -0.60
    akeru
    -0.60
    iers
    -0.59
     proced
    -0.59
     rejo
    -0.58
     Rivals
    -0.58
    idays
    -0.58
     Congratulations
    -0.57
    POSITIVE LOGITS
    %"
    1.22
    %-
    1.17
    %
    1.16
     percent
    1.15
     percentile
    1.01
     ppm
    1.00
    %,
    1.00
    %)
    0.97
    percent
    0.95
    %.
    0.93
    Act Density 0.261%

    No Known Activations