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

    Neuronpedia

    INDEX
    Explanations

    numeric values with percentage symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly percentages and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.73
    actionDate
    -0.70
    ovie
    -0.70
    DragonMagazine
    -0.68
    reb
    -0.67
    cffffcc
    -0.65
    zos
    -0.64
     skim
    -0.63
     compan
    -0.63
    Sov
    -0.60
    POSITIVE LOGITS
    %
    0.68
    %;
    0.68
     ±
    0.66
    00
    0.66
    %,
    0.66
     respondents
    0.64
    50
    0.63
     commits
    0.61
     pts
    0.61
     MIA
    0.60
    Act Density 0.042%

    No Known Activations