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

    Neuronpedia

    INDEX
    Explanations

    numerals or percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.75
    redo
    -0.71
     marqu
    -0.70
    achev
    -0.67
     Wilde
    -0.65
    erity
    -0.65
    sonian
    -0.64
    ellation
    -0.61
    bilt
    -0.61
    rovers
    -0.59
    POSITIVE LOGITS
     percent
    1.16
    %
    1.12
    %,
    1.09
    %.
    1.06
    %;
    1.03
    percent
    0.90
     ±
    0.89
    ±
    0.89
     %
    0.84
     Percent
    0.84
    Act Density 0.065%

    No Known Activations