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

    Neuronpedia

    INDEX
    Explanations

    terms related to probability and statistics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "probability" in various contexts related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    este
    -0.91
    artney
    -0.86
    Interstitial
    -0.86
    agra
    -0.80
    era
    -0.79
    pa
    -0.77
    rine
    -0.75
    ebus
    -0.73
    afort
    -0.72
    ken
    -0.71
    POSITIVE LOGITS
     probability
    1.29
     probabilities
    1.09
    abl
    0.91
    chance
    0.87
     veter
    0.81
    etheless
    0.80
     chance
    0.80
    DragonMagazine
    0.79
     impro
    0.78
    llor
    0.75
    Act Density 0.009%

    No Known Activations