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

    Neuronpedia

    INDEX
    Explanations

    numbers, specifically percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aucus
    -0.75
    pty
    -0.74
    redo
    -0.73
    farious
    -0.68
    riers
    -0.67
    sters
    -0.67
    achus
    -0.66
    pocket
    -0.66
    ellation
    -0.65
    hetti
    -0.64
    POSITIVE LOGITS
     percent
    0.90
     mph
    0.85
     ±
    0.84
    ±
    0.81
     lbs
    0.81
    %
    0.78
     acres
    0.76
     kHz
    0.74
     pounds
    0.74
     percentile
    0.74
    Act Density 0.066%

    No Known Activations