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

    Neuronpedia

    INDEX
    Explanations

    numbers related to statistics, percentages, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.82
    busters
    -0.75
    pty
    -0.74
    idays
    -0.70
    ships
    -0.69
    adobe
    -0.69
    pocket
    -0.69
    aucus
    -0.69
    cards
    -0.66
    farious
    -0.65
    POSITIVE LOGITS
     ±
    0.84
     lbs
    0.83
     kHz
    0.77
     pounds
    0.77
     million
    0.76
     percent
    0.74
    lbs
    0.74
    652
    0.72
     WRITE
    0.72
     mph
    0.71
    Act Density 0.071%

    No Known Activations