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

    Neuronpedia

    INDEX
    Explanations

    numbers related to distances or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to distances, ages, and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hierarchy
    -0.69
    parency
    -0.69
    ribution
    -0.68
    ventory
    -0.67
    ioch
    -0.62
    TextColor
    -0.61
    orts
    -0.61
    osion
    -0.60
     Dos
    -0.60
    output
    -0.59
    POSITIVE LOGITS
    ½
    1.05
     inches
    0.85
     cents
    0.84
     ½
    0.80
    teenth
    0.80
    inches
    0.79
     shy
    0.75
    een
    0.74
    º
    0.72
    cm
    0.72
    Act Density 0.125%

    No Known Activations