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

    Neuronpedia

    INDEX
    Explanations

    numerical terms and mathematical concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numerical and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whis
    -0.84
    butt
    -0.82
    bucks
    -0.81
    cha
    -0.81
     Incarn
    -0.79
    rir
    -0.75
    jack
    -0.74
    IDA
    -0.73
    yards
    -0.72
    adder
    -0.72
    POSITIVE LOGITS
     numerical
    1.36
     mathematical
    1.08
     calculation
    1.02
     calculations
    1.02
     computation
    1.00
     equations
    0.96
     representations
    0.95
     numeric
    0.92
     comput
    0.91
     referen
    0.90
    Act Density 0.012%

    No Known Activations