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

    Neuronpedia

    INDEX
    Explanations

    references to shoes

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.85
     Modes
    -0.73
    REDACTED
    -0.73
     Debor
    -0.70
    imens
    -0.68
    Downloadha
    -0.67
    ADRA
    -0.67
     MacArthur
    -0.66
    encia
    -0.65
    mingham
    -0.64
    POSITIVE LOGITS
    toe
    1.01
    horn
    0.97
     shoe
    0.92
     heel
    0.85
    oried
    0.80
     strap
    0.79
    bag
    0.77
    hoff
    0.76
     cart
    0.74
     bag
    0.73
    Act Density 0.018%

    No Known Activations