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

    Neuronpedia

    INDEX
    Explanations

    temperatures in degrees

    oai_token-act-pair · gpt-3.5-turbo

    temperature measurements in degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.91
    icate
    -0.83
    udeb
    -0.79
    eer
    -0.78
    cash
    -0.77
    compan
    -0.74
    don
    -0.73
    abor
    -0.71
    stra
    -0.71
    maker
    -0.70
    POSITIVE LOGITS
     Celsius
    1.29
     Fahrenheit
    1.21
     degrees
    1.00
    º
    0.98
    elsius
    0.89
    rees
    0.89
    °
    0.87
     latitude
    0.86
    degree
    0.85
    renheit
    0.84
    Act Density 0.012%

    No Known Activations