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

    Neuronpedia

    INDEX
    Explanations

    temperatures in Celsius

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alter
    -0.93
    gotten
    -0.86
    ebin
    -0.80
    ublic
    -0.80
    elle
    -0.76
    doms
    -0.71
    orno
    -0.71
    stra
    -0.70
    sonian
    -0.70
     Tycoon
    -0.69
    POSITIVE LOGITS
     Celsius
    1.23
    elsius
    1.20
     Fahrenheit
    1.13
    renheit
    1.04
     warming
    1.01
     warmer
    0.95
     temperatures
    0.93
     heater
    0.92
     temperature
    0.92
     hotter
    0.88
    Act Density 0.007%

    No Known Activations