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

    Neuronpedia

    INDEX
    Explanations

    words related to temperatures and temperature control

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rahim
    -0.80
    business
    -0.79
    lus
    -0.73
    legate
    -0.72
    enegger
    -0.72
    vous
    -0.69
    umbn
    -0.69
    ioned
    -0.69
    fman
    -0.68
    BACK
    -0.67
    POSITIVE LOGITS
     extremes
    1.22
     fluctuations
    1.13
     gradient
    1.12
     temperatures
    1.10
     temperature
    0.98
     anomalies
    0.94
     fluct
    0.93
     rise
    0.92
     readings
    0.91
    elsius
    0.91
    Act Density 0.037%

    No Known Activations