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

    Neuronpedia

    INDEX
    Explanations

    references to temperature and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agr
    -0.17
    uilder
    -0.16
    igar
    -0.15
    dol
    -0.15
    som
    -0.15
    iei
    -0.14
    size
    -0.14
    eward
    -0.14
    laus
    -0.14
    磨
    -0.14
    POSITIVE LOGITS
    orarily
    0.21
    reature
    0.17
     Celsius
    0.17
    oft
    0.16
    atures
    0.16
    /time
    0.16
    alte
    0.15
     Fahrenheit
    0.15
    erture
    0.15
    /weather
    0.15
    Act Density 0.021%

    No Known Activations