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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with temperature variations and environmental factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.15
     Tobias
    -0.14
    orca
    -0.14
    TOR
    -0.14
    IPA
    -0.13
    atori
    -0.13
     adopt
    -0.13
    Verdana
    -0.13
    kdir
    -0.13
    otal
    -0.13
    POSITIVE LOGITS
     temperature
    0.73
     temperatures
    0.67
     temp
    0.61
     Temperature
    0.59
    temperature
    0.59
     temps
    0.56
     temper
    0.54
     Temper
    0.54
     tem
    0.54
    Temperature
    0.53
    Act Density 0.081%

    No Known Activations