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

    Neuronpedia

    INDEX
    Explanations

    temperature-related words and terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to temperature and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -1.14
    HCR
    -0.82
    theless
    -0.79
    baum
    -0.73
    POL
    -0.67
    Õ
    -0.66
    deen
    -0.66
    hani
    -0.66
    leigh
    -0.65
    Ãį
    -0.65
    POSITIVE LOGITS
    temp
    1.00
     temp
    0.94
    erno
    0.78
    istor
    0.77
    ient
    0.77
    urus
    0.74
    Temp
    0.72
    catentry
    0.69
    oiler
    0.67
     sheet
    0.66
    Act Density 0.011%

    No Known Activations