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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to temperature

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe sound or temperature changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    este
    -0.78
    eno
    -0.76
    etition
    -0.75
    ainted
    -0.75
    EP
    -0.75
    shire
    -0.73
    advertising
    -0.73
    eb
    -0.73
    eren
    -0.71
    Ward
    -0.70
    POSITIVE LOGITS
     than
    1.63
     Than
    1.44
    than
    1.25
     "$:/
    0.92
     ado
    0.80
    iating
    0.77
     versions
    0.75
    anguage
    0.75
    ModLoader
    0.74
     behaved
    0.73
    Act Density 0.061%

    No Known Activations