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

    Neuronpedia

    INDEX
    Explanations

    words related to stress or exertion

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "strain" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.78
    hyde
    -0.77
    wolves
    -0.76
    erald
    -0.71
    bear
    -0.71
    ¥µ
    -0.70
    wolf
    -0.66
     Flavoring
    -0.66
    boys
    -0.64
    STON
    -0.64
    POSITIVE LOGITS
    angling
    1.00
    angled
    0.98
    angle
    0.96
    atum
    0.91
    aining
    0.90
    agg
    0.89
    uture
    0.88
    ainer
    0.87
    ained
    0.85
    aditional
    0.83
    Act Density 0.006%

    No Known Activations