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

    Neuronpedia

    INDEX
    Explanations

    quotations with emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    quotes or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.80
    ·
    -0.75
    etheless
    -0.71
    ijing
    -0.69
    ĪĴ
    -0.69
    İĭ
    -0.67
    ĵĺ
    -0.67
    Ħ¢
    -0.66
    eb
    -0.64
    erity
    -0.63
    POSITIVE LOGITS
     reads
    1.06
    said
    0.97
     says
    0.94
     said
    0.94
     recalls
    0.85
     wrote
    0.78
     laughs
    0.75
     recalled
    0.73
    ],"
    0.73
     writes
    0.72
    Act Density 0.083%

    No Known Activations