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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ����
    -0.74
    thood
    -0.73
    gpu
    -0.70
    imi
    -0.70
    Ò
    -0.70
    âĦ¢:
    -0.67
    etsy
    -0.67
    earch
    -0.66
    ounces
    -0.64
    /"
    -0.63
    POSITIVE LOGITS
    oret
    1.59
     latter
    1.27
     downside
    1.16
     simplest
    1.13
    resa
    1.10
    odore
    1.06
    ories
    1.06
     biggest
    1.05
     easiest
    1.05
     irony
    1.04
    Act Density 0.395%

    No Known Activations