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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Webb" and related references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oras
    -0.80
    acerb
    -0.77
    haps
    -0.77
    ãĥ´
    -0.73
     Aram
    -0.70
    CENT
    -0.70
    onym
    -0.69
    ãĥ¡
    -0.69
    stood
    -0.69
    cess
    -0.68
    POSITIVE LOGITS
     Webb
    0.92
    atcher
    0.86
    swick
    0.84
    enegger
    0.83
    hedon
    0.78
     Dixon
    0.78
    orld
    0.76
    ithing
    0.76
    yer
    0.75
     Weaver
    0.73
    Act Density 0.030%

    No Known Activations