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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of characters or individuals

    oai_token-act-pair · gpt-3.5-turbo

    character names and their roles in various forms of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newsletters
    -0.76
    comments
    -0.68
    lesiastical
    -0.66
    Edited
    -0.66
    ITAL
    -0.65
    ulatory
    -0.65
    Islamic
    -0.64
    ointed
    -0.64
     mats
    -0.64
    Japan
    -0.63
    POSITIVE LOGITS
     Luthor
    0.97
     Stark
    0.95
     Winchester
    0.95
     Finch
    0.91
     Reyes
    0.90
     Sawyer
    0.87
     kidn
    0.86
     Locke
    0.86
     Osw
    0.86
     Weasley
    0.85
    Act Density 0.221%

    No Known Activations