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

    Neuronpedia

    INDEX
    Explanations

    phrases related to documents, articles, petitions, and schedules

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the current status or updates regarding subjects or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.63
     Tests
    -0.57
     Practices
    -0.56
     Franch
    -0.56
    tackle
    -0.55
    "},"
    -0.54
     battled
    -0.53
    merce
    -0.53
    birds
    -0.52
     retreat
    -0.52
    POSITIVE LOGITS
     redacted
    0.83
     paraph
    0.77
     quoted
    0.77
     summar
    0.75
     reprinted
    0.75
     aloud
    0.74
     ital
    0.74
     narration
    0.73
     quoting
    0.73
     acronym
    0.73
    Act Density 1.346%

    No Known Activations