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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific fictional character

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonexistent
    -0.71
     elig
    -0.68
    lished
    -0.67
     fingerprint
    -0.66
     tert
    -0.62
     unsustainable
    -0.60
     notorious
    -0.60
     partName
    -0.59
     dism
    -0.59
     Entry
    -0.59
    POSITIVE LOGITS
    igans
    0.95
    bugs
    0.92
    kamp
    0.86
    felt
    0.85
    hoe
    0.83
    rake
    0.77
    bug
    0.77
    zman
    0.75
    ghan
    0.74
    gger
    0.73
    Act Density 0.078%

    No Known Activations