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

    Neuronpedia

    INDEX
    Explanations

    words related to negative aspects or events

    oai_token-act-pair · gpt-3.5-turbo

    references to "mal" terms, particularly those associated with negative or harmful concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.72
    loo
    -0.68
    nesday
    -0.68
     Hobby
    -0.65
     Fifty
    -0.64
     Emirates
    -0.64
     Clubs
    -0.64
     Jackets
    -0.63
     Defenders
    -0.63
     Wide
    -0.63
    POSITIVE LOGITS
    ignant
    1.19
    colm
    1.08
    practice
    1.07
    adies
    1.04
    absor
    1.02
    formed
    1.01
    igned
    1.00
    igning
    0.97
    cellaneous
    0.92
    adjust
    0.92
    Act Density 0.023%

    No Known Activations