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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "does not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.79
    PDATE
    -0.75
    lined
    -0.71
     Seasons
    -0.68
     Citiz
    -0.66
     Designs
    -0.65
     Rebellion
    -0.64
    tons
    -0.64
     Gry
    -0.63
     Communities
    -0.62
    POSITIVE LOGITS
     necessarily
    1.29
    icably
    1.06
     exist
    1.04
     intend
    1.03
     hesitate
    1.00
     belong
    1.00
     bother
    0.99
     condone
    0.97
     distinguish
    0.97
    necess
    0.93
    Act Density 0.108%

    No Known Activations