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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "no such thing."

    oai_token-act-pair · gpt-3.5-turbo

    phrases negating the existence of certain concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipedia
    -0.81
    ertodd
    -0.79
    ï¸ı
    -0.68
    kick
    -0.67
     Zombies
    -0.66
     Brass
    -0.66
     Orn
    -0.65
    uay
    -0.65
    cius
    -0.65
     Loaded
    -0.65
    POSITIVE LOGITS
    thing
    0.77
    ities
    0.75
     thing
    0.72
    worldly
    0.72
    ties
    0.70
     reservations
    0.68
     bidder
    0.66
     matters
    0.64
     sizable
    0.62
     appendix
    0.62
    Act Density 0.023%

    No Known Activations