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

    Neuronpedia

    INDEX
    Explanations

    positive words or affirmations

    oai_token-act-pair · gpt-3.5-turbo

    words related to affliction or suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.85
    DragonMagazine
    -0.73
    BuyableInstoreAndOnline
    -0.72
    assetsadobe
    -0.71
    sonian
    -0.70
    KEN
    -0.70
    SpaceEngineers
    -0.69
     Weir
    -0.68
    STD
    -0.66
    ppo
    -0.64
    POSITIVE LOGITS
    irming
    1.11
    luence
    1.07
    liction
    1.02
    ront
    0.99
    aff
    0.98
    ording
    0.96
    irms
    0.93
    irmed
    0.91
    onso
    0.88
    semb
    0.87
    Act Density 0.006%

    No Known Activations