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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction or concealment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction and disposal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.77
    GAME
    -0.71
    IELD
    -0.67
    BALL
    -0.65
     Faw
    -0.62
     Samar
    -0.60
    manship
    -0.60
     Trader
    -0.59
     heel
    -0.58
    water
    -0.58
    POSITIVE LOGITS
    ation
    1.86
    ated
    1.84
    ating
    1.80
    ate
    1.45
    ations
    1.44
    ators
    1.42
    ates
    1.41
    ator
    1.38
    acy
    1.25
    ATED
    1.22
    Act Density 0.076%

    No Known Activations