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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of destruction or concealment

    oai_token-act-pair · gpt-3.5-turbo

    words related to overwhelming situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.88
    BALL
    -0.72
     ACTION
    -0.71
    water
    -0.68
    IRO
    -0.67
    WAYS
    -0.65
    ORGE
    -0.65
    side
    -0.64
    GAME
    -0.64
    grass
    -0.62
    POSITIVE LOGITS
    ating
    1.77
    ated
    1.75
    ation
    1.74
    ations
    1.58
    ates
    1.49
    ate
    1.47
    ators
    1.43
    ator
    1.38
    ational
    1.33
    ATED
    1.19
    Act Density 0.075%

    No Known Activations