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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to provocation, controversy, and tension

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "incite" and its variations, indicating a focus on provoking or stirring up emotions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.78
    wagen
    -0.71
    geist
    -0.70
    hyde
    -0.70
     Unch
    -0.67
    BOOK
    -0.66
    Ĥ¬
    -0.64
     Savior
    -0.64
     Hunters
    -0.63
    hari
    -0.63
    POSITIVE LOGITS
    ursions
    1.31
    ision
    1.30
    ursion
    1.28
    orporated
    1.27
    itement
    1.18
    isions
    1.18
    arcer
    1.16
    idences
    1.16
    isive
    1.15
    identally
    1.13
    Act Density 0.010%

    No Known Activations