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

    Neuronpedia

    INDEX
    Explanations

    phrases related to asserting a statement or claim

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "assert" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bake
    -0.78
     Carbuncle
    -0.68
    ppo
    -0.67
    mys
    -0.63
    shows
    -0.61
    clean
    -0.61
     Hort
    -0.60
    nton
    -0.60
    carb
    -0.60
    oho
    -0.60
    POSITIVE LOGITS
    iveness
    1.02
    ively
    1.00
    antly
    0.93
    uably
    0.93
    olated
    0.90
    ive
    0.90
    ions
    0.90
    urances
    0.90
    ements
    0.89
    uable
    0.89
    Act Density 0.022%

    No Known Activations