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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "check"

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of checking or verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uma
    -0.83
    etheless
    -0.79
    stories
    -0.75
    İĭ
    -0.73
    oric
    -0.72
    adia
    -0.69
    nan
    -0.67
    olph
    -0.67
    argon
    -0.66
    pher
    -0.66
    POSITIVE LOGITS
     check
    3.62
     checks
    2.70
    check
    2.56
     Check
    2.29
     checking
    2.29
    Check
    2.15
     checked
    2.07
    checks
    2.01
     Checks
    2.01
    checking
    1.78
    Act Density 0.011%

    No Known Activations