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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical data, particularly margins of error in statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to error margins and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.67
     trance
    -0.65
    ãĥīãĥ©
    -0.64
     passively
    -0.64
    APTER
    -0.63
     Trance
    -0.63
    iferation
    -0.63
    iazep
    -0.62
     cataly
    -0.62
    Pg
    -0.61
    POSITIVE LOGITS
     margin
    1.14
     +/-
    1.12
     margins
    1.10
     error
    1.06
     sampling
    0.99
     ±
    0.92
     Error
    0.92
     rounding
    0.88
     errors
    0.87
     uncertainties
    0.86
    Act Density 0.098%

    No Known Activations