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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Standard deviation or measurement error

    np_acts-logits-general · gemini-2.0-flash

    quantifying error or deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Réponses
    -0.60
     Parke
    -0.56
    Viungo
    -0.55
     Choo
    -0.51
    ckeys
    -0.51
    DeleteBehavior
    -0.51
     tocó
    -0.50
     mendes
    -0.49
     Pier
    -0.48
     เย
    -0.48
    POSITIVE LOGITS
     error
    1.47
     errors
    1.31
     uncertainty
    1.30
     Error
    1.21
     uncertainties
    1.21
    error
    1.18
     deviation
    1.11
    Error
    1.10
     Uncertainty
    1.10
     Errors
    1.08
    Act Density 1.338%

    No Known Activations