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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical values and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.83
     Superhosts
    -0.80
    AnchorStyles
    -0.80
    Искәрмәләр
    -0.79
     broadest
    -0.73
    Jeografia
    -0.73
    haustible
    -0.73
    Chham
    -0.72
     Momb
    -0.71
     Abbé
    -0.71
    POSITIVE LOGITS
     values
    1.96
     Values
    1.75
    values
    1.70
    Values
    1.58
     VALUES
    1.43
     value
    1.34
    VALUES
    1.28
     valeurs
    1.25
     VALUE
    1.24
     Value
    1.23
    Act Density 0.097%

    No Known Activations