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

    Neuronpedia

    INDEX
    Explanations

    sections related to analysis and findings in research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     françaises
    -0.65
     seules
    -0.56
     kyllä
    -0.54
     seuls
    -0.54
     précédentes
    -0.54
     gratuits
    -0.53
     spéciaux
    -0.52
     supplémentaires
    -0.52
     nationales
    -0.51
     lourd
    -0.51
    POSITIVE LOGITS
     AND
    1.20
     OF
    1.15
     WITH
    1.04
     FROM
    0.91
    AND
    0.90
     TO
    0.89
     FOR
    0.86
    WITH
    0.85
     ON
    0.83
    OF
    0.83
    Act Density 0.208%

    No Known Activations