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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions and phrases indicating value or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atik
    -0.16
    isson
    -0.16
    reet
    -0.15
    eward
    -0.14
    ehir
    -0.14
    äºĮ人
    -0.14
     NodeType
    -0.14
    asting
    -0.14
    athe
    -0.14
    ath
    -0.14
    POSITIVE LOGITS
    ìĶ¨
    0.16
    ürn
    0.16
    çļĦæĥħ
    0.15
    ophy
    0.15
     Levy
    0.15
    èĦ
    0.14
    openh
    0.14
     strips
    0.14
    stri
    0.14
    chwitz
    0.14
    Act Density 0.028%

    No Known Activations