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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases indicating typical examples or characteristics of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dieux
    -0.52
     pères
    -0.49
     religieuses
    -0.49
     verheir
    -0.49
     zewnętrzne
    -0.48
     bağlantılar
    -0.47
     lägen
    -0.46
    ButtonModule
    -0.46
     gröss
    -0.46
     électroniques
    -0.45
    POSITIVE LOGITS
     typical
    1.77
    Typical
    1.73
     Typical
    1.67
    typical
    1.66
     typique
    1.38
    典型
    1.34
     типи
    1.29
     típico
    1.26
     TYP
    1.23
     típica
    1.20
    Act Density 0.320%

    No Known Activations