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

    Neuronpedia

    INDEX
    Explanations

    references to traditional practices or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eynman
    -0.85
     parlent
    -0.79
    뮬
    -0.76
     auraient
    -0.75
    tauscht
    -0.75
    amaño
    -0.73
     Lorca
    -0.71
     auront
    -0.71
     beetles
    -0.69
     Lough
    -0.68
    POSITIVE LOGITS
     Traditional
    1.21
     tradi
    1.21
     traditions
    1.20
     tradition
    1.18
     traditional
    1.13
    Traditional
    1.12
     Tradition
    1.04
     tradis
    1.03
    traditional
    1.03
    TRAD
    0.98
    Act Density 0.085%

    No Known Activations