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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to named individuals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     PopupWindow
    -0.93
    Kanpo
    -0.91
     sèche
    -0.86
     ſtand
    -0.84
     McDonough
    -0.83
    parsedMessage
    -0.82
     pingente
    -0.81
     ſind
    -0.79
     дописавши
    -0.79
     nonce
    -0.78
    POSITIVE LOGITS
     Ste
    1.47
    Ste
    1.33
     ste
    1.27
     Steen
    1.20
    ste
    1.09
     STE
    1.09
     Steele
    1.00
     Steiner
    0.99
    STE
    0.96
     Steine
    0.93
    Act Density 0.024%

    No Known Activations