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

    Neuronpedia

    INDEX
    Explanations

    text related to names and proper nouns, particularly those associated with legal cases or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seton
    -0.86
    kaido
    -0.84
     Sepp
    -0.83
    قط
    -0.81
     zij
    -0.80
     Hadid
    -0.80
     Zij
    -0.78
     mẽ
    -0.76
    Hozzáférés
    -0.75
    {~
    -0.74
    POSITIVE LOGITS
     KRA
    1.00
     Kram
    0.90
     GRA
    0.88
     Kraw
    0.88
     createSprite
    0.86
     Kramer
    0.85
     Kra
    0.84
     straws
    0.83
    Kra
    0.81
     Thra
    0.81
    Act Density 3.094%

    No Known Activations