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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    grün
    -0.08
     автомоб
    -0.07
    喇
    -0.07
    🧚
    -0.07
     Shortly
    -0.07
    _LOOK
    -0.07
    㸌
    -0.07
    awaii
    -0.07
    úc
    -0.07
     Fur
    -0.06
    POSITIVE LOGITS
     extents
    0.07
    Remark
    0.07
    Accounts
    0.07
    ("-");↵
    0.07
     Vault
    0.07
    ))
↵
↵
    0.07
    ,’
    0.07
    ировки
    0.07
    numbers
    0.06
    (bits
    0.06
    Act Density 0.002%

    No Known Activations