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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ava
    -0.07
    -log
    -0.07
     mail
    -0.07
     staples
    -0.06
     deductible
    -0.06
    /tcp
    -0.06
     FN
    -0.06
    -speed
    -0.06
    getToken
    -0.06
     kosten
    -0.06
    POSITIVE LOGITS
    侍
    0.07
    ########
    0.07
    REGION
    0.06
     assembly
    0.06
    ┍
    0.06
    இ
    0.06
    لاث
    0.06
    繼
    0.06
    粟
    0.06
    speech
    0.06
    Act Density 0.032%

    No Known Activations