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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Deprecated
    -0.07
    .loads
    -0.07
    ulse
    -0.07
     Dyn
    -0.07
    棫
    -0.07
    �
    -0.07
    _BS
    -0.06
    udit
    -0.06
     calculator
    -0.06
    ตาย
    -0.06
    POSITIVE LOGITS
    _FUNCTION
    0.07
    eneral
    0.07
    ressed
    0.07
    STORE
    0.07
     negro
    0.07
     enzyme
    0.07
    (mock
    0.07
     kafka
    0.07
     knock
    0.06
    /address
    0.06
    Act Density 0.009%

    No Known Activations