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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eling
    -0.07
    辩
    -0.07
    ⇂
    -0.07
    .numpy
    -0.07
     Baghd
    -0.07
     klar
    -0.07
     singing
    -0.07
    ម
    -0.06
     clown
    -0.06
     Exp
    -0.06
    POSITIVE LOGITS
    AccessType
    0.07
     часа
    0.07
    Results
    0.07
    _TRAN
    0.07
    _CY
    0.07
    什么原因
    0.07
     resembles
    0.07
    _DAYS
    0.07
     =
↵
    0.06
    /modules
    0.06
    Act Density 0.022%

    No Known Activations