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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    很快就
    -0.07
    所以我
    -0.07
    ⵟ
    -0.07
     snapped
    -0.07
    di
    -0.07
     problem
    -0.07
     provide
    -0.07
    depend
    -0.06
     valueType
    -0.06
    bool
    -0.06
    POSITIVE LOGITS
    颀
    0.08
    _stock
    0.08
    üncü
    0.07
    belie
    0.07
    _MONITOR
    0.07
    (stderr
    0.07
    (pass
    0.07
     scars
    0.07
     Millenn
    0.07
    谤
    0.07
    Act Density 0.206%

    No Known Activations