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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -inverse
    -0.08
     joe
    -0.07
    中毒
    -0.07
    תואר
    -0.07
    "One
    -0.07
    �
    -0.07
     �
    -0.07
    _px
    -0.07
    梾
    -0.07
    ."""
    -0.06
    POSITIVE LOGITS
     rem
    0.07
     incorpor
    0.07
    Cell
    0.07
    Hi
    0.07
    disc
    0.07
    checker
    0.07
    Dispatcher
    0.07
     ship
    0.07
    кор
    0.06
    ꌼ
    0.06
    Act Density 0.013%

    No Known Activations