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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     consume
    -0.07
     студ
    -0.07
    pher
    -0.07
    ס
    -0.07
    国有
    -0.06
    Envelope
    -0.06
     Screen
    -0.06
    שמו
    -0.06
    bo
    -0.06
    Fel
    -0.06
    POSITIVE LOGITS
     §§
    0.08
    .getIndex
    0.07
    二十年
    0.07
     fanatic
    0.07
     Bend
    0.07
    .buf
    0.07
    NIC
    0.07
    _ang
    0.07
    _handler
    0.07
    慢慢
    0.07
    Act Density 0.104%

    No Known Activations