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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     arithmetic
    -0.07
     psychologically
    -0.07
    锚
    -0.07
    isors
    -0.07
    季节
    -0.07
     Las
    -0.07
     jov
    -0.07
    (contract
    -0.07
     Dere
    -0.07
    conversation
    -0.06
    POSITIVE LOGITS
     bekom
    0.07
    🏿
    0.07
    涴
    0.07
    ייע
    0.07
    iki
    0.06
     Hogan
    0.06
    _UPDATE
    0.06
     BCM
    0.06
    بنى
    0.06
    变身
    0.06
    Act Density 0.000%

    No Known Activations