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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    临床
    -0.07
    龉
    -0.07
    而
    -0.07
     (!((
    -0.07
     Jeremy
    -0.07
    董事
    -0.07
    今晚
    -0.07
    	char
    -0.07
    loan
    -0.07
     and
    -0.07
    POSITIVE LOGITS
     toned
    0.06
     POSS
    0.06
    _]
    0.06
     heterosexual
    0.06
     Anniversary
    0.06
    곗
    0.06
    🅱
    0.06
    _sd
    0.06
    ציב
    0.06
    -Out
    0.06
    Act Density 0.002%

    No Known Activations