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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -it
    -0.08
    揖
    -0.07
     speculated
    -0.07
    斥
    -0.07
    bases
    -0.07
    �
    -0.07
    banana
    -0.07
    ɣ
    -0.07
     Sy
    -0.07
    ulent
    -0.07
    POSITIVE LOGITS
     liberties
    0.07
    	right
    0.07
    >';
↵
    0.06
    🏚
    0.06
    //--------------------------------------------------------------------------------
    0.06
     Schn
    0.06
     troublesome
    0.06
     الأمريكي
    0.06
     veröffentlicht
    0.06
    ࠍ
    0.06
    Act Density 0.014%

    No Known Activations