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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Fal
    0.43
     Chop
    0.43
     gib
    0.41
     strictest
    0.40
     chop
    0.38
     Joachim
    0.38
     Otto
    0.38
    جوم
    0.37
    phol
    0.37
    öpf
    0.37
    POSITIVE LOGITS
    pard
    0.43
    wia
    0.41
    兟
    0.41
     ಬಂದ
    0.40
     ٹرسٹ
    0.40
    惠
    0.39
    翳
    0.39
     लहंगा
    0.39
     vliegt
    0.38
    俵
    0.37
    Act Density 0.000%

    No Known Activations