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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     notwendig
    1.10
     entscheid
    1.10
     nötig
    1.08
     sayang
    1.06
     Imo
    1.05
     humain
    1.02
    ूड
    1.00
    Jetzt
    1.00
     lèvres
    1.00
     mivel
    0.99
    POSITIVE LOGITS
     معمول
    1.07
    کار
    1.06
    𝒏
    1.05
    方式
    1.03
    𝐧
    1.01
    იდან
    1.01
    Career
    1.00
    𝐫
    0.98
    ے۔
    0.98
    setC
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.