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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ارت
    0.81
    𝘵
    0.81
    ेंद्र
    0.77
    ūn
    0.77
    umbent
    0.75
    IDI
    0.74
    enuine
    0.74
    perty
    0.73
     слот
    0.72
    ن
    0.71
    POSITIVE LOGITS
     let
    0.74
     translucent
    0.73
     become
    0.72
     sheep
    0.68
     cloak
    0.68
     cent
    0.68
     continue
    0.68
     wear
    0.67
     Photo
    0.67
     baz
    0.67
    Act Density 0.000%

    No Known Activations