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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pe
    -0.31
     she
    -0.28
    ilon
    -0.28
    æĭľ
    -0.27
     Pe
    -0.27
     pe
    -0.26
    hat
    -0.26
    åŃĶ
    -0.26
     wast
    -0.26
     leash
    -0.26
    POSITIVE LOGITS
    .ModelForm
    0.29
    rush
    0.29
    onian
    0.29
    ç»ıè´¹
    0.28
    //{↵
    0.27
    arking
    0.26
    æ¶ħ
    0.26
    xfc
    0.25
    /{$
    0.25
    callable
    0.25
    Act Density 0.004%

    No Known Activations

    This feature has no known activations.