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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Verhältnis
    0.44
     गर्ल
    0.41
    啻
    0.41
    簾
    0.40
     బ్యాంకు
    0.38
    0.38
     Dietary
    0.38
    पेयी
    0.38
    ׃
    0.38
     Occurrence
    0.37
    POSITIVE LOGITS
    dead
    0.43
    wedge
    0.40
     models
    0.40
     apologies
    0.39
     apology
    0.38
     whisper
    0.38
     modeller
    0.38
     モデル
    0.38
     모델
    0.37
     whispered
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.