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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    蕲
    -0.08
     ----------------------------------------------------------------------------
    -0.07
     amigo
    -0.07
     inappropriate
    -0.07
     meaningful
    -0.07
    uplicate
    -0.07
    争
    -0.06
    iding
    -0.06
    inside
    -0.06
    ствовать
    -0.06
    POSITIVE LOGITS
    _MODEL
    0.07
    地下室
    0.07
    rès
    0.07
    .geom
    0.07
     brunette
    0.07
     churches
    0.07
    最常见的
    0.07
    シリーズ
    0.07
    _RED
    0.07
     explosions
    0.07
    Act Density 0.130%

    No Known Activations