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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     incoherent
    0.86
     factorial
    0.84
     Xiang
    0.83
     asshole
    0.83
     Yue
    0.81
     Цуки
    0.80
     Hunan
    0.79
     antidepressant
    0.78
     endomet
    0.78
     alarming
    0.78
    POSITIVE LOGITS
    ان
    0.85
    ק
    0.77
    ח
    0.77
    ल
    0.76
    ச
    0.75
     vostra
    0.73
    ل
    0.73
    我
    0.72
    न
    0.72
    using
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.