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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    癞
    0.42
     tá
    0.39
     randomize
    0.38
     tart
    0.37
    塔
    0.36
     troll
    0.36
     ih
    0.36
    撸
    0.36
    梖
    0.36
     tk
    0.35
    POSITIVE LOGITS
     neglecting
    1.02
     neglects
    0.88
    忽略
    0.80
     forgetting
    0.80
     neglect
    0.79
     ignoring
    0.76
     olvid
    0.73
     forgets
    0.73
     forgot
    0.72
     забы
    0.72
    Act Density 0.096%

    No Known Activations