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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     forcefully
    0.44
    賏
    0.43
     کوتا
    0.42
    粙
    0.42
     контро
    0.41
    ทอง
    0.41
    ⼈
    0.41
     Jap
    0.41
    鍾
    0.40
     Rules
    0.40
    POSITIVE LOGITS
    lger
    0.40
     zak
    0.39
    pentine
    0.39
    就没有
    0.39
    മ്
    0.38
    rte
    0.38
     fatal
    0.38
     Mixed
    0.37
     dvar
    0.37
    pmatrix
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.