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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pions
    0.89
     facets
    0.87
     vows
    0.86
    爹
    0.85
     boobs
    0.84
     dangers
    0.83
    erty
    0.83
     sputtered
    0.82
    allItems
    0.81
     TCS
    0.81
    POSITIVE LOGITS
    ኾ
    0.84
     abhängig
    0.83
     separately
    0.83
    рган
    0.83
    別に
    0.83
    䡏
    0.81
    锭
    0.81
     vooraf
    0.81
     परिचय
    0.81
    вшей
    0.80
    Act Density 0.000%

    No Known Activations