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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ha
    1.07
    polit
    1.06
    ting
    1.06
    ы
    1.05
    フォーマンス
    1.04
    రాలు
    1.02
    बिनेट
    1.01
     menghubungi
    1.01
    ற்புத
    1.00
    jähr
    0.98
    POSITIVE LOGITS
     GED
    1.23
     openai
    1.22
     (−
    1.17
     livelihood
    1.15
     ironing
    1.13
     keras
    1.13
    jols
    1.12
     kerat
    1.11
     препят
    1.10
    疇
    1.10
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.