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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ite
    1.12
    iting
    1.10
    ural
    1.03
     araç
    1.02
    ince
    0.98
    емости
    0.97
    rive
    0.97
    iverso
    0.96
    ixe
    0.95
    ude
    0.94
    POSITIVE LOGITS
    Reload
    1.39
    𝓗
    1.36
     discredited
    1.35
    \%.
    1.34
    一个
    1.33
     inaccur
    1.30
    晛
    1.27
    tung
    1.27
    Emotional
    1.25
    <unused416>
    1.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.