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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     לקרא
    -0.08
    ре
    -0.07
    人力
    -0.07
    성이
    -0.07
    长大了
    -0.07
    زواج
    -0.06
    Reporting
    -0.06
    очно
    -0.06
     Thu
    -0.06
    @AllArgsConstructor
    -0.06
    POSITIVE LOGITS
     defenses
    0.07
    (grammar
    0.07
     Wass
    0.07
     Dysfunction
    0.06
    薢
    0.06
    _player
    0.06
    鳉
    0.06
     Andrea
    0.06
    ɝ
    0.06
     flavour
    0.06
    Act Density 0.010%

    No Known Activations