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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    إمكان
    -0.07
     pun
    -0.07
     verify
    -0.06
    𬘬
    -0.06
    这件事情
    -0.06
    劣势
    -0.06
     renowned
    -0.06
    (turn
    -0.06
    (cljs
    -0.06
    唐山
    -0.06
    POSITIVE LOGITS
     Цена
    0.07
     oi
    0.07
    天河
    0.06
    0.06
    0.06
    0.06
     结
    0.06
     centres
    0.06
     Svens
    0.06
    _reordered
    0.06
    Act Density 0.016%

    No Known Activations