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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vict
    -0.08
    <context
    -0.07
     textbooks
    -0.07
     besie
    -0.07
    caught
    -0.07
    ϙ
    -0.07
    สไต
    -0.07
    Cole
    -0.06
    찐
    -0.06
    LEAN
    -0.06
    POSITIVE LOGITS
    ível
    0.07
    帶
    0.07
    프
    0.07
    有更多的
    0.07
    _ID
    0.06
    إل
    0.06
     datab
    0.06
    意图
    0.06
    ank
    0.06
    至上
    0.06
    Act Density 0.003%

    No Known Activations