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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    くな
    -0.07
     yaşad
    -0.07
    장애인
    -0.07
    审视
    -0.07
    -0.07
    热带
    -0.06
    bben
    -0.06
    阳县
    -0.06
     Beach
    -0.06
    퀅
    -0.06
    POSITIVE LOGITS
     cows
    0.08
    编码
    0.08
     modifiers
    0.08
    fig
    0.07
     whore
    0.07
     editing
    0.07
    __((
    0.07
     efficacy
    0.07
    (files
    0.07
    用戶
    0.07
    Act Density 0.018%

    No Known Activations