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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (_("
    -0.07
    副秘书长
    -0.07
    㫴
    -0.07
    ⽥
    -0.07
    炳
    -0.07
    (txt
    -0.07
    ירו
    -0.07
    徹
    -0.06
    并无
    -0.06
    狀
    -0.06
    POSITIVE LOGITS
    嘻
    0.07
     subsets
    0.07
    דע
    0.07
     customization
    0.07
    خطط
    0.07
    怀疑
    0.07
     hype
    0.06
    Dub
    0.06
     그런
    0.06
     checkpoint
    0.06
    Act Density 0.030%

    No Known Activations