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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bench
    -0.07
     võ
    -0.07
    ="<?=
    -0.07
     Jian
    -0.07
    _validation
    -0.07
     שימוש
    -0.07
     (_)
    -0.07
    יפ
    -0.07
    _flow
    -0.07
    行政
    -0.07
    POSITIVE LOGITS
     horizon
    0.07
    멤
    0.07
     habits
    0.06
     decorate
    0.06
    .ObjectMeta
    0.06
    混
    0.06
    �
    0.06
     traumat
    0.06
     intoxicated
    0.06
    这段时间
    0.06
    Act Density 0.006%

    No Known Activations