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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sider
    -0.08
    셍
    -0.07
     jeszcze
    -0.07
    olate
    -0.07
    Founder
    -0.07
    UGH
    -0.07
     DATABASE
    -0.07
     horrible
    -0.07
     beginner
    -0.07
    久了
    -0.07
    POSITIVE LOGITS
     ­
    0.07
    ↤
    0.07
    ↳
    0.07
    实事求
    0.06
    没收
    0.06
    _peak
    0.06
     splits
    0.06
    _ME
    0.06
     scores
    0.06
    _almost
    0.06
    Act Density 0.005%

    No Known Activations