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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     adjusting
    -0.07
    professional
    -0.07
    绘
    -0.07
     promotion
    -0.07
     Bracket
    -0.07
     LN
    -0.07
    _cover
    -0.07
     orbital
    -0.07
    itled
    -0.07
    otional
    -0.06
    POSITIVE LOGITS
     שעות
    0.07
    	Set
    0.07
    semi
    0.07
    Be
    0.07
    печат
    0.07
    ToRemove
    0.06
    慰
    0.06
    ㅆ
    0.06
    ömür
    0.06
     reass
    0.06
    Act Density 0.009%

    No Known Activations