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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     depress
    0.53
     mergers
    0.51
     patents
    0.51
     routines
    0.49
     negative
    0.49
     thousands
    0.49
     depletion
    0.49
     outperform
    0.48
     modify
    0.48
     bey
    0.48
    POSITIVE LOGITS
     матч
    0.63
    朼
    0.59
    Ⲛ
    0.58
    禣
    0.58
    ꞌ
    0.57
    Игра
    0.57
    Israeli
    0.56
    '".
    0.56
    䢀
    0.56
    Ки
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.