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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    d
    0.79
     Position
    0.62
    Pos
    0.59
     Pos
    0.58
     Relation
    0.58
     Fund
    0.58
     Purse
    0.57
     "!
    0.57
     Gravity
    0.56
     Pol
    0.56
    POSITIVE LOGITS
     گزشتہ
    0.68
     اگلے
    0.66
    屢
    0.66
     nächste
    0.66
     mampu
    0.65
     infraestructura
    0.64
     другую
    0.64
    我还
    0.63
     кілька
    0.63
     പ
    0.63
    Act Density 0.010%

    No Known Activations