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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    serious
    -0.07
    ij
    -0.06
    (Matrix
    -0.06
    ',{↵
    -0.06
    ila
    -0.06
     Mutation
    -0.06
     signs
    -0.06
     conscient
    -0.06
    	move
    -0.06
     Good
    -0.06
    POSITIVE LOGITS
     الساعة
    0.07
     intéress
    0.07
    华盛顿
    0.07
    漖
    0.07
    _Template
    0.07
     살아
    0.06
    ہ
    0.06
     예산
    0.06
    왓
    0.06
    _dep
    0.06
    Act Density 0.009%

    No Known Activations