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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _intr
    -0.08
     informs
    -0.07
    ertype
    -0.07
     realise
    -0.07
    汆
    -0.07
    円
    -0.07
    American
    -0.06
    洼
    -0.06
     adip
    -0.06
     ağrı
    -0.06
    POSITIVE LOGITS
     וח
    0.08
    一緒
    0.07
     lasted
    0.07
     workspace
    0.07
    Tot
    0.07
     loophole
    0.07
     summar
    0.06
    葴
    0.06
    -way
    0.06
    是他
    0.06
    Act Density 0.000%

    No Known Activations