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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .testing
    -0.07
     funny
    -0.07
    -offset
    -0.07
    _find
    -0.07
     PIO
    -0.07
     afraid
    -0.07
    供电
    -0.06
     ImVec
    -0.06
    _flow
    -0.06
    /contentassist
    -0.06
    POSITIVE LOGITS
    不敢
    0.07
     Geliş
    0.06
     dern
    0.06
     trends
    0.06
    ±
    0.06
     States
    0.06
     depicted
    0.06
    иру
    0.06
    telefono
    0.06
    战国
    0.06
    Act Density 0.126%

    No Known Activations