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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _SPECIAL
    -0.07
     poetry
    -0.07
     pokud
    -0.06
     Commentary
    -0.06
     cheeses
    -0.06
    raç
    -0.06
     COUNT
    -0.06
     Alger
    -0.06
    دن
    -0.06
    olid
    -0.06
    POSITIVE LOGITS
    rather
    0.08
    <View
    0.07
    Rather
    0.07
    дия
    0.06
    ollectors
    0.06
    phant
    0.06
     wakeup
    0.06
     disconnect
    0.06
    lep
    0.06
    单
    0.06
    Act Density 0.016%

    No Known Activations