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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    urat
    -0.75
    adders
    -0.73
     Aires
    -0.72
    enum
    -0.71
    DIT
    -0.71
    ources
    -0.71
     Parameters
    -0.70
    yth
    -0.70
    mosp
    -0.68
     Frie
    -0.67
    POSITIVE LOGITS
     satell
    0.74
     privatization
    0.64
     peas
    0.63
     tuna
    0.63
    mast
    0.63
     espionage
    0.59
     puppy
    0.58
     Thief
    0.58
     cler
    0.56
     Pilgrim
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.