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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    âĶģ
    -0.78
     Cosponsors
    -0.76
     Ratio
    -0.74
    engine
    -0.70
     Address
    -0.70
    ury
    -0.68
     BaseType
    -0.68
     Riv
    -0.67
    uries
    -0.67
     âĹ
    -0.66
    POSITIVE LOGITS
     vend
    0.74
     flo
    0.70
    engu
    0.67
     slump
    0.66
    tered
    0.65
    ucks
    0.64
    lp
    0.64
     Winston
    0.64
    wn
    0.63
     Jama
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.