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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aments
    -0.77
     Parables
    -0.77
    affles
    -0.74
    uchs
    -0.74
    enegger
    -0.71
    ashington
    -0.71
    irgin
    -0.71
    yon
    -0.69
    aji
    -0.68
    ushima
    -0.68
    POSITIVE LOGITS
     uptake
    0.73
     bandwagon
    0.69
     cervical
    0.65
     detection
    0.65
    cheat
    0.65
    emp
    0.64
     WW
    0.63
     overload
    0.63
    rower
    0.62
     OPS
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.