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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    irtual
    -0.87
    angler
    -0.78
    ission
    -0.75
    ynt
    -0.74
    wild
    -0.73
    atically
    -0.72
    animous
    -0.69
    utation
    -0.69
    ember
    -0.68
    eto
    -0.67
    POSITIVE LOGITS
     Rico
    0.72
    ONSORED
    0.71
     Mub
    0.70
     Neck
    0.70
     Suffolk
    0.66
     respectively
    0.65
     Clyde
    0.64
     Giul
    0.64
     Mare
    0.61
     Sod
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.