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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    named
    -0.76
    ranged
    -0.74
    =~
    -0.72
    necess
    -0.69
    mentioned
    -0.69
    beh
    -0.66
    nor
    -0.65
    ../
    -0.64
    controller
    -0.64
    democratic
    -0.64
    POSITIVE LOGITS
    BILITIES
    0.82
    çīĪ
    0.80
     BIT
    0.71
    anon
    0.69
     TA
    0.66
    Bi
    0.65
     TOUR
    0.65
    urai
    0.63
    ricanes
    0.63
    iatus
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.