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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Titus
    -0.78
     Sut
    -0.72
    eous
    -0.69
     Theodore
    -0.69
     Omn
    -0.68
     Roads
    -0.67
     Cortex
    -0.66
    eering
    -0.65
    istani
    -0.65
    ð
    -0.64
    POSITIVE LOGITS
     dropped
    0.70
     capitals
    0.68
     reluct
    0.67
     drops
    0.67
    unk
    0.66
    adobe
    0.63
     empt
    0.62
    host
    0.62
     lenders
    0.61
     coefficient
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.