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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ioxide
    -0.83
    kefeller
    -0.83
    emale
    -0.77
     1922
    -0.73
     1923
    -0.71
    ibaba
    -0.71
     1924
    -0.67
    velength
    -0.67
     Waves
    -0.66
    igree
    -0.66
    POSITIVE LOGITS
     ANGEL
    0.80
    ------------------------
    0.78
    MEN
    0.71
    Secondly
    0.70
    >]
    0.70
     =====
    0.70
     VIDEOS
    0.70
     --------------------
    0.69
    SW
    0.66
     hostage
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.