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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ause
    -0.73
    roller
    -0.68
     Sevent
    -0.65
    naire
    -0.64
     Sheen
    -0.64
    />
    -0.63
    atorium
    -0.63
    antasy
    -0.62
     Expend
    -0.61
    acious
    -0.59
    POSITIVE LOGITS
     istg
    0.79
    ÏĢ
    0.75
    DAQ
    0.72
    ãĤ´ãĥ³
    0.72
    æ©Ł
    0.70
    imentary
    0.68
    æľ
    0.68
    ãģĨ
    0.67
    vable
    0.66
    GBT
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.