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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aus
    -0.83
    birth
    -0.70
    abol
    -0.64
     shuffle
    -0.64
    quarter
    -0.63
    ched
    -0.61
     combust
    -0.61
    apor
    -0.61
    bec
    -0.61
    shoot
    -0.61
    POSITIVE LOGITS
     Gujar
    0.86
    adder
    0.74
    iaries
    0.73
     complicit
    0.73
     Sachs
    0.71
     msec
    0.69
    raltar
    0.67
     propos
    0.66
    orf
    0.66
     fortun
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.