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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    elf
    -0.62
     Awakening
    -0.61
    space
    -0.61
     marks
    -0.61
    beat
    -0.60
     Impossible
    -0.58
     metast
    -0.58
     ABC
    -0.58
    breaker
    -0.57
     Toad
    -0.57
    POSITIVE LOGITS
    Ur
    0.76
    uzzle
    0.71
    rix
    0.70
    uer
    0.68
    zzle
    0.67
    etus
    0.67
    UD
    0.66
    Admin
    0.66
    î
    0.65
    UL
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.