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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    idan
    -0.91
    jen
    -0.84
    ÙĴ
    -0.80
     Faul
    -0.77
    forth
    -0.76
    lees
    -0.72
    channelAvailability
    -0.71
    inators
    -0.69
     Hort
    -0.68
    hound
    -0.67
    POSITIVE LOGITS
    eln
    0.69
     Mansion
    0.67
     adjud
    0.65
     polic
    0.62
     Assassin
    0.61
     opp
    0.60
     opinion
    0.60
    chwitz
    0.60
     magistrate
    0.59
    olicy
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.