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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ishops
    -0.73
    BILITIES
    -0.71
    SHIP
    -0.70
     Mandatory
    -0.67
    )].
    -0.65
    IRC
    -0.64
     Cosponsors
    -0.64
    istries
    -0.63
     Chev
    -0.63
    tein
    -0.62
    POSITIVE LOGITS
    yang
    0.74
    strom
    0.68
    vil
    0.63
    DonaldTrump
    0.61
    yu
    0.60
    uler
    0.60
     redemption
    0.60
    VALUE
    0.59
    marine
    0.59
     prevail
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.