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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ansas
    -0.76
     appellant
    -0.71
    follow
    -0.69
    quit
    -0.68
    cill
    -0.62
    rys
    -0.60
    ment
    -0.60
     occupant
    -0.60
     heed
    -0.60
    ments
    -0.60
    POSITIVE LOGITS
    isSpecialOrderable
    0.72
    hess
    0.67
    KI
    0.64
    EVA
    0.63
    FORMATION
    0.62
    Strong
    0.62
    Beta
    0.62
    orne
    0.61
    INT
    0.61
     Everyone
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.