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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.73
    schild
    -0.73
    hyde
    -0.71
    allas
    -0.71
     Towns
    -0.70
    DonaldTrump
    -0.68
    idon
    -0.68
    dylib
    -0.67
    ciating
    -0.66
    alys
    -0.66
    POSITIVE LOGITS
     Rainbow
    0.73
     Drop
    0.65
     Alto
    0.65
     scissors
    0.65
     certification
    0.60
     DU
    0.59
    inventoryQuantity
    0.58
    duc
    0.58
     \'
    0.57
     testers
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.