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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.81
    yll
    -0.75
    Justice
    -0.74
    Iv
    -0.73
    ABC
    -0.71
    Rose
    -0.70
    UID
    -0.69
    rition
    -0.69
    DERR
    -0.68
    Daddy
    -0.67
    POSITIVE LOGITS
     paralyzed
    0.71
    igmatic
    0.67
    pter
    0.65
     pole
    0.64
     flank
    0.63
     reel
    0.62
    tor
    0.61
     copy
    0.60
    iens
    0.60
     parachute
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.