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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Shape
    -0.74
    UFF
    -0.65
    ologically
    -0.63
    inventoryQuantity
    -0.62
     Trance
    -0.58
    gered
    -0.58
    abytes
    -0.58
     Barron
    -0.57
    ORPG
    -0.57
    ilant
    -0.57
    POSITIVE LOGITS
    lig
    0.77
    photos
    0.76
    avorable
    0.67
    ãĥīãĥ©
    0.63
     parity
    0.63
     advis
    0.62
    wan
    0.62
    lik
    0.61
     hangs
    0.61
     aux
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.