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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ancer
    -0.68
    acious
    -0.66
    avia
    -0.66
    agger
    -0.63
    aye
    -0.62
    ydia
    -0.62
    idious
    -0.61
    odor
    -0.61
    akia
    -0.61
    ukemia
    -0.61
    POSITIVE LOGITS
     indo
    0.75
    ividual
    0.73
     whim
    0.68
    ramid
    0.64
     ptr
    0.64
     Referred
    0.64
     peanuts
    0.61
    usal
    0.61
     pegged
    0.61
     mock
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.