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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     underrated
    -0.75
    phrine
    -0.65
    orate
    -0.64
     Dominican
    -0.64
    å¦
    -0.62
     precinct
    -0.62
    rade
    -0.62
     Pryor
    -0.61
    orers
    -0.60
     Bahá
    -0.60
    POSITIVE LOGITS
    kat
    0.68
    rikes
    0.65
    aughtered
    0.64
     {:
    0.64
     cooper
    0.63
    nown
    0.63
    iscovery
    0.62
    erial
    0.62
    artifacts
    0.62
    heter
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.