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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vre
    -0.74
     initialized
    -0.67
    gel
    -0.66
    ateur
    -0.65
     vegan
    -0.61
     Camden
    -0.60
     Kelvin
    -0.59
     ..."
    -0.59
     artif
    -0.59
     ammonia
    -0.58
    POSITIVE LOGITS
    enza
    0.89
    otions
    0.80
    ials
    0.77
    adan
    0.73
    azines
    0.71
    ç¥ŀ
    0.68
     Cance
    0.66
     Records
    0.66
    uria
    0.64
     Clan
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.