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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ICLE
    -0.77
    oder
    -0.72
    ottage
    -0.72
    OTE
    -0.71
    Advertisements
    -0.71
    Mods
    -0.70
    HT
    -0.68
    CEPT
    -0.67
    uin
    -0.65
    GROUP
    -0.64
    POSITIVE LOGITS
     Barcl
    0.73
     Canaver
    0.69
     Sabb
    0.68
     NEC
    0.65
     Polo
    0.64
    prints
    0.62
     Charg
    0.62
    responsible
    0.61
     Barron
    0.61
     Alberto
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.