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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    opian
    -0.80
    >>>>>>>>
    -0.77
    ources
    -0.76
    ateurs
    -0.74
    ©¶æ
    -0.72
     ///
    -0.70
    athan
    -0.69
     âĹı
    -0.69
    gemony
    -0.68
    ¯¯¯¯¯¯¯¯
    -0.68
    POSITIVE LOGITS
    ufact
    0.73
     KL
    0.72
     Stab
    0.66
     Cinem
    0.66
    EMBER
    0.63
     Khalid
    0.61
     Cumber
    0.61
     Customer
    0.61
     Thames
    0.60
     KB
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.