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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    alg
    -0.77
    ajor
    -0.77
    sonian
    -0.74
    ahime
    -0.72
    aper
    -0.72
    rils
    -0.71
    arus
    -0.70
    atra
    -0.70
    rift
    -0.69
     CES
    -0.68
    POSITIVE LOGITS
     WHITE
    0.62
    Ĥª
    0.61
     Reply
    0.61
     TRUMP
    0.60
     Tile
    0.59
     Firm
    0.59
     Feather
    0.58
     Knock
    0.58
     Older
    0.57
     Hoo
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.