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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tremend
    -0.72
    gian
    -0.68
    theless
    -0.68
    Glass
    -0.68
    hello
    -0.67
     Hallow
    -0.67
     Lancaster
    -0.67
    ModLoader
    -0.66
    rent
    -0.64
    Fil
    -0.63
    POSITIVE LOGITS
    eworks
    0.71
    alore
    0.67
     sway
    0.65
    odox
    0.65
    etta
    0.64
     Diesel
    0.63
     indul
    0.63
    >]
    0.61
    opal
    0.61
    ablish
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.