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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hades
    -0.72
     Sark
    -0.71
     Nickel
    -0.69
     Cartoon
    -0.69
     Vs
    -0.68
     Keyboard
    -0.67
     Tolkien
    -0.66
     Premiere
    -0.66
     Sapphire
    -0.64
     Tob
    -0.64
    POSITIVE LOGITS
    mble
    0.81
    rowd
    0.78
    animous
    0.73
    Whit
    0.71
    ership
    0.71
    aida
    0.71
    nown
    0.71
    oup
    0.70
    lv
    0.70
    ifest
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.