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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tsukuyomi
    -0.78
     Ecuador
    -0.71
     majorities
    -0.64
     sack
    -0.64
     Ferdinand
    -0.64
    pressed
    -0.63
    mares
    -0.63
    vation
    -0.61
     jug
    -0.60
     shrug
    -0.60
    POSITIVE LOGITS
    oult
    0.77
    Blade
    0.76
    IOR
    0.73
    ources
    0.66
    arten
    0.65
    add
    0.63
    inton
    0.60
    CLASSIFIED
    0.60
    mel
    0.60
    Contin
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.