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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Scale
    -0.66
    cale
    -0.65
    lore
    -0.65
     scale
    -0.64
     reckoning
    -0.63
     substitute
    -0.62
     sprite
    -0.60
    rend
    -0.60
     solution
    -0.60
     form
    -0.59
    POSITIVE LOGITS
    uador
    0.82
    killed
    0.77
    ounded
    0.76
    uploads
    0.76
    chwitz
    0.73
    oÄŁ
    0.69
    sett
    0.69
    aned
    0.68
    capt
    0.67
    ownt
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.