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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    spell
    -0.71
    veyard
    -0.66
    Enlarge
    -0.64
    icons
    -0.62
     guts
    -0.62
     Graveyard
    -0.61
    Bench
    -0.61
     antioxid
    -0.60
     Spotlight
    -0.60
    arth
    -0.58
    POSITIVE LOGITS
    apo
    0.81
    hered
    0.81
    equ
    0.79
    ument
    0.68
     Pol
    0.66
    quartered
    0.66
    ether
    0.65
     Dise
    0.65
    bred
    0.64
    olution
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.