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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inav
    -0.72
     antiquity
    -0.70
     moons
    -0.68
    vae
    -0.66
     necks
    -0.64
     throats
    -0.63
     Uran
    -0.62
     reform
    -0.61
    ulence
    -0.61
    Sov
    -0.61
    POSITIVE LOGITS
     ILCS
    0.84
     Cage
    0.74
    =-=-=-=-=-=-=-=-
    0.69
     Capcom
    0.68
     Melody
    0.68
     LAPD
    0.67
     Adren
    0.67
    oi
    0.67
    CAP
    0.66
    ijk
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.