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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Curtis
    -0.67
     Gret
    -0.65
     Guild
    -0.64
     GF
    -0.64
     Mist
    -0.63
     Gem
    -0.63
     Glover
    -0.62
     Gib
    -0.62
    ede
    -0.61
     Alger
    -0.61
    POSITIVE LOGITS
    gered
    0.83
    kefeller
    0.82
    irtual
    0.80
    puter
    0.78
    idine
    0.76
    ngth
    0.75
    onom
    0.73
    nir
    0.72
    kus
    0.71
    odynamics
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.