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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olation
    -0.88
    ooth
    -0.68
    auntlet
    -0.67
    ourney
    -0.66
    à¼
    -0.66
    wayne
    -0.64
    RAFT
    -0.63
    IG
    -0.63
     Forever
    -0.63
    IDER
    -0.62
    POSITIVE LOGITS
     spoiler
    0.68
     newcom
    0.62
    TOP
    0.59
    abama
    0.57
     hypot
    0.57
     displacement
    0.56
    mast
    0.56
     cav
    0.56
     excluding
    0.55
     assuming
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.