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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.79
    ãĥĨ
    -0.72
    ç·
    -0.66
    RIC
    -0.66
    wer
    -0.64
    inus
    -0.64
     Innocent
    -0.64
    rand
    -0.63
    axter
    -0.62
     Favorite
    -0.62
    POSITIVE LOGITS
    anwhile
    0.69
    skirts
    0.68
     sacks
    0.67
    export
    0.66
     enshr
    0.63
    gam
    0.63
    edom
    0.61
    gap
    0.60
    effic
    0.60
     Skydragon
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.