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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abouts
    -0.70
     "$:/
    -0.64
     fossils
    -0.63
    holes
    -0.62
    EStreamFrame
    -0.61
    æĪ¦
    -0.60
    ?]
    -0.60
    ILA
    -0.60
    osaurus
    -0.59
    tery
    -0.58
    POSITIVE LOGITS
    yrinth
    0.82
    aeus
    0.73
    pec
    0.65
     AES
    0.65
    lav
    0.63
     ASA
    0.62
     Recommend
    0.60
    zik
    0.59
    formance
    0.59
    antz
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.