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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    schild
    -0.75
    isphere
    -0.74
     disbel
    -0.73
    cv
    -0.71
    CV
    -0.65
    heit
    -0.65
    heimer
    -0.63
    MH
    -0.62
     antiv
    -0.61
    USS
    -0.60
    POSITIVE LOGITS
    arcity
    0.88
     Sox
    0.76
    gdala
    0.73
    uca
    0.67
    agues
    0.66
    gars
    0.66
    hyde
    0.65
    otle
    0.63
    berto
    0.63
    umerable
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.