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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.80
    nesday
    -0.75
    orah
    -0.74
    kos
    -0.73
    nir
    -0.73
    hovah
    -0.70
    nai
    -0.70
    arers
    -0.70
    ãĥĥãĥī
    -0.69
    kefeller
    -0.69
    POSITIVE LOGITS
    anova
    0.77
    ives
    0.66
    crit
    0.64
    udi
    0.62
     Lust
    0.59
     EP
    0.59
    pects
    0.58
    usive
    0.58
     Chaff
    0.57
     escapes
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.