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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mens
    -0.82
    izabeth
    -0.77
    oi
    -0.76
    hea
    -0.75
    een
    -0.70
    ital
    -0.68
    ASY
    -0.68
    chen
    -0.67
    aughed
    -0.66
    oga
    -0.66
    POSITIVE LOGITS
     reluct
    0.76
     brill
    0.72
     retina
    0.69
     cog
    0.66
     Moroc
    0.65
     Brill
    0.65
     Emblem
    0.64
    lights
    0.63
    ĪĴ
    0.63
     kitten
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.