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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     laun
    -0.72
     Seym
    -0.70
     skew
    -0.70
    ĪĴ
    -0.67
    ahime
    -0.66
     DD
    -0.65
     themed
    -0.64
    azeera
    -0.62
     Wrap
    -0.62
     RTX
    -0.61
    POSITIVE LOGITS
    imen
    0.68
    Minor
    0.67
    eping
    0.66
    eda
    0.66
    rian
    0.65
    efe
    0.64
    ares
    0.64
    emy
    0.64
    ookie
    0.63
    emies
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.