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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \<
    -0.71
    MH
    -0.70
     GOODMAN
    -0.68
    ELY
    -0.68
    KEN
    -0.67
     Yog
    -0.64
    :(
    -0.63
    WER
    -0.62
    Nar
    -0.62
    AIR
    -0.61
    POSITIVE LOGITS
    ugu
    0.85
    acion
    0.73
    opped
    0.72
    ussia
    0.68
    doms
    0.66
     extraord
    0.66
    ierrez
    0.65
    conservancy
    0.64
     amnesty
    0.64
    icago
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.