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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .$
    -0.86
     Forbidden
    -0.72
    kj
    -0.68
    DNA
    -0.68
    coins
    -0.65
    ochond
    -0.64
     castles
    -0.63
    +=
    -0.63
     wisely
    -0.62
    Explore
    -0.62
    POSITIVE LOGITS
    ĵ
    0.75
    ĪĴ
    0.70
    govtrack
    0.67
    archives
    0.66
    ¿½
    0.64
    plain
    0.64
    rounder
    0.61
    ĺħ
    0.61
    £ı
    0.60
    intendent
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.