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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    interstitial
    -0.81
    oples
    -0.81
    issance
    -0.78
     Yugoslavia
    -0.75
     Yugoslav
    -0.74
    atically
    -0.73
    vernment
    -0.71
    asonic
    -0.65
    1945
    -0.63
     onset
    -0.62
    POSITIVE LOGITS
    oxide
    0.68
    ERO
    0.66
    OTOS
    0.66
    bors
    0.65
    ographies
    0.64
    Chel
    0.63
    ogh
    0.63
    ################
    0.63
    roy
    0.61
     Neighbor
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.