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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    æĸ¹
    -0.79
    ety
    -0.71
    than
    -0.67
    fighter
    -0.66
     skyline
    -0.66
    together
    -0.66
    escape
    -0.65
     marines
    -0.62
     Texans
    -0.62
     Imperium
    -0.61
    POSITIVE LOGITS
    ometown
    0.74
    ENE
    0.72
    inventoryQuantity
    0.72
    brew
    0.67
    ktop
    0.64
    uling
    0.64
    ANE
    0.62
    sle
    0.62
    ULAR
    0.61
    ECK
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.