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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    esson
    -0.67
    chwitz
    -0.67
     reconc
    -0.65
    baugh
    -0.64
     happen
    -0.63
     Objects
    -0.63
    Weapons
    -0.63
    mol
    -0.63
    getic
    -0.62
     installations
    -0.61
    POSITIVE LOGITS
    #$
    0.71
     Priority
    0.65
    awar
    0.65
     ILCS
    0.64
    pecting
    0.62
     LINE
    0.62
    ayson
    0.61
     hindsight
    0.61
     underest
    0.60
    arsity
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.