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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Levine
    -0.68
    icut
    -0.67
    hoe
    -0.65
     defic
    -0.63
     Heller
    -0.62
    inical
    -0.62
    ema
    -0.62
     Hutchinson
    -0.62
    =#
    -0.61
    netflix
    -0.61
    POSITIVE LOGITS
     Picks
    0.64
    woods
    0.64
    swick
    0.63
    anmar
    0.63
    emale
    0.63
     Concept
    0.61
    yrinth
    0.61
    heon
    0.61
    ciples
    0.60
    rentice
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.