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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cedes
    -0.74
    pite
    -0.73
    osity
    -0.70
    afort
    -0.67
    anium
    -0.67
    arse
    -0.66
    avering
    -0.66
    osponsors
    -0.64
    jad
    -0.62
    negie
    -0.62
    POSITIVE LOGITS
    rosis
    0.70
    Ò
    0.67
    naissance
    0.65
     Sherman
    0.65
    imental
    0.63
     Abrams
    0.61
    GREEN
    0.60
    sov
    0.60
     hipp
    0.59
    EST
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.