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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    esity
    -0.76
     Gaul
    -0.68
    Virginia
    -0.65
    hound
    -0.62
    cca
    -0.61
    load
    -0.61
    ruary
    -0.60
    nered
    -0.60
    glomer
    -0.60
    LO
    -0.60
    POSITIVE LOGITS
     newsletters
    0.69
    ript
    0.69
    orks
    0.68
    ãĤ¨ãĥ«
    0.66
    argon
    0.64
    ffiti
    0.64
     wards
    0.63
     partName
    0.62
     Divinity
    0.62
    ograms
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.