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

    Neuronpedia

    INDEX
    Explanations

    characteristics and features that distinguish unique items or phenomena

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    hyp
    -0.54
     hypotheses
    -0.52
    prepareStatement
    -0.52
     Penrose
    -0.49
    Hyp
    -0.46
    Butyl
    -0.46
    rese
    -0.46
     Pind
    -0.46
     agronom
    -0.45
    ayah
    -0.45
    POSITIVE LOGITS
     unique
    0.82
     Unique
    0.81
    IBarButtonItem
    0.81
     caractéristique
    0.81
     characteristic
    0.81
    Characteristic
    0.80
     distinctive
    0.79
    HasAnnotation
    0.79
    characteristic
    0.78
     uniquely
    0.78
    Act Density 0.076%

    No Known Activations