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

    Neuronpedia

    INDEX
    Explanations

    terms associated with nuclear weapons and their capabilities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.65
     polizia
    -0.64
     кӀ
    -0.57
     policiales
    -0.56
    VIAF
    -0.55
    yelitis
    -0.54
     ['./
    -0.54
     movimenti
    -0.53
     beweging
    -0.52
    ContextCompat
    -0.52
    POSITIVE LOGITS
     Wikimedijinoj
    0.57
    parsedMessage
    0.56
     nukes
    0.56
     nuke
    0.55
     AppCompatTheme
    0.55
    featureID
    0.55
    buttonBar
    0.54
    zeka
    0.53
    almaz
    0.52
    lccn
    0.52
    Act Density 0.010%

    No Known Activations