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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate the significance or necessity of actions or conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     enough
    -0.56
    reda
    -0.52
     gila
    -0.52
     poids
    -0.49
     Sécurité
    -0.49
     autrement
    -0.48
     payé
    -0.48
     saites
    -0.48
     saurait
    -0.48
    клопе
    -0.47
    POSITIVE LOGITS
    RetentionPolicy
    0.83
     GenerationType
    0.76
    HostException
    0.76
    AccessFile
    0.74
     Савезне
    0.65
     WebDriverWait
    0.64
    getColumnIndex
    0.60
    SuppressMessage
    0.59
    жере
    0.59
    GenerationType
    0.59
    Act Density 0.062%

    No Known Activations