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

    Neuronpedia

    INDEX
    Explanations

    labels and indicators related to scenes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostante
    -0.80
    hematical
    -0.75
    hitung
    -0.72
     provisoire
    -0.70
    RetentionPolicy
    -0.70
    üyük
    -0.68
     extensible
    -0.68
    autonomie
    -0.67
    úgó
    -0.67
     cortas
    -0.67
    POSITIVE LOGITS
     scene
    1.99
     scenes
    1.91
     SCENE
    1.85
     Scene
    1.82
    SceneManagement
    1.70
     Scenes
    1.63
    scene
    1.61
    Scene
    1.55
    SCENE
    1.54
    Scenes
    1.48
    Act Density 0.048%

    No Known Activations