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

    Neuronpedia

    INDEX
    Explanations

    references to engines and their components or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     directos
    -0.86
     Waw
    -0.83
    haway
    -0.83
     direta
    -0.81
    httphttps
    -0.81
     scolas
    -0.81
    oporosis
    -0.80
     sacrament
    -0.79
     CWE
    -0.79
     Justus
    -0.78
    POSITIVE LOGITS
     engines
    1.66
     engine
    1.54
     Engines
    1.48
    engines
    1.42
     Engine
    1.35
    engine
    1.32
    Engines
    1.29
     ENGINE
    1.27
    Engine
    1.27
    ENGINE
    1.21
    Act Density 0.092%

    No Known Activations