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

    Neuronpedia

    INDEX
    Explanations

    references to fuel types and their efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.80
     Poi
    -0.61
     Kotlin
    -0.57
    Tembelea
    -0.55
    WithMany
    -0.53
     Burt
    -0.53
    سطس
    -0.53
    utilisons
    -0.53
     consents
    -0.53
    AccessorTable
    -0.52
    POSITIVE LOGITS
     fuel
    1.05
    Fuel
    0.89
     Fuel
    0.88
     топлива
    0.72
     FUEL
    0.71
    FUEL
    0.70
    fuel
    0.68
    djangoproject
    0.66
     anywhere
    0.64
    Tazama
    0.62
    Act Density 0.045%

    No Known Activations