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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles and automotive engineering

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     alkoh
    -0.79
     kosme
    -0.79
     kollek
    -0.76
     panik
    -0.75
     Malte
    -0.72
     ideolog
    -0.71
     Ferdin
    -0.71
     konkre
    -0.70
     Jä
    -0.70
     monaster
    -0.69
    POSITIVE LOGITS
     performance
    0.61
     outperform
    0.60
     achievable
    0.58
     performances
    0.56
    ongevity
    0.55
    creamy
    0.55
     capability
    0.55
     durability
    0.54
     conftest
    0.53
     efficiency
    0.53
    Act Density 0.351%

    No Known Activations