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

    Neuronpedia

    INDEX
    Explanations

    mentions and details about different types of engines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.32
     reinstate
    -0.74
     inaugurate
    -0.73
     defray
    -0.72
     mobilize
    -0.70
     rehabilitate
    -0.70
     rejoined
    -0.70
     disbur
    -0.70
     strode
    -0.68
     recollect
    -0.68
    POSITIVE LOGITS
     Engine
    1.18
     engine
    1.17
     engines
    1.10
     Engines
    1.09
     Minang
    1.09
    Engine
    1.07
     maroc
    1.07
    Engines
    1.04
     ENGINE
    1.04
    engines
    1.04
    Act Density 0.071%

    No Known Activations