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

    Neuronpedia

    INDEX
    Explanations

    terms related to speed or fast processes

    oai_token-act-pair · gpt-3.5-turbo

    references to speed or efficiency in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.86
    eryl
    -0.82
    inatory
    -0.78
    tical
    -0.75
    rien
    -0.74
    vironment
    -0.74
    oral
    -0.73
    utical
    -0.72
    riel
    -0.72
    gdala
    -0.72
    POSITIVE LOGITS
    running
    1.00
    loader
    0.98
    iest
    0.93
    wagon
    0.93
    ily
    0.89
    iness
    0.87
    boat
    0.87
    runs
    0.87
     speed
    0.86
    boats
    0.85
    Act Density 0.025%

    No Known Activations