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

    Neuronpedia

    INDEX
    Explanations

    references to speed or velocity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eryl
    -0.80
    oral
    -0.79
    roma
    -0.79
    pha
    -0.74
    ortium
    -0.72
    arl
    -0.71
     Bie
    -0.71
    pheus
    -0.71
    tical
    -0.70
    qqa
    -0.70
    POSITIVE LOGITS
     speed
    1.00
    wagon
    1.00
    loader
    0.98
     acceleration
    0.95
    boat
    0.92
     speeds
    0.92
    boats
    0.88
    speed
    0.88
    running
    0.88
    iest
    0.86
    Act Density 0.021%

    No Known Activations