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

    Neuronpedia

    INDEX
    Explanations

    terms related to speed or rapid movement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to speed and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caption
    -0.72
    nam
    -0.70
    acles
    -0.69
    OME
    -0.69
    omes
    -0.68
    bery
    -0.67
    nee
    -0.65
    AME
    -0.64
     Cosponsors
    -0.64
    shire
    -0.62
    POSITIVE LOGITS
     velocity
    1.40
    ocity
    1.27
     Velocity
    1.10
    Vel
    0.95
     acceleration
    0.82
     mosqu
    0.82
     trajectory
    0.78
     recoil
    0.76
    ability
    0.75
     acceler
    0.75
    Act Density 0.006%

    No Known Activations