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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various types of computer drives

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of drives, specifically related to technology and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -1.03
    ileaks
    -0.83
    icipated
    -0.74
     truce
    -0.70
     Lumpur
    -0.69
    oco
    -0.67
    orically
    -0.67
    abad
    -0.66
    iege
    -0.64
    ambo
    -0.63
    POSITIVE LOGITS
    away
    0.94
    train
    0.93
    aways
    0.79
    Drive
    0.77
    haw
    0.76
    back
    0.75
    hardt
    0.73
    drive
    0.71
    bike
    0.71
    driving
    0.70
    Act Density 0.027%

    No Known Activations