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

    Neuronpedia

    INDEX
    Explanations

    terms related to expedited or fast-tracked processes or procedures

    oai_token-act-pair · gpt-3.5-turbo

    words related to expedited processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.86
    arov
    -0.80
    artisan
    -0.79
    ãĤ¤ãĥĪ
    -0.70
    achev
    -0.69
    undy
    -0.68
     Compass
    -0.65
    anners
    -0.65
    orno
    -0.65
    folk
    -0.63
    POSITIVE LOGITS
     commute
    1.09
     deliveries
    0.86
    escal
    0.79
     delivery
    0.78
     commuting
    0.77
     fulfillment
    0.77
    otide
    0.75
    motion
    0.73
     interval
    0.73
    aneous
    0.73
    Act Density 0.320%

    No Known Activations