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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, decisions, and states of being, often with emphasis or impact

    oai_token-act-pair · gpt-3.5-turbo

    words related to action or movement concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reborn
    -0.80
     Kills
    -0.78
     Daylight
    -0.73
    ORGE
    -0.71
    GMT
    -0.69
     Abbey
    -0.69
    hower
    -0.69
     Tune
    -0.65
     Participant
    -0.64
    :]
    -0.64
    POSITIVE LOGITS
    alog
    0.92
    asting
    0.86
    aring
    0.84
    quartered
    0.83
    alogue
    0.80
    tain
    0.80
    itored
    0.79
    alyst
    0.79
    oldown
    0.79
    ivery
    0.78
    Act Density 0.162%

    No Known Activations