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

    Neuronpedia

    INDEX
    Explanations

    data related to participants' offline activities and merits in a system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activity metrics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otin
    -0.71
    lite
    -0.63
    ounter
    -0.62
    igans
    -0.62
    fits
    -0.61
     Anthem
    -0.60
    kj
    -0.60
    nas
    -0.60
    mus
    -0.59
     abl
    -0.59
    POSITIVE LOGITS
    ?????-
    0.66
    ©¶æ¥µ
    0.64
    Description
    0.60
    Action
    0.59
    thinkable
    0.59
    Super
    0.57
    Dec
    0.57
    Reward
    0.57
    Movie
    0.57
     ACTIONS
    0.56
    Act Density 0.081%

    No Known Activations