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

    Neuronpedia

    INDEX
    Explanations

    numerical values like votes or times associated with certain actions, such as starting a playthrough in a game

    oai_token-act-pair · gpt-3.5-turbo

    references to votes and rankings related to games or competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendars
    -0.69
    yout
    -0.64
    20439
    -0.64
    humans
    -0.60
     unse
    -0.56
    Reloaded
    -0.56
    sch
    -0.55
    nen
    -0.55
     behav
    -0.55
     favor
    -0.53
    POSITIVE LOGITS
    escription
    0.63
    senal
    0.62
     Wraith
    0.60
     Azerb
    0.57
     Rica
    0.53
     ItemLevel
    0.53
    owship
    0.52
     Colts
    0.51
    icut
    0.51
    ucer
    0.51
    Act Density 1.453%

    No Known Activations