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

    Neuronpedia

    INDEX
    Explanations

    keywords related to completing tasks or challenges in a game context, particularly quests

    oai_token-act-pair · gpt-3.5-turbo

    mentions of quests or related terminology in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ————
    -0.73
    oci
    -0.66
    shr
    -0.66
     Slater
    -0.63
    weights
    -0.62
     thirds
    -0.58
    lihood
    -0.58
     atoms
    -0.58
     sexes
    -0.58
     iod
    -0.58
    POSITIVE LOGITS
    ioned
    1.35
    yrinth
    0.96
    rade
    0.92
    ing
    0.87
    love
    0.86
    naire
    0.84
    naires
    0.83
    ril
    0.82
    eria
    0.79
    uably
    0.78
    Act Density 0.050%

    No Known Activations