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

    Neuronpedia

    INDEX
    Explanations

    mentions of missions or goals

    oai_token-act-pair · gpt-3.5-turbo

    references to missions and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.84
    picking
    -0.82
    Column
    -0.77
     Ange
    -0.70
    urrency
    -0.68
    urrencies
    -0.68
    cling
    -0.66
    batch
    -0.66
    amera
    -0.66
    ª
    -0.64
    POSITIVE LOGITS
    eers
    0.90
     mission
    0.89
    arily
    0.88
     missions
    0.84
     creep
    0.81
     Impossible
    0.81
     Vie
    0.76
     accomplished
    0.75
     abroad
    0.74
     Mission
    0.73
    Act Density 0.019%

    No Known Activations