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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals or purposes

    oai_token-act-pair · gpt-3.5-turbo

    references to goals or aims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Torrent
    -0.67
    zz
    -0.65
     Pratt
    -0.62
     Cumber
    -0.62
    irl
    -0.61
     Parks
    -0.61
     ming
    -0.60
    ines
    -0.59
     strains
    -0.59
     Ruff
    -0.59
    POSITIVE LOGITS
     objective
    3.86
     objectives
    2.22
     Objective
    2.19
     goal
    1.62
     aim
    1.50
     unbiased
    1.45
     objectively
    1.42
     subjective
    1.41
    object
    1.36
    goal
    1.32
    Act Density 0.018%

    No Known Activations