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

    Neuronpedia

    INDEX
    Explanations

    words related to specific goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "aimed" related to intended outcomes or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.81
     Solitaire
    -0.77
     Leilan
    -0.77
     Combine
    -0.75
    Score
    -0.72
     Norn
    -0.70
     Situation
    -0.68
    Legend
    -0.67
    natureconservancy
    -0.67
     Split
    -0.66
    POSITIVE LOGITS
     aimed
    1.02
     toward
    0.94
    sonian
    0.91
     aiming
    0.89
    emouth
    0.87
     towards
    0.85
    ovie
    0.85
     provoking
    0.84
     thrust
    0.81
     squarely
    0.80
    Act Density 0.014%

    No Known Activations