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

    Neuronpedia

    INDEX
    Explanations

    references to plans, ideas, or aspirations for the future

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "vision" and perspectives on future goals or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.72
    byter
    -0.69
    avis
    -0.64
    paying
    -0.59
    Numbers
    -0.59
    Wr
    -0.58
    ahon
    -0.57
    due
    -0.56
     suscept
    -0.56
    achi
    -0.56
    POSITIVE LOGITS
    aries
    1.37
     vision
    1.15
     visions
    1.05
    alist
    0.91
    naire
    0.83
    scape
    0.83
    ary
    0.83
     visionary
    0.79
     Vision
    0.77
     goggles
    0.76
    Act Density 0.060%

    No Known Activations