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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "peek"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "peek" or variations related to looking or seeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to taking a quick look or glance at something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iction
    -0.87
    ãĥŁ
    -0.77
    Interstitial
    -0.75
    effective
    -0.73
    dependent
    -0.72
    famous
    -0.71
    majority
    -0.71
    million
    -0.70
    versive
    -0.70
    responsible
    -0.70
    POSITIVE LOGITS
     peek
    1.35
     wink
    0.73
     hints
    0.73
    atz
    0.72
     headlights
    0.71
     glimps
    0.70
     Nieto
    0.70
     previews
    0.70
    hao
    0.68
    abies
    0.66
    Act Density 0.011%

    No Known Activations