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

    Neuronpedia

    INDEX
    Explanations

    references to indoor and outdoor locations or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to outdoor and indoor activities or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.65
    sections
    -0.64
    inders
    -0.64
    nce
    -0.64
     artery
    -0.62
    acts
    -0.60
    gments
    -0.60
    nex
    -0.58
    ptic
    -0.58
    ptoms
    -0.58
    POSITIVE LOGITS
     outdoors
    1.09
     indoors
    0.99
    manship
    0.97
    creen
    0.94
    ModLoader
    0.86
    men
    0.85
    edIn
    0.82
    erness
    0.81
    smanship
    0.80
    ï¸
    0.79
    Act Density 0.009%

    No Known Activations