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

    Neuronpedia

    INDEX
    Explanations

    references to the physical back or rear position of objects or people

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "back"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    7601
    -0.70
    aukee
    -0.70
    Ń·
    -0.69
     Parenthood
    -0.69
    inational
    -0.68
    izo
    -0.67
    upon
    -0.66
    Cola
    -0.64
    éĹĺ
    -0.64
    eteria
    -0.64
    POSITIVE LOGITS
    side
    1.18
    packs
    1.01
    woods
    1.00
    drops
    0.94
    seat
    0.90
     alley
    0.89
    hand
    0.88
    door
    0.88
    stab
    0.88
    gam
    0.88
    Act Density 0.037%

    No Known Activations