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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the concept of going back or returning

    oai_token-act-pair · gpt-3.5-turbo

    references to returning or going back to a previous state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ision
    -0.69
    ifix
    -0.68
    nt
    -0.67
    ise
    -0.65
    tein
    -0.64
    ities
    -0.64
    ittee
    -0.63
    inational
    -0.61
     viz
    -0.60
    uary
    -0.59
    POSITIVE LOGITS
    GROUND
    1.01
    dated
    0.99
    side
    0.99
    packs
    0.97
    door
    0.97
    )=(
    0.96
    tracking
    0.91
    gam
    0.88
    stab
    0.88
    wards
    0.87
    Act Density 0.074%

    No Known Activations