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

    Neuronpedia

    INDEX
    Explanations

    instances of things or people coming back to a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inational
    -0.79
    enaries
    -0.64
     pall
    -0.64
    rifice
    -0.63
    ities
    -0.62
    wealth
    -0.62
    ifix
    -0.62
    ision
    -0.61
    uary
    -0.59
    kel
    -0.59
    POSITIVE LOGITS
    tracking
    1.12
    GROUND
    1.08
    dated
    1.01
    packing
    1.01
    packs
    0.99
    stab
    0.90
    ordered
    0.88
    fires
    0.86
    seat
    0.84
    fired
    0.84
    Act Density 0.051%

    No Known Activations