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

    Neuronpedia

    INDEX
    Explanations

    events or actions that happened in the past

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inational
    -0.68
     viz
    -0.63
    orpor
    -0.61
     dioxide
    -0.61
     constitu
    -0.61
    risome
    -0.60
    ×IJ
    -0.60
    izo
    -0.59
     wa
    -0.58
     tyr
    -0.58
    POSITIVE LOGITS
    wards
    1.07
    GROUND
    1.07
    lash
    1.05
    dated
    1.05
    packs
    1.01
    stories
    0.98
    stab
    0.98
    door
    0.98
    tracking
    0.96
    ward
    0.94
    Act Density 0.037%

    No Known Activations