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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an action or choice related to selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovember
    -0.72
    orah
    -0.66
    amen
    -0.62
    geist
    -0.61
     resil
    -0.58
    âĹ¼
    -0.58
    chief
    -0.57
    warming
    -0.57
    pires
    -0.57
    atics
    -0.55
    POSITIVE LOGITS
    arate
    0.71
    ause
    0.65
     Submit
    0.65
     ACTIONS
    0.64
    Export
    0.63
    oa
    0.63
    ivity
    0.62
    anges
    0.61
    Widget
    0.61
     UNCLASSIFIED
    0.61
    Act Density 0.004%

    No Known Activations