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

    Neuronpedia

    INDEX
    Explanations

    titles or mentions of individuals in a council or committee

    oai_token-act-pair · gpt-3.5-turbo

    mentions of membership or affiliation with groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sell
    -0.72
    ils
    -0.71
    iannopoulos
    -0.71
    escal
    -0.71
    uder
    -0.70
    offensive
    -0.70
    elf
    -0.69
    ources
    -0.69
    acha
    -0.68
    orah
    -0.68
    POSITIVE LOGITS
     Member
    1.29
    Member
    1.11
    ertodd
    1.04
     Members
    0.97
    Activity
    0.91
    Joined
    0.90
    holder
    0.84
    holders
    0.79
     States
    0.79
     Membership
    0.78
    Act Density 0.008%

    No Known Activations