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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals as members of groups or committees

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals holding membership positions in various organizations or committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anche
    -0.85
    ources
    -0.83
    bows
    -0.79
    elsius
    -0.78
    orsi
    -0.77
    urses
    -0.75
    cale
    -0.72
    ahime
    -0.71
    cape
    -0.70
    imar
    -0.70
    POSITIVE LOGITS
    holder
    0.87
    Joined
    0.83
    member
    0.82
     member
    0.77
     Member
    0.77
     membership
    0.77
    Activity
    0.77
     STATES
    0.76
    leader
    0.75
     isEnabled
    0.74
    Act Density 0.026%

    No Known Activations