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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to audience engagement or public interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subordinates
    -0.61
     disbanded
    -0.60
     mediation
    -0.57
     subcontract
    -0.55
     refinement
    -0.55
     dismant
    -0.55
    HQ
    -0.55
     treaties
    -0.54
     Presidency
    -0.54
     staffing
    -0.52
    POSITIVE LOGITS
     wondering
    0.83
     noticing
    0.81
     instinctively
    0.78
     nostalgic
    0.77
     experiencing
    0.77
     craving
    0.77
     appreciate
    0.77
    Interested
    0.77
    ustomed
    0.76
     watching
    0.76
    Act Density 0.987%

    No Known Activations