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

    Neuronpedia

    INDEX
    Explanations

    words related to formal communication and titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of formal titles and acknowledgments in a context of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.75
    spawn
    -0.73
     confir
    -0.70
     liking
    -0.69
    entimes
    -0.69
     messing
    -0.68
     sparing
    -0.67
     peril
    -0.67
    etheless
    -0.66
    conservancy
    -0.66
    POSITIVE LOGITS
     Catherine
    1.20
     Deborah
    1.19
     Cynthia
    1.19
     William
    1.19
     Kenneth
    1.18
     David
    1.17
     Peter
    1.17
     Katherine
    1.16
     Richard
    1.15
     Timothy
    1.15
    Act Density 0.245%

    No Known Activations