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

    Neuronpedia

    INDEX
    Explanations

    occupational roles or titles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles or positions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.84
     domains
    -0.81
    isms
    -0.81
     Puzzles
    -0.77
     petitions
    -0.76
    ships
    -0.76
     shotguns
    -0.75
     interfaces
    -0.74
     Rooms
    -0.70
     grievances
    -0.69
    POSITIVE LOGITS
     performer
    1.15
     dancer
    1.03
     contributor
    1.02
     lover
    1.01
    angler
    0.97
     keeper
    0.95
     participant
    0.94
     practitioner
    0.94
     guy
    0.94
    mitter
    0.93
    Act Density 0.475%

    No Known Activations