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

    Neuronpedia

    INDEX
    Explanations

    references to volunteer activities

    oai_token-act-pair · gpt-3.5-turbo

    references to volunteer work and volunteer-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fixes
    -0.80
    erella
    -0.78
    hetti
    -0.76
    acles
    -0.72
    etr
    -0.70
    dar
    -0.70
    etus
    -0.69
    down
    -0.69
    eki
    -0.68
    Rated
    -0.67
    POSITIVE LOGITS
    unte
    1.16
     volunteering
    1.00
     volunteer
    0.92
     Volunteers
    0.87
     firefighter
    0.84
     volunteers
    0.83
     volunteered
    0.73
    izable
    0.73
    intern
    0.73
     Volunte
    0.72
    Act Density 0.022%

    No Known Activations