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

    Neuronpedia

    INDEX
    Explanations

    text related to charitable donations and fundraising efforts

    oai_token-act-pair · gpt-3.5-turbo

    references to charitable organizations and their funding activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brute
    -0.93
     confir
    -0.88
     brut
    -0.83
    bole
    -0.82
     spoilers
    -0.80
     incrim
    -0.79
    ebin
    -0.74
     hypot
    -0.73
     speculation
    -0.73
     manip
    -0.73
    POSITIVE LOGITS
     Children
    1.31
     Youth
    1.30
     Autism
    1.28
     Scholarship
    1.25
     nonprofit
    1.20
     Homeless
    1.20
     Families
    1.20
     Mothers
    1.20
     Fellowship
    1.18
     Healing
    1.18
    Act Density 0.520%

    No Known Activations