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

    Neuronpedia

    INDEX
    Explanations

    mentions of charitable activities

    oai_token-act-pair · gpt-3.5-turbo

    references to charities and charitable actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amura
    -0.83
    anian
    -0.73
    ás
    -0.71
    ussen
    -0.70
    abe
    -0.69
    nu
    -0.67
    uru
    -0.66
    ropolitan
    -0.64
    qi
    -0.63
    achus
    -0.62
    POSITIVE LOGITS
     organization
    1.01
     organisation
    1.00
     organizations
    0.98
     charity
    0.94
     fundraising
    0.94
     donation
    0.91
     foundation
    0.90
     fundraiser
    0.89
     organisations
    0.89
     charitable
    0.88
    Act Density 0.069%

    No Known Activations