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

    Neuronpedia

    INDEX
    Explanations

    mentions of charitable activities or donations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of charitable organizations or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Demand
    -0.74
    UID
    -0.68
     Rasmussen
    -0.67
     Detected
    -0.67
     Clockwork
    -0.66
     Kardashian
    -0.65
     Sty
    -0.65
    PUT
    -0.64
    noon
    -0.63
    Sensor
    -0.63
    POSITIVE LOGITS
     charity
    1.11
     charities
    1.07
     fundra
    0.84
     orphans
    0.79
     charitable
    0.79
    ilial
    0.78
     mosqu
    0.77
    itably
    0.77
     solicitation
    0.76
    intern
    0.76
    Act Density 0.011%

    No Known Activations