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

    Neuronpedia

    INDEX
    Explanations

    phrases related to charitable donations and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "benefit" or "influence"

    np_acts-logits-general · gemini-2.0-flash

    benefit Save

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.57
    RTEE
    -0.55
    -------
    -0.55
     ✭✭
    -0.52
     Gael
    -0.51
     FTSE
    -0.50
    󠁣
    -0.49
     pprint
    -0.47
    heça
    -0.47
     lowa
    -0.47
    POSITIVE LOGITS
     Hospice
    0.66
     charity
    0.61
     CreateTagHelper
    0.57
     Humane
    0.56
    oneofs
    0.56
     animal
    0.56
     zvuky
    0.55
     Favorite
    0.54
     favorite
    0.54
     Alzheimer
    0.52
    Act Density 0.016%

    No Known Activations