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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to giveaways and charitable distributions

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

    giveaways and sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.60
     RDC
    -0.55
    ########.
    -0.54
    DockStyle
    -0.48
    ponses
    -0.48
    lossians
    -0.47
    codiles
    -0.46
    tanleria
    -0.46
    HandleFunc
    -0.45
     yolks
    -0.45
    POSITIVE LOGITS
     giveaway
    1.90
     Giveaway
    1.69
     giveaways
    1.61
    Giveaway
    1.41
     Geschenk
    0.73
     GIVE
    0.73
     gift
    0.71
    aways
    0.69
    give
    0.69
    eaway
    0.68
    Act Density 0.002%

    No Known Activations