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

    Neuronpedia

    INDEX
    Explanations

    promotional offers and customer engagement phrases

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

    advertisements and free offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    openConnection
    -0.39
    oredCriteria
    -0.39
    awakeFromNib
    -0.39
    wapV
    -0.38
    SharedCtor
    -0.37
     voeten
    -0.37
    AppMethodBeat
    -0.36
     onCancelled
    -0.34
     Governors
    -0.34
    websocket
    -0.34
    POSITIVE LOGITS
     advertised
    0.77
     reklama
    0.61
     advertisement
    0.59
     advertisements
    0.58
     publicidad
    0.58
    adverti
    0.57
    廣告
    0.56
    广告
    0.56
     advertising
    0.56
     rekla
    0.55
    Act Density 0.074%

    No Known Activations