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

    Neuronpedia

    INDEX
    Explanations

    behaviors indicative of passive-aggressive tendencies

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

    deviation from normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.51
    hopefully
    -0.47
    eleste
    -0.45
    expandindo
    -0.44
     hoped
    -0.43
    Hauptartikel
    -0.42
     vár
    -0.42
    潜力
    -0.41
     stim
    -0.41
    quiry
    -0.41
    POSITIVE LOGITS
     unusually
    0.94
     suddenly
    0.86
     ungewöhn
    0.82
     sudden
    0.80
     inusual
    0.79
     unusual
    0.77
     plötzlich
    0.77
     soudain
    0.73
     excessively
    0.72
     abnormally
    0.71
    Act Density 0.052%

    No Known Activations