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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consequence or result

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

    preceding negative experiences or actions

    np_acts-logits-general · gemini-2.0-flash

    undesirable outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зулта
    -0.63
    ynchronously
    -0.59
    EDEFAULT
    -0.59
     Reun
    -0.58
    webElementXpaths
    -0.57
    windowFixed
    -0.57
    nisses
    -0.56
    onViewCreated
    -0.55
    nambuco
    -0.55
    transQ
    -0.55
    POSITIVE LOGITS
     such
    0.71
     solche
    0.70
    Such
    0.64
     Such
    0.64
     betroffen
    0.62
     समस्या
    0.61
     affected
    0.59
     suffer
    0.58
     подоб
    0.58
    ViewFeatures
    0.58
    Act Density 0.557%

    No Known Activations