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

    Neuronpedia

    INDEX
    Explanations

    terms related to unintended or unintentional outcomes

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

    unintended consequence or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.70
    AnchorStyles
    -0.64
    ьаж
    -0.63
     مشين
    -0.63
    CloseOperation
    -0.60
    ніципа
    -0.55
    PickerController
    -0.54
     &___
    -0.54
    :✨
    -0.54
    Архівовано
    -0.54
    POSITIVE LOGITS
     unintended
    1.77
     unintentional
    1.56
     unintentionally
    1.51
     inadvert
    1.47
     inadvertently
    1.40
     uninten
    1.04
     accidental
    1.03
     unwittingly
    1.02
     unforeseen
    0.99
     unplanned
    0.97
    Act Density 0.009%

    No Known Activations