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

    Neuronpedia

    INDEX
    Explanations

    words related to unwanted or undesirable situations

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

    unwanted side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.76
    lapsingToolbar
    -0.65
    KommentareTeilen
    -0.63
    DockStyle
    -0.61
    EndContext
    -0.60
    AndEndTag
    -0.56
    رشف
    -0.55
    ))^{
    -0.55
     المعيارى
    -0.55
    ArrowToggle
    -0.55
    POSITIVE LOGITS
     unwanted
    2.06
     unwelcome
    1.28
     undesirable
    1.23
     undes
    1.02
     unintended
    0.80
    undes
    0.79
    wanted
    0.73
     ناخ
    0.72
     unsolicited
    0.71
     ungew
    0.66
    Act Density 0.006%

    No Known Activations