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

    Neuronpedia

    INDEX
    Explanations

    references to changes in societal attitudes or values

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

    deterioration or decline

    np_acts-logits-general · gemini-2.0-flash

    decline or deterioration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.59
    CppMethod
    -0.56
    請繼續往下閱讀
    -0.52
    Autoritní
    -0.50
    rungsseite
    -0.49
     NSCoder
    -0.49
    PickerController
    -0.48
    openhauer
    -0.48
    -------------</
    -0.48
     wiedzieć
    -0.47
    POSITIVE LOGITS
     decline
    0.54
     deterioration
    0.52
     deteriorated
    0.48
     degeneration
    0.47
     declining
    0.47
     deteriorating
    0.45
     declines
    0.42
     deteriorate
    0.42
     slowing
    0.41
     becoming
    0.40
    Act Density 0.894%

    No Known Activations