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

    Neuronpedia

    INDEX
    Explanations

    references to the term "this" indicating context or state within code

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

    this ->

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slidesPer
    -0.47
     المعيارى
    -0.46
     &___
    -0.46
     disambiguazione
    -0.46
     lizenzfreies
    -0.45
    rawtypes
    -0.45
    +#+
    -0.44
    Portály
    -0.43
    tvguidetime
    -0.43
    言えば
    -0.42
    POSITIVE LOGITS
    this
    0.66
    Ini
    0.53
    THIS
    0.51
    SpringRunner
    0.50
    Fisher
    0.49
    InjectMocks
    0.47
    UpInside
    0.46
    Ceci
    0.46
    Hamilton
    0.45
    verwaltung
    0.45
    Act Density 0.003%

    No Known Activations