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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and adjectives indicating specificity

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

    such / this / these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haupt
    -0.44
    things
    -0.43
    redacted
    -0.43
    CppMethod
    -0.42
    stark
    -0.42
    Shang
    -0.42
    GOTREF
    -0.41
     desertcart
    -0.41
    retail
    -0.41
     Shang
    -0.41
    POSITIVE LOGITS
     Paglinawan
    0.53
     كومونز
    0.45
     mêmes
    0.45
     Wiktionnaire
    0.44
     enfermera
    0.43
     plegable
    0.41
     uveden
    0.41
     oznacza
    0.40
     дописавши
    0.39
     dieselbe
    0.39
    Act Density 0.030%

    No Known Activations