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

    Neuronpedia

    INDEX
    Explanations

    references to "this" and "that" in various contexts

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

    "This" as a discourse marker

    np_acts-logits-general · gemini-2.0-flash

    in this context or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.73
    exitRule
    -0.72
     arşivlendi
    -0.66
     مشين
    -0.57
    twimg
    -0.57
     snippetHide
    -0.56
    WithMany
    -0.56
     خارجية
    -0.55
     dams
    -0.55
     bezeichneter
    -0.54
    POSITIVE LOGITS
     regard
    0.68
     calendriers
    0.67
     anledning
    0.59
    complexContent
    0.56
    Neste
    0.56
     respect
    0.55
     vein
    0.55
    KommentareTeilen
    0.54
    yntaxException
    0.54
    jooq
    0.54
    Act Density 0.151%

    No Known Activations