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

    Neuronpedia

    INDEX
    Explanations

    phrases and keywords related to significant historical events and statements regarding their implications

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

    specific phrases or endings

    np_acts-logits-general · gemini-2.5-flash-lite

    high-frequency function words and contraction markers (articles, pronouns, auxiliaries, and apostrophes), with occasional spikes on numerals/dates and initial chunks of proper nouns.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.52
    Tikang
    -0.46
    JsonPropertyName
    -0.43
     Infór
    -0.41
     énon
    -0.41
     dividido
    -0.41
     élu
    -0.40
     Utf
    -0.40
     éduc
    -0.40
    newspaper
    -0.39
    POSITIVE LOGITS
     AssemblyCulture
    0.53
     heapq
    0.42
    forRoot
    0.42
     Wikimedijinoj
    0.40
    WriteTagHelper
    0.39
     priori
    0.37
    ----</
    0.37
     старости
    0.37
    setContentView
    0.36
    -------
    0.35
    Act Density 0.054%

    No Known Activations