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

    Neuronpedia

    INDEX
    Explanations

    the presence of single-character or one-letter responses in conversations

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

    I found

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

    markers that signal the start of an answer/model response, including the answer delimiter and the first token(s) of the reply.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.51
     AssemblyCulture
    -0.49
    aarrggbb
    -0.49
    WebpackPlugin
    -0.48
     يتيمه
    -0.47
    SupportActionBar
    -0.46
    رشف
    -0.46
    featureID
    -0.45
    HtmlAttribute
    -0.44
    PreExecute
    -0.44
    POSITIVE LOGITS
    UnsafeEnabled
    0.44
    localctx
    0.34
    ribut
    0.34
    AntiForgeryToken
    0.32
     Guilford
    0.32
    soccer
    0.31
    tvguidetime
    0.31
    prüche
    0.31
     Examiners
    0.31
     Morn
    0.31
    Act Density 0.002%

    No Known Activations