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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation and that indicate a shift in tone or content in the text

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

    periods that end sentences at the conclusion of paragraphs or major sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    <eos>
    -1.12
    ↵↵↵↵↵↵↵
    -0.99
    ↵↵↵
    -0.97
    ↵↵↵↵↵
    -0.93
    ↵↵↵↵↵↵
    -0.91
    ↵↵↵↵↵↵↵↵
    -0.91
    ↵↵↵↵
    -0.90
    ↵↵↵↵↵↵↵↵↵
    -0.89
    ↵↵
    -0.87
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.86
    POSITIVE LOGITS
    +#+#
    0.85
     kasarigan
    0.83
     يتيمه
    0.79
     صوتيه
    0.78
     jadx
    0.75
    RenderAtEndOf
    0.75
     كومونز
    0.75
    AddTagHelper
    0.75
     disambiguazione
    0.73
    rungsseite
    0.73
    Act Density 0.702%

    No Known Activations