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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting of dialogue or narrative flow

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

    following a dash or comma

    np_acts-logits-general · gemini-2.0-flash

    em dash punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utory
    -0.59
    ppsala
    -0.54
    enido
    -0.54
    nodeValue
    -0.54
    irut
    -0.53
    ulz
    -0.52
    #%%
    -0.52
    YourGuide
    -0.52
    trecht
    -0.52
    migrationBuilder
    -0.51
    POSITIVE LOGITS
    the
    1.40
    that
    1.32
    there
    1.30
    this
    1.29
    they
    1.26
    and
    1.24
    but
    1.24
    when
    1.21
    it
    1.20
    if
    1.19
    Act Density 0.618%

    No Known Activations