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

    Neuronpedia

    INDEX
    Explanations

    first person plural or singular pronouns alone or in combination with a verb.

    oai_token-act-pair · gemini-2.0-flash

    any non-standard or informal expressions

    np_token-act-pair-logits · gpt-4o-mini

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shocked
    -1.41
     astonished
    -1.27
     disappointed
    -1.26
     stunned
    -1.23
     delighted
    -1.23
     shock
    -1.23
    shocked
    -1.21
     surprised
    -1.20
     overjoyed
    -1.20
     disgusted
    -1.20
    POSITIVE LOGITS
    aarrggbb
    0.66
    GraphicsUnit
    0.50
    dropna
    0.46
    mobileqq
    0.41
    cche
    0.39
     refirió
    0.39
    liferay
    0.39
    saida
    0.39
    HtmlAttribute
    0.38
     fuoco
    0.38
    Act Density 1.080%

    No Known Activations