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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles.

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

    personal and professional biographical information.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    titles, honorifics, and formal designations for people, especially in professional or official contexts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Honorifics and titles

    np_acts-logits-general · gemini-2.0-flash

    honorifics and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eslint
    -0.50
    eca
    -0.49
    pah
    -0.47
    stan
    -0.47
    __()
    -0.47
     اقت
    -0.47
    OPA
    -0.47
    telse
    -0.46
    apor
    -0.46
    pach
    -0.45
    POSITIVE LOGITS
     Dr
    1.30
     Prof
    1.20
    Dr
    1.20
     Professor
    1.20
     Mrs
    1.15
    Professor
    1.12
     Monfieur
    1.12
     Drs
    1.11
    Prof
    1.09
    Mrs
    1.09
    Act Density 0.150%

    No Known Activations