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

    Neuronpedia

    INDEX
    Explanations

    numeric values or references that indicate links to other sites or related information.

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

    numerical calculations and code snippets in a written document.

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

    names of trails, paths, or routes, particularly those related to recreation or transportation.

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

    Followed by specific punctuation or capitalization

    np_acts-logits-general · gemini-2.0-flash

    national wildlife crime unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     […]
    -1.46
     …
    -1.04
    <eos>
    -0.97
     ...
    -0.91
     [...]
    -0.89
    […]
    -0.88
    ↵
    -0.85
    ↵↵
    -0.83
     
    -0.81
    …
    -0.77
    POSITIVE LOGITS
     Савезне
    1.62
    Personensuche
    1.61
    tagHelperRunner
    1.60
     Мексичка
    1.42
     autorytatywna
    1.39
    ſelves
    1.36
    LookAnd
    1.36
     typelib
    1.36
    ſelf
    1.34
     defaultstate
    1.30
    Act Density 0.255%

    No Known Activations