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

    Neuronpedia

    INDEX
    Explanations

    discussions about advertising models and consumer behavior regarding devices.

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

    references to technology, specifically related to devices and their functionalities.

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

    punctuation marks, especially periods, question marks, and commas, often at the end of sentences or clauses.

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

    Question at the end of a text

    np_acts-logits-general · gemini-2.0-flash

    maybe perhaps probably

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     absolutamente
    -0.61
    териалы
    -0.60
    tissima
    -0.58
    !!!!!!!!!!!!!!!!
    -0.56
    ！】
    -0.55
    ArrowToggle
    -0.55
    !\
    -0.55
    ！！」
    -0.55
    requently
    -0.53
    !!!!!!!
    -0.53
    POSITIVE LOGITS
     maybe
    1.69
     Maybe
    1.51
    maybe
    1.46
    Maybe
    1.45
     perhaps
    1.44
     Perhaps
    1.28
    perhaps
    1.25
    Perhaps
    1.20
     probably
    1.15
     talvez
    1.13
    Act Density 0.452%

    No Known Activations