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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and phrases indicating dialogue or speech

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

    Punctuation before quoted speech or interjections

    np_acts-logits-general · gemini-2.0-flash

    quote followed by dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ................
    -0.52
    ...............
    -0.47
    ...........
    -0.46
    ........
    -0.46
    ..............
    -0.46
    …………………………………………
    -0.45
    ..........
    -0.45
    aden
    -0.43
    ...)
    -0.43
    ......
    -0.42
    POSITIVE LOGITS
     hey
    1.06
     Hey
    0.96
     okay
    0.92
     OK
    0.85
    Hey
    0.83
     Okay
    0.81
    Hozzáférés
    0.81
     “
    0.79
     wow
    0.79
     ok
    0.78
    Act Density 0.122%

    No Known Activations