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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols that indicate questions or exclamations

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

    Punctuation, especially exclamation marks

    np_acts-logits-general · gemini-2.0-flash

    exclamation marks and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.84
     дописавши
    -0.72
    VERTISEMENT
    -0.71
     виправивши
    -0.70
     تضيفلها
    -0.70
     endfor
    -0.69
     defaultstate
    -0.69
     Fond
    -0.69
    Fond
    -0.68
    providedIn
    -0.68
    POSITIVE LOGITS
    !
    1.01
    !!!
    0.97
    !!
    0.95
    !!!!
    0.92
    !!!!!
    0.82
    !!!!!!
    0.80
    ！
    0.76
    !!!!!!!
    0.76
    !!!)
    0.75
    !!)
    0.75
    Act Density 0.140%

    No Known Activations