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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks and exclamation points

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

    Opening quotation marks

    np_acts-logits-general · gemini-2.0-flash

    dialogue punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.03
     itſelf
    -0.94
    __':
    -0.90
     myſelf
    -0.88
     fhort
    -0.83
    LEGGI
    -0.83
    LLocation
    -0.82
     raiſ
    -0.82
    __":
    -0.78
     ſy
    -0.78
    POSITIVE LOGITS
     “
    1.65
     "
    1.53
    “
    1.25
    「
    1.24
     „
    1.22
     «
    1.22
    、「
    1.19
    ，“
    1.12
     ‘
    1.10
     「
    1.03
    Act Density 0.155%

    No Known Activations