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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotation marks in the text

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

    llbracket bracketed sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?”
    -0.55
    ”
    -0.53
    nha
    -0.52
    ”?
    -0.48
    anan
    -0.48
    Shady
    -0.47
    anen
    -0.47
     suspens
    -0.47
    ”“
    -0.46
    ？”
    -0.46
    POSITIVE LOGITS
    '''
    1.55
     '''
    1.27
    '''
    1.13
    ''')
    0.86
    ''''
    0.80
    ('''
    0.74
    ''',
    0.63
    ''');
    0.59
     transfieras
    0.57
    mstyle
    0.57
    Act Density 0.059%

    No Known Activations