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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.47
     itſelf
    -1.12
     ſeveral
    -1.06
     ſind
    -1.05
     myſelf
    -1.04
     Monfieur
    -1.02
     Anſ
    -0.99
     themſelves
    -0.99
     ་་
    -0.99
     ويكيميديا
    -0.98
    POSITIVE LOGITS
     '
    3.35
     ‘
    2.63
     "
    2.14
     ('
    1.98
    ('
    1.98
    ='
    1.95
     ['
    1.75
    -'
    1.73
     ’
    1.70
    =>'
    1.65
    Act Density 0.098%

    No Known Activations