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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.92
    {"
    -0.76
     {"
    -0.75
    ]["
    -0.75
     “
    -0.74
     ".
    -0.72
    “
    -0.70
    ={"
    -0.70
    "
    -0.68
     "";
    -0.68
    POSITIVE LOGITS
     ‘
    1.44
     '
    1.33
    『
    1.22
     (‘
    1.18
    、『
    1.09
    。『
    1.03
    -'
    1.01
    (‘
    1.01
    |'
    1.00
     ('
    1.00
    Act Density 0.064%

    No Known Activations