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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating praise or deserving recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ома
    -0.15
    оби
    -0.14
    imson
    -0.14
    ARRIER
    -0.14
    intr
    -0.14
    TURE
    -0.13
    .Networking
    -0.13
    incerely
    -0.13
    .exchange
    -0.13
    pected
    -0.13
    POSITIVE LOGITS
     credit
    0.89
     Credit
    0.75
    credit
    0.73
    Credit
    0.70
     credits
    0.63
     Credits
    0.54
    _credit
    0.54
    .credit
    0.50
     créd
    0.50
    credits
    0.48
    Act Density 0.139%

    No Known Activations