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

    Neuronpedia

    INDEX
    Explanations

    references to pledges, promises, and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orz
    -0.16
    بط
    -0.16
    vidia
    -0.15
    quo
    -0.15
     geile
    -0.15
    اسطة
    -0.15
    unkt
    -0.14
     Tcp
    -0.14
     सल
    -0.13
    oucher
    -0.13
    POSITIVE LOGITS
     promise
    0.92
     promises
    0.84
     Promise
    0.77
     commitments
    0.71
     commitment
    0.70
    promise
    0.70
     pledge
    0.69
     promised
    0.69
    Promise
    0.67
     pledges
    0.64
    Act Density 0.394%

    No Known Activations