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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to agreements and consents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëłĪìĬ¤
    -0.15
    752
    -0.15
    registr
    -0.14
    stration
    -0.14
    882
    -0.14
    blr
    -0.14
    ekler
    -0.14
    miner
    -0.14
    ÃŃch
    -0.14
    486
    -0.14
    POSITIVE LOGITS
    rag
    0.17
     writing
    0.15
    writing
    0.15
     otherwise
    0.14
    .future
    0.14
    igu
    0.14
     Writing
    0.14
    otto
    0.13
     Naz
    0.13
     otra
    0.13
    Act Density 0.001%

    No Known Activations