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

    Neuronpedia

    INDEX
    Explanations

    descriptions of products and their features such as materials, functionalities, and benefits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and safety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affidav
    -0.51
    REDACTED
    -0.49
    éĥ
    -0.48
     reopened
    -0.48
     surn
    -0.48
     repud
    -0.47
    president
    -0.47
     retracted
    -0.47
    ãĤ¸
    -0.47
     admitting
    -0.46
    POSITIVE LOGITS
     outdoors
    0.62
     vibration
    0.61
     visually
    0.58
     airflow
    0.58
     effortlessly
    0.58
     vibrations
    0.58
    erning
    0.56
     gratification
    0.56
     versatility
    0.56
     smoother
    0.55
    Act Density 1.509%

    No Known Activations