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

    Neuronpedia

    INDEX
    Explanations

    instances of text related to online content, such as news, updates, promotions, and website content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "content" related to various forms of media or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.72
     Rasmussen
    -0.68
    athan
    -0.67
    STRUCT
    -0.67
     Ram
    -0.62
     Werewolf
    -0.62
     Rosa
    -0.61
     Cot
    -0.61
     CVE
    -0.60
     AMERICA
    -0.60
    POSITIVE LOGITS
    edly
    1.38
     content
    1.11
    Content
    0.87
    content
    0.80
     Content
    0.79
    ais
    0.78
    estine
    0.71
    ioned
    0.71
    istence
    0.71
    lessly
    0.71
    Act Density 0.019%

    No Known Activations