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

    Neuronpedia

    INDEX
    Explanations

    terms related to online content or intellectual property

    oai_token-act-pair · gpt-3.5-turbo

    references to "content" and variations of that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siem
    -0.73
    rolet
    -0.70
     damn
    -0.68
    vals
    -0.65
    udeb
    -0.64
     Sons
    -0.64
    athan
    -0.63
     Herb
    -0.61
    ipers
    -0.60
     Hank
    -0.59
    POSITIVE LOGITS
    edly
    1.52
    ment
    0.94
    ions
    0.89
    ioned
    0.85
     creators
    0.82
    ed
    0.81
     content
    0.79
    iar
    0.77
    Content
    0.76
    ication
    0.76
    Act Density 0.032%

    No Known Activations