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

    Neuronpedia

    INDEX
    Explanations

    social media handles for various individuals and platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to social media interactions and follow requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anan
    -0.63
    chwitz
    -0.61
    ring
    -0.60
     unanim
    -0.60
    uable
    -0.59
     massac
    -0.59
    aughtered
    -0.59
    ingen
    -0.58
    cific
    -0.58
     surplus
    -0.57
    POSITIVE LOGITS
     Twitter
    1.68
     twitter
    1.62
    Twitter
    1.48
     Facebook
    1.34
     Instagram
    1.25
    Facebook
    1.21
     facebook
    1.20
    facebook
    1.19
    twitter
    1.15
     LinkedIn
    1.14
    Act Density 0.037%

    No Known Activations