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

    Neuronpedia

    INDEX
    Explanations

    names of social media platforms and specific online profiles

    oai_token-act-pair · gpt-3.5-turbo

    references to Facebook and social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olin
    -0.70
    aples
    -0.70
    Downloadha
    -0.70
    riott
    -0.67
    OPA
    -0.66
    rosc
    -0.64
    ktop
    -0.62
    riel
    -0.62
     Guardiola
    -0.62
    hov
    -0.61
    POSITIVE LOGITS
     username
    1.11
     page
    0.97
     profile
    0.96
     account
    0.94
     postings
    0.89
     timeline
    0.86
     hashtag
    0.85
     avatar
    0.84
     commenter
    0.83
     webpage
    0.83
    Act Density 0.110%

    No Known Activations