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

    Neuronpedia

    INDEX
    Explanations

    social media handles and URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and user accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bragging
    -0.73
     fin
    -0.64
     deduction
    -0.64
     intest
    -0.64
    naire
    -0.63
     Dame
    -0.62
     frying
    -0.61
    anca
    -0.61
    slaught
    -0.61
    agan
    -0.60
    POSITIVE LOGITS
    Help
    0.86
    Follow
    0.85
    Magazine
    0.84
    Dispatch
    0.83
    iframe
    0.80
    News
    0.80
     Investigative
    0.78
    Alert
    0.77
    Politics
    0.77
    Subscribe
    0.75
    Act Density 0.191%

    No Known Activations