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

    Neuronpedia

    INDEX
    Explanations

    email addresses and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    symbols or phrases associated with email and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³³³
    -0.72
    ;;;;
    -0.70
     dock
    -0.63
    âĶģ
    -0.63
    ////////////////////////////////
    -0.62
     Chains
    -0.62
     Angels
    -0.61
     ..............
    -0.61
     ......
    -0.59
     ....
    -0.59
    POSITIVE LOGITS
    medi
    0.79
    world
    0.71
    daily
    0.70
    serious
    0.69
    turn
    0.66
    usat
    0.66
    bleacher
    0.65
    hidden
    0.65
    threat
    0.64
    arthed
    0.64
    Act Density 0.042%

    No Known Activations