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

    Neuronpedia

    INDEX
    Explanations

    references to the intended audience or viewership, as well as mentions of reaching or connecting with them

    oai_token-act-pair · gpt-3.5-turbo

    references to an audience or viewers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erald
    -0.65
     Scot
    -0.64
    loo
    -0.63
    grave
    -0.62
    phrine
    -0.61
    nir
    -0.61
     Plum
    -0.61
    abs
    -0.60
     Ide
    -0.60
    bats
    -0.60
    POSITIVE LOGITS
    atics
    0.88
     member
    0.84
     members
    0.83
    atic
    0.80
     audiences
    0.79
     audience
    0.79
    members
    0.78
    atically
    0.77
    iences
    0.75
     Favorite
    0.69
    Act Density 0.030%

    No Known Activations