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

    Neuronpedia

    INDEX
    Explanations

    mentions or discussions of audience

    oai_token-act-pair · gpt-3.5-turbo

    references to an audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    empt
    -0.71
     Ide
    -0.69
    phrine
    -0.67
    ced
    -0.66
    idy
    -0.64
    erald
    -0.64
    omic
    -0.64
    abs
    -0.64
     Plum
    -0.62
    grave
    -0.61
    POSITIVE LOGITS
     audience
    0.88
    atics
    0.87
    atically
    0.85
    Reviewer
    0.82
     audiences
    0.82
     tuning
    0.75
    ÃįÃį
    0.73
     tuned
    0.72
    atic
    0.70
    iences
    0.67
    Act Density 0.019%

    No Known Activations