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

    Neuronpedia

    INDEX
    Explanations

    references to the target audience or readership

    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
     Ide
    -0.68
    phrine
    -0.66
    empt
    -0.65
     Scot
    -0.64
    idy
    -0.63
    ced
    -0.63
    grave
    -0.62
    erald
    -0.61
     Plum
    -0.61
    abs
    -0.60
    POSITIVE LOGITS
    atics
    0.88
     audience
    0.82
    atically
    0.80
    Reviewer
    0.78
     members
    0.77
     audiences
    0.76
     member
    0.75
    members
    0.75
    atic
    0.75
    iences
    0.74
    Act Density 0.026%

    No Known Activations