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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is given as a courtesy or provided by someone or a source

    oai_token-act-pair · gpt-3.5-turbo

    the word "courtesy" and its variations, indicating references to sources or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pton
    -0.83
    lear
    -0.79
    vals
    -0.78
    thin
    -0.77
    oshenko
    -0.77
    ggle
    -0.75
    icted
    -0.74
    ago
    -0.74
    alone
    -0.73
    thing
    -0.73
    POSITIVE LOGITS
    tesy
    1.14
     courtesy
    1.06
    giving
    0.81
     Credit
    0.77
    CLASSIFIED
    0.76
     Thomson
    0.76
     swipe
    0.70
     Dragonbound
    0.69
     ®
    0.67
     Courtesy
    0.67
    Act Density 0.006%

    No Known Activations