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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their roles in contexts involving communication or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulously
    -0.77
    GGGGGGGG
    -0.73
    uctive
    -0.73
     perjury
    -0.72
    nesday
    -0.70
    igree
    -0.70
    aminer
    -0.69
    utherford
    -0.67
    spection
    -0.66
    PASS
    -0.65
    POSITIVE LOGITS
    xus
    0.83
    ®
    0.80
    §
    0.78
    «
    0.76
    eries
    0.75
    Ń
    0.75
    ¨
    0.73
    Ĭ
    0.73
    ©¶æ
    0.69
    er
    0.69
    Act Density 0.013%

    No Known Activations