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

    Neuronpedia

    INDEX
    Explanations

    names of organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to various international organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ½
    -0.84
    ãĤ¨ãĥ«
    -0.82
    sonian
    -0.78
    ð
    -0.77
    æµ
    -0.76
    espie
    -0.75
    Ö¼
    -0.72
    é£
    -0.71
     Gillespie
    -0.71
    ebook
    -0.69
    POSITIVE LOGITS
     XIII
    0.91
     Organization
    0.89
     Organisation
    0.84
    eers
    0.78
    ĸļ
    0.73
    ally
    0.72
     Headquarters
    0.71
    ovo
    0.70
     sanctioned
    0.70
    ality
    0.69
    Act Density 0.015%

    No Known Activations