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

    Neuronpedia

    INDEX
    Explanations

    accusations of wrongdoing or blame towards specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to accusations or claims against individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -0.60
    iants
    -0.58
    endor
    -0.58
     OG
    -0.54
    zan
    -0.54
    nov
    -0.53
    NOR
    -0.53
    nu
    -0.52
     Austral
    -0.50
     UL
    -0.50
    POSITIVE LOGITS
    of
    1.35
     of
    1.24
    Of
    1.13
     thereof
    1.08
     Of
    0.97
    OF
    0.96
     OF
    0.92
    eme
    0.73
    ta
    0.70
    aukee
    0.67
    Act Density 0.712%

    No Known Activations