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

    Neuronpedia

    INDEX
    Explanations

    information related to academic studies and research, especially involving specific institutions, researchers, and subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to academic research and the individuals involved in it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.64
    fuck
    -0.64
     negro
    -0.64
     fuck
    -0.60
    !",
    -0.59
     (?,
    -0.56
     unlaw
    -0.56
    ,[
    -0.54
    emort
    -0.54
     hath
    -0.54
    POSITIVE LOGITS
    .).
    0.83
    >.
    0.75
    ]."
    0.74
    ].
    0.73
    ]).
    0.73
    ).
    0.72
    é¾
    0.70
     ].
    0.68
    advertisement
    0.62
    arton
    0.62
    Act Density 0.805%

    No Known Activations