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

    Neuronpedia

    INDEX
    Explanations

    news articles or headlines related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to crime and political controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.70
     skelet
    -0.70
    )."
    -0.67
    Secondly
    -0.65
     conflic
    -0.65
     UNCLASSIFIED
    -0.63
    }.
    -0.63
    Versions
    -0.62
     Vaugh
    -0.62
    76561
    -0.60
    POSITIVE LOGITS
     Belfast
    0.77
     Donald
    0.67
     Transgender
    0.64
     âĢº
    0.64
     Thursday
    0.64
     Wednesday
    0.64
     Hillary
    0.63
     Updated
    0.62
    ctuary
    0.60
     Tuesday
    0.59
    Act Density 1.780%

    No Known Activations