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

    Neuronpedia

    INDEX
    Explanations

    entities and locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to significant societal issues or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ttes
    -0.88
    ythm
    -0.72
    gdala
    -0.70
     SIG
    -0.70
    pter
    -0.68
    /.
    -0.67
    oho
    -0.67
     Dyn
    -0.67
    illac
    -0.66
    ounge
    -0.66
    POSITIVE LOGITS
    Britain
    0.85
    Labour
    0.83
    England
    0.83
     analys
    0.79
    BBC
    0.79
     apologise
    0.77
     recogn
    0.75
     fue
    0.75
    Scotland
    0.75
     campaigners
    0.73
    Act Density 0.186%

    No Known Activations