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

    Neuronpedia

    INDEX
    Explanations

    references to past events or historical occurrences.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    words related to news articles and reports, specifically those involving incidents, investigations, or government activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to death or mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.66
    enegger
    -0.59
     incorpor
    -0.58
    atever
    -0.57
    retty
    -0.55
    AAAAAAAA
    -0.53
    ÃĥÃĤ
    -0.52
    aturdays
    -0.52
     nomine
    -0.52
     referen
    -0.51
    POSITIVE LOGITS
    ¶
    0.62
     Belfast
    0.58
    ratom
    0.57
    zbollah
    0.56
     Rohingya
    0.51
     NHS
    0.51
     marijuana
    0.49
     Ph
    0.48
     Haram
    0.47
     HIV
    0.47
    Act Density 1.577%

    No Known Activations