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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    themes related to violence and serious crime incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.70
    Interested
    -0.66
    iple
    -0.65
    MpServer
    -0.61
     largeDownload
    -0.61
    taboola
    -0.60
     partName
    -0.60
    autions
    -0.60
    offer
    -0.59
    ciplinary
    -0.58
    POSITIVE LOGITS
     unpopular
    0.67
     enemy
    0.63
     oneself
    0.63
     nonexistent
    0.63
     supposedly
    0.62
     lowly
    0.62
     crappy
    0.61
     dictators
    0.60
     something
    0.60
     unprotected
    0.60
    Act Density 0.857%

    No Known Activations