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

    Neuronpedia

    INDEX
    Explanations

    names of people, likely related to news or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ================================================================
    -0.66
     insightful
    -0.66
     illuminating
    -0.63
     cz
    -0.63
     innov
    -0.63
    Introdu
    -0.62
    ularity
    -0.62
     infographic
    -0.61
     philosophers
    -0.61
     broaden
    -0.60
    POSITIVE LOGITS
     pleaded
    1.17
     surrendered
    1.10
     died
    1.06
     Jr
    1.00
     suffered
    0.96
     disappeared
    0.95
     stabbed
    0.93
     vanished
    0.93
     texted
    0.93
     underwent
    0.91
    Act Density 0.279%

    No Known Activations