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

    Neuronpedia

    INDEX
    Explanations

    references to notable individuals and their contributions or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awn
    -0.17
     Ludwig
    -0.16
    067
    -0.15
     pne
    -0.14
     Meta
    -0.14
    itals
    -0.14
    θο
    -0.14
    äºĭæ¥Ń
    -0.14
    aba
    -0.14
    æĮ¯
    -0.14
    POSITIVE LOGITS
    Obama
    0.18
     Orwell
    0.18
    ijkstra
    0.17
     Einstein
    0.17
     Mandela
    0.17
     Churchill
    0.17
     Dylan
    0.16
     Turing
    0.16
     Lincoln
    0.16
     Hitler
    0.15
    Act Density 0.391%

    No Known Activations