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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific terms related to various subjects and topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citiz
    -0.90
     lawy
    -0.78
     skelet
    -0.74
    د
    -0.74
     contrace
    -0.72
     proble
    -0.71
     cryst
    -0.71
     charism
    -0.70
     metic
    -0.70
     therap
    -0.69
    POSITIVE LOGITS
     APR
    0.72
    adium
    0.70
    vier
    0.70
    UF
    0.69
    nos
    0.69
    ufact
    0.69
    weed
    0.69
    aro
    0.68
    xt
    0.66
    uary
    0.65
    Act Density 1.174%

    No Known Activations