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

    Neuronpedia

    INDEX
    Explanations

    proper names or titles mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.79
    ometers
    -0.71
    ersive
    -0.65
     oun
    -0.64
    erker
    -0.63
     gif
    -0.62
    aukee
    -0.62
    eren
    -0.62
     contrace
    -0.61
    umat
    -0.61
    POSITIVE LOGITS
     "#
    0.95
     ''
    0.86
     "@
    0.82
    onyms
    0.74
     "(
    0.72
     ``
    0.71
    name
    0.70
    é£
    0.70
     Osama
    0.70
     "_
    0.69
    Act Density 0.104%

    No Known Activations