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

    Neuronpedia

    INDEX
    Explanations

    keywords related to artificial intelligence (AI)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and discussions related to artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.97
     Townsend
    -0.80
    ings
    -0.79
    ados
    -0.71
    stable
    -0.70
    eous
    -0.69
    iffe
    -0.69
    é¾įå¥ij士
    -0.67
    ional
    -0.67
    ilts
    -0.66
    POSITIVE LOGITS
    onomous
    0.78
    OC
    0.75
    GEN
    0.70
     theoret
    0.68
     flaw
    0.67
    AI
    0.67
    BI
    0.67
    GR
    0.66
    HA
    0.65
     AI
    0.64
    Act Density 0.007%

    No Known Activations