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

    Neuronpedia

    INDEX
    Explanations

    terms related to software, specifically focusing on words ending in 'ware'

    oai_token-act-pair · gpt-3.5-turbo

    words related to software and technology products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autonom
    -0.76
    uations
    -0.72
    uating
    -0.70
    uates
    -0.67
    ione
    -0.65
    ulatory
    -0.65
    inated
    -0.65
    itability
    -0.65
    ENC
    -0.63
    iann
    -0.63
    POSITIVE LOGITS
    ware
    1.28
    housing
    1.15
    manship
    1.10
    bytes
    1.04
    houses
    1.04
    ness
    0.99
    house
    0.94
    fare
    0.91
    works
    0.91
    nown
    0.91
    Act Density 0.025%

    No Known Activations