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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data extraction and processing

    oai_token-act-pair · gpt-3.5-turbo

    phrases with the verb "is" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.74
    edin
    -0.67
    eers
    -0.67
     climates
    -0.66
    markets
    -0.65
     Governments
    -0.63
     warranties
    -0.63
    Enlarge
    -0.62
    luaj
    -0.61
    ouver
    -0.61
    POSITIVE LOGITS
     shorthand
    0.87
     synonymous
    0.87
     substituted
    0.84
     considered
    0.82
     omitted
    0.82
    omorphic
    0.77
     preferable
    0.77
     replaced
    0.76
    nt
    0.76
     pronounced
    0.75
    Act Density 0.277%

    No Known Activations