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

    Neuronpedia

    INDEX
    Explanations

    words related to grammar and syntax

    oai_token-act-pair · gpt-3.5-turbo

    words with specific suffixes that suggest academic, artistic, or scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.76
    KEN
    -0.74
    IRD
    -0.72
    vier
    -0.71
     Coinbase
    -0.70
    cedented
    -0.68
    href
    -0.67
    LER
    -0.67
     Faster
    -0.65
    imil
    -0.65
    POSITIVE LOGITS
    ity
    0.96
    ized
    0.96
    ities
    0.92
    izing
    0.90
    ization
    0.90
     warfare
    0.84
     prowess
    0.82
     properties
    0.82
    ALLY
    0.82
    izes
    0.81
    Act Density 0.066%

    No Known Activations