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

    Neuronpedia

    INDEX
    Explanations

    phrases related to architectural features and amenities

    oai_token-act-pair · gpt-3.5-turbo

    sentences or fragments that end with a period, suggesting the completion of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     canon
    -0.71
     sooner
    -0.70
    ãĤ´
    -0.70
    itol
    -0.69
    omics
    -0.66
    poke
    -0.65
     fide
    -0.64
     spoiler
    -0.64
    «ĺ
    -0.64
    odox
    -0.64
    POSITIVE LOGITS
     Additionally
    1.41
     Lastly
    1.38
     Finally
    1.19
     Overall
    1.19
     Meanwhile
    1.18
     Along
    1.15
     Also
    1.12
     Each
    1.11
     Ultimately
    1.10
     Furthermore
    1.07
    Act Density 0.458%

    No Known Activations