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

    Neuronpedia

    INDEX
    Explanations

    numbers in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "j"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bleach
    -0.66
     Lauder
    -0.66
     bombard
    -0.66
     dispers
    -0.63
     Sheen
    -0.60
     MacArthur
    -0.60
     Ferr
    -0.59
     productive
    -0.59
     Huntington
    -0.59
     dictators
    -0.58
    POSITIVE LOGITS
    ournals
    1.45
    unction
    1.24
    ealous
    1.20
    acket
    1.18
    unal
    1.16
    utsu
    1.13
    ordan
    1.13
    itsu
    1.12
    ean
    1.11
    oint
    1.05
    Act Density 0.032%

    No Known Activations