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

    Neuronpedia

    INDEX
    Explanations

    names mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SIGN
    -0.68
    LEASE
    -0.67
    REDACTED
    -0.66
    ONSORED
    -0.66
    Reviewer
    -0.64
     precon
    -0.63
    ships
    -0.63
    ship
    -0.62
    CLASSIFIED
    -0.61
     repetition
    -0.61
    POSITIVE LOGITS
    ources
    1.30
    ourced
    1.16
    nyder
    1.13
    kaya
    1.11
    aurus
    1.10
    essions
    1.09
    wered
    1.09
    atisf
    1.07
    ourcing
    1.06
    inki
    1.05
    Act Density 0.084%

    No Known Activations