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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with initials followed by a period

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "A" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.62
     Emmy
    -0.61
     optics
    -0.60
     Lies
    -0.59
     ease
    -0.58
    aries
    -0.57
     Etsy
    -0.55
     incons
    -0.55
     Bigfoot
    -0.54
     neutrality
    -0.54
    POSITIVE LOGITS
    BILITY
    1.37
    ircraft
    1.20
    qua
    1.19
    gency
    1.18
    chieve
    1.13
    uliffe
    1.13
    BILITIES
    1.13
    quila
    1.11
    ntil
    1.09
    perture
    1.08
    Act Density 0.053%

    No Known Activations