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

    Neuronpedia

    INDEX
    Explanations

    names of people, places, or entities ending with the letter 'a'

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RANT
    -0.57
    uyomi
    -0.56
     evenly
    -0.55
     exceptions
    -0.53
     convention
    -0.50
     sockets
    -0.50
     brim
    -0.50
     recre
    -0.50
     lodging
    -0.49
     expectancy
    -0.48
    POSITIVE LOGITS
    a
    3.41
    i
    1.46
    aan
    1.45
    aa
    1.44
    aq
    1.44
    ea
    1.41
    aic
    1.41
    e
    1.40
    aaa
    1.38
    an
    1.38
    Act Density 0.059%

    No Known Activations