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

    Neuronpedia

    INDEX
    Explanations

    singular nouns

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redients
    -0.65
    asionally
    -0.64
     Exper
    -0.63
    Links
    -0.63
     assorted
    -0.63
    aly
    -0.62
    parts
    -0.61
    unknown
    -0.61
     beware
    -0.59
    DEF
    -0.58
    POSITIVE LOGITS
     dime
    1.22
     single
    1.12
    ught
    1.08
     slightest
    1.07
     satisfactory
    1.06
     penny
    1.01
    rouse
    1.01
     clue
    0.98
     lot
    0.96
     coherent
    0.95
    Act Density 0.185%

    No Known Activations