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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "an"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rust
    -0.66
    lda
    -0.66
     dstg
    -0.63
    Stars
    -0.62
    olit
    -0.58
    queue
    -0.57
    clips
    -0.56
    ï¸ı
    -0.56
    jam
    -0.55
     Nation
    -0.55
    POSITIVE LOGITS
     an
    1.70
    An
    1.31
     An
    1.23
    an
    0.90
     AN
    0.87
     another
    0.84
    another
    0.82
     something
    0.75
    interstitial
    0.73
     unpre
    0.69
    Act Density 0.265%

    No Known Activations