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

    Neuronpedia

    INDEX
    Explanations

    words that begin with the letter 'A' and have high positional significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the article "A"

    np_acts-logits-general · gemini-2.0-flash

    article followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.27
     themſelves
    -1.17
     myſelf
    -1.14
     himſelf
    -1.12
     ſeveral
    -1.09
     purpoſe
    -1.06
     poffe
    -1.03
     faſt
    -1.02
     leaſt
    -1.01
     ſever
    -1.01
    POSITIVE LOGITS
     new
    0.74
     A
    0.71
    .
    0.67
    new
    0.57
     M
    0.56
     B
    0.56
     unique
    0.54
     
    0.54
     brief
    0.53
     simple
    0.52
    Act Density 0.242%

    No Known Activations