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

    Neuronpedia

    INDEX
    Explanations

    Flea market-related and cybersecurity terms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "a" and its different forms or related suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aurus
    -0.70
    achev
    -0.67
    imil
    -0.65
    ascript
    -0.63
    ADVERTISEMENT
    -0.61
     unrestricted
    -0.60
    dated
    -0.58
     ABV
    -0.58
     MV
    -0.57
     uncont
    -0.57
    POSITIVE LOGITS
    fleet
    0.71
    bay
    0.69
    ope
    0.66
    TABLE
    0.64
    stock
    0.63
    gate
    0.63
    puff
    0.63
    âĸ¬
    0.62
     Turtles
    0.61
    pool
    0.60
    Act Density 0.277%

    No Known Activations