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

    Neuronpedia

    INDEX
    Explanations

    contractions of the word "it" or possessive forms related to the first person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.67
     Мексичка
    -1.09
    Portale
    -1.06
    rungsseite
    -0.99
     ―――――
    -0.92
     Савезне
    -0.91
     Baillargeon
    -0.90
    -0.88
    +#+
    -0.87
    osoba
    -0.87
    POSITIVE LOGITS
     You
    0.73
     you
    0.65
    You
    0.65
     it
    0.63
    y
    0.61
     They
    0.60
     a
    0.60
     and
    0.58
    g
    0.58
    ak
    0.57
    Act Density 0.171%

    No Known Activations