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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" indicating comparisons or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¾ãģŁ
    -0.20
    usercontent
    -0.14
     åħ¶ä»ĸ
    -0.14
    _then
    -0.13
     обо
    -0.13
    .EventSystems
    -0.13
     ëijĺ
    -0.13
    ä¹Ī
    -0.13
    'autres
    -0.13
    ia
    -0.13
    POSITIVE LOGITS
     ones
    0.37
     those
    0.36
    ones
    0.32
    those
    0.28
     ours
    0.24
     Ones
    0.24
     Those
    0.23
    Those
    0.22
    :
    0.20
     denen
    0.20
    Act Density 0.143%

    No Known Activations