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

    Neuronpedia

    INDEX
    Explanations

    elements related to formal reports or scientific claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.30
     themſelves
    -1.21
    ſelves
    -1.20
     Monfieur
    -1.20
     itſelf
    -1.20
    ſelf
    -1.18
     purpoſe
    -1.17
     ſtand
    -1.13
     ſmall
    -1.11
     himſelf
    -1.11
    POSITIVE LOGITS
    <i>
    0.43
    ,
    0.42
    <eos>
    0.42
     (
    0.42
     E
    0.41
     medida
    0.41
    <b>
    0.41
     ...
    0.40
     “
    0.39
    ...
    0.38
    Act Density 0.997%

    No Known Activations