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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences of similar values in a numerical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -1.40
     queſta
    -1.38
    ſchaft
    -1.31
    <unused52>
    -1.29
    <unused23>
    -1.28
    <unused16>
    -1.28
    <unused41>
    -1.28
    <unused43>
    -1.28
    <unused8>
    -1.28
    <unused14>
    -1.28
    POSITIVE LOGITS
    ↵
    0.53
    …
    0.41
    ’
    0.37
    .
    0.34
    1
    0.32
    ...
    0.30
     “
    0.29
      
    0.28
    -
    0.28
    ↵↵
    0.28
    Act Density 1.235%

    No Known Activations