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

    Neuronpedia

    INDEX
    Explanations

    copyright notices and licensing information in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.42
     
    -0.39
    .
    -0.37
    2
    -0.33
    ↵↵
    -0.33
    1
    -0.33
      
    -0.32
    ”
    -0.32
    3
    -0.30
    <eos>
    -0.30
    POSITIVE LOGITS
     ſind
    1.30
    GEBURTSDATUM
    1.27
    ロウィン
    1.24
    ðsíða
    1.24
    ſicht
    1.23
    <unused3>
    1.22
    <unused52>
    1.22
    <unused14>
    1.21
    <unused8>
    1.21
    [@BOS@]
    1.21
    Act Density 0.369%

    No Known Activations