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

    Neuronpedia

    INDEX
    Explanations

    elements related to emphasized text formatting in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.96
     queſta
    -0.94
    MigrationBuilder
    -0.93
     müſſen
    -0.88
    majánló
    -0.87
     geweſen
    -0.85
    <unused74>
    -0.84
    <unused43>
    -0.84
    <unused14>
    -0.84
    [@BOS@]
    -0.84
    POSITIVE LOGITS
    <strong>
    1.22
    <b>
    0.94
    <h1>
    0.71
      
    0.48
       
    0.46
    ↵
    0.44
    id
    0.42
        
    0.40
    mathbf
    0.39
    switch
    0.38
    Act Density 0.817%

    No Known Activations