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

    Neuronpedia

    INDEX
    Explanations

    repeated sequences of characters or structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -0.98
     ſche
    -0.90
    majánló
    -0.88
     indígen
    -0.85
     ſta
    -0.83
     faſt
    -0.83
     queſta
    -0.82
    pecabe
    -0.81
    iſen
    -0.79
    ambién
    -0.79
    POSITIVE LOGITS
    hline
    0.66
     
    0.57
    <blockquote>
    0.56
    ↵↵
    0.55
    ,
    0.54
     “
    0.54
    (
    0.52
    :
    0.52
     (
    0.51
    <tr>
    0.50
    Act Density 0.145%

    No Known Activations