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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or special characters used in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indígen
    -0.93
    <unused79>
    -0.82
     desmotivaciones
    -0.82
     laſſen
    -0.82
    <unused16>
    -0.82
    <unused8>
    -0.82
     queſta
    -0.82
     auroit
    -0.82
     ainfi
    -0.82
    [@BOS@]
    -0.81
    POSITIVE LOGITS
    ↵
    0.84
    ↵↵
    0.82
    ,
    0.79
    .
    0.71
     
    0.71
     (
    0.71
    '
    0.67
    ↵↵↵
    0.63
      
    0.62
     and
    0.62
    Act Density 0.362%

    No Known Activations