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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly politicians or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.76
    âĢ¢âĢ¢
    -0.71
    Gaza
    -0.64
    ãĤ±
    -0.63
    ãĤ¦
    -0.61
    CDC
    -0.61
    é¾
    -0.60
     franc
    -0.59
     kcal
    -0.57
     IPM
    -0.56
    POSITIVE LOGITS
    ttle
    0.94
    mort
    0.88
    issan
    0.86
    acket
    0.77
    ikh
    0.73
    ung
    0.70
    inge
    0.68
    amic
    0.67
    azine
    0.67
    ophile
    0.67
    Act Density 0.073%

    No Known Activations