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

    Neuronpedia

    INDEX
    Explanations

    references to written communication such as letters or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to formal written communications, especially letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illon
    -0.61
     deform
    -0.61
    ptions
    -0.60
    Variable
    -0.60
    onut
    -0.59
    Ħ¢
    -0.59
     å¤
    -0.59
    illian
    -0.59
    ivably
    -0.58
     Bronze
    -0.57
    POSITIVE LOGITS
     addressed
    1.05
     letter
    1.03
     dated
    1.00
     outlining
    0.99
    Letter
    0.95
     urging
    0.94
     inbox
    0.92
    letter
    0.91
     requesting
    0.91
     sent
    0.87
    Act Density 0.107%

    No Known Activations