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

    Neuronpedia

    INDEX
    Explanations

    salutations at the beginning of letters or messages

    oai_token-act-pair · gpt-3.5-turbo

    the salutation "Dear" typically used in letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.83
    ider
    -0.74
    elson
    -0.73
    uits
    -0.72
    itol
    -0.70
    antry
    -0.69
    frac
    -0.67
    igsaw
    -0.67
    elled
    -0.66
    artifacts
    -0.64
    POSITIVE LOGITS
     Reader
    1.26
     Readers
    1.12
     reader
    1.07
     Friends
    0.97
     Diary
    0.96
     readers
    0.95
     Customers
    0.92
     friends
    0.89
     dear
    0.87
     Customer
    0.86
    Act Density 0.028%

    No Known Activations