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

    Neuronpedia

    INDEX
    Explanations

    the end of a document or a specific type of content formatting

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.74
     sleeper
    -0.73
     endeav
    -0.69
     sensations
    -0.68
     wardrobe
    -0.67
     challeng
    -0.66
     slightest
    -0.65
     royalty
    -0.65
     fleeting
    -0.65
     endeavour
    -0.64
    POSITIVE LOGITS
     "(
    1.14
     He
    1.12
     "[
    1.11
     Speaking
    1.01
     His
    1.01
     Previously
    1.00
     "
    0.99
     According
    0.98
     Thousands
    0.97
     "'
    0.96
    Act Density 0.311%

    No Known Activations