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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utter
    -0.78
     royalty
    -0.74
     luxurious
    -0.73
     badass
    -0.71
     darling
    -0.71
     readable
    -0.70
     sens
    -0.70
     sleeper
    -0.70
     slightest
    -0.69
     traitor
    -0.69
    POSITIVE LOGITS
     Ideally
    1.07
     Typically
    1.04
     Eventually
    1.01
     Instead
    1.00
     Ultimately
    1.00
     Because
    0.99
     Currently
    0.99
     Especially
    0.98
     Conversely
    0.98
     Luckily
    0.97
    Act Density 0.203%

    No Known Activations