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
     slam
    -0.67
     pudding
    -0.61
     allowance
    -0.60
     dime
    -0.60
     gamble
    -0.59
     grade
    -0.59
     sack
    -0.58
     renegoti
    -0.58
     loser
    -0.58
     alley
    -0.58
    POSITIVE LOGITS
     Whilst
    1.21
     Firstly
    1.17
     However
    1.10
    Firstly
    1.05
     While
    0.98
     Specifically
    0.97
     Although
    0.96
     Whether
    0.96
     Initially
    0.96
     Unfortunately
    0.93
    Act Density 0.604%

    No Known Activations