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

    Neuronpedia

    INDEX
    Explanations

    sentences that are the end of dialogues or conversations

    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
    eatures
    -0.83
    eteenth
    -0.77
    iber
    -0.76
     uncommon
    -0.73
    itionally
    -0.73
     encount
    -0.72
    olars
    -0.71
    itional
    -0.71
     predominantly
    -0.71
    quartered
    -0.69
    POSITIVE LOGITS
     Anyway
    1.18
     Sorry
    1.15
     Please
    1.13
     You
    1.11
     That
    1.10
     Where
    1.10
     Somebody
    1.08
     Alright
    1.07
     Goodbye
    1.07
     Whoever
    1.05
    Act Density 0.237%

    No Known Activations