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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "sure" followed by common discourse markers or continuation words.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    metaData
    -0.30
     Méndez
    -0.30
     terk
    -0.29
    innerWidth
    -0.29
     Tar
    -0.29
     movement
    -0.29
    ted
    -0.29
     conduite
    -0.28
     Bork
    -0.28
    O
    -0.28
    POSITIVE LOGITS
     sure
    0.88
    Sure
    0.84
    sure
    0.84
     Sure
    0.82
     فريبيس
    0.82
     SURE
    0.81
    出版年
    0.81
    BufferException
    0.77
    Хьажоргаш
    0.73
    WriteTagHelper
    0.71
    Act Density 0.142%

    No Known Activations