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

    Neuronpedia

    INDEX
    Explanations

    related to significant changes or improvements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the adverb "significantly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -1.00
    nar
    -0.82
    ifully
    -0.77
    iens
    -0.75
    uay
    -0.74
    sburgh
    -0.73
    icion
    -0.71
    elf
    -0.71
    icip
    -0.70
    ies
    -0.69
    POSITIVE LOGITS
     impacting
    0.95
     effected
    0.83
     impacted
    0.82
    00007
    0.78
     outper
    0.77
     benefited
    0.76
     differ
    0.75
     disrupt
    0.74
     deterior
    0.74
     endowed
    0.73
    Act Density 0.023%

    No Known Activations