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

    Neuronpedia

    INDEX
    Explanations

    words related to significant impact or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating substantial changes or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.87
    ifully
    -0.87
    sburgh
    -0.80
    aily
    -0.78
    icip
    -0.77
    nar
    -0.74
    lest
    -0.72
    icion
    -0.72
    icular
    -0.71
    elsen
    -0.71
    POSITIVE LOGITS
     impacting
    0.97
     impacted
    0.96
     effected
    0.96
     differ
    0.86
     outper
    0.82
     reduce
    0.81
     reduces
    0.81
     deterior
    0.79
     degrade
    0.79
     influenced
    0.78
    Act Density 0.053%

    No Known Activations