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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases involving consideration or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "when," often indicating conditional scenarios or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lish
    -0.75
    tip
    -0.70
    selves
    -0.70
    guard
    -0.68
    minster
    -0.68
    idity
    -0.66
    assad
    -0.65
    lez
    -0.65
    realDonaldTrump
    -0.64
    igmatic
    -0.64
    POSITIVE LOGITS
     compared
    1.30
     coupled
    1.17
     contrasted
    1.16
     considering
    1.08
     comparing
    1.07
     viewed
    1.01
     you
    1.01
     combined
    0.99
     paired
    0.99
     juxtap
    0.96
    Act Density 0.122%

    No Known Activations