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

    Neuronpedia

    INDEX
    Explanations

    expressions of contrast or negation

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases expressing a lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    former
    -0.78
    quet
    -0.75
    arling
    -0.72
    riber
    -0.69
    onic
    -0.66
    umbn
    -0.66
    ourses
    -0.66
    papers
    -0.64
    interstitial
    -0.64
    onding
    -0.64
    POSITIVE LOGITS
     uncommon
    1.35
     surprising
    1.16
     unreasonable
    1.16
     clear
    1.09
    icable
    1.06
     unusual
    1.04
     unheard
    1.04
     incon
    1.04
     coincidence
    1.00
     advisable
    0.96
    Act Density 0.083%

    No Known Activations