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

    Neuronpedia

    INDEX
    Explanations

    quantitative and statistical information related to various categories such as crime rates, income levels, tax rates, and temperature averages

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" and other similar prepositions indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REF
    -0.73
     fate
    -0.73
    unity
    -0.71
    pard
    -0.71
     ingred
    -0.70
    HAEL
    -0.67
    skin
    -0.67
    ŀ
    -0.67
    ĺħ
    -0.66
     convol
    -0.64
    POSITIVE LOGITS
     accordance
    1.26
    effic
    1.16
     relation
    1.15
    efficiency
    1.09
     spite
    1.09
     lieu
    1.09
    versions
    1.07
     comparison
    1.06
     conjunction
    1.01
    versely
    1.01
    Act Density 0.328%

    No Known Activations