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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions that connect clauses and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PEOPLE
    -0.17
    people
    -0.16
    esh
    -0.15
    人ãģĮ
    -0.15
     people
    -0.15
    ayment
    -0.14
    人人
    -0.14
    ags
    -0.14
    Odd
    -0.14
    odd
    -0.14
    POSITIVE LOGITS
     many
    0.27
     some
    0.26
    many
    0.24
    some
    0.21
     certains
    0.21
     certain
    0.21
     algunos
    0.20
     most
    0.20
     algunas
    0.20
     Some
    0.20
    Act Density 0.002%

    No Known Activations