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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okt
    -0.16
     Zuk
    -0.15
    rophy
    -0.14
    ForRow
    -0.14
    hsi
    -0.14
    UNET
    -0.14
    alet
    -0.14
    enus
    -0.13
    eno
    -0.13
    appen
    -0.13
    POSITIVE LOGITS
     access
    0.31
     opportunity
    0.26
     opportunities
    0.25
     latitude
    0.22
     flexibility
    0.20
    æľºä¼ļ
    0.20
     freedom
    0.20
     Opportunities
    0.20
    access
    0.20
     chance
    0.20
    Act Density 0.043%

    No Known Activations