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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to language and bilingualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agas
    -0.16
    æģµ
    -0.15
    anford
    -0.15
    ãĥĭãĥ¼
    -0.15
    ikes
    -0.15
    bourg
    -0.15
    çĶ
    -0.14
    ags
    -0.14
    ometown
    -0.14
    Disposition
    -0.14
    POSITIVE LOGITS
     spoken
    0.22
     flu
    0.21
     language
    0.21
     English
    0.20
    -switch
    0.19
     Language
    0.19
     communication
    0.19
     proficiency
    0.18
    language
    0.18
    English
    0.17
    Act Density 0.101%

    No Known Activations