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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social hierarchy and status within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uiltin
    -0.16
     Lots
    -0.15
    hai
    -0.14
    untas
    -0.14
    ownt
    -0.14
    nav
    -0.14
    :
    -0.14
    getDisplay
    -0.14
    X
    -0.14
     kob
    -0.14
    POSITIVE LOGITS
     kind
    0.23
     sort
    0.20
    éĤ£ç§į
    0.19
    kind
    0.16
     kinds
    0.16
    ãĥ¼ãĥĨ
    0.16
     заклад
    0.15
     KIND
    0.15
    Msp
    0.15
     sorts
    0.15
    Act Density 0.181%

    No Known Activations