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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "named" and related expressions denoting identification or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ساب
    -0.17
    HQ
    -0.15
    IOR
    -0.14
    agers
    -0.14
     queryString
    -0.14
    ÙģÙĨ
    -0.14
     обÑıз
    -0.14
    habit
    -0.13
    links
    -0.13
    вал
    -0.13
    POSITIVE LOGITS
    ropping
    0.22
    ropped
    0.15
    rops
    0.15
    rop
    0.15
    elik
    0.14
     kus
    0.14
    ake
    0.14
    AKE
    0.14
    abella
    0.14
    429
    0.14
    Act Density 0.018%

    No Known Activations