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

    Neuronpedia

    INDEX
    Explanations

    references to objects or subjects, particularly any form of the word "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aidu
    -0.16
    872
    -0.15
     Zukunft
    -0.14
    _nested
    -0.14
    ologi
    -0.14
    lej
    -0.14
    NotAllowed
    -0.14
    รà¸ĵ
    -0.14
    478
    -0.13
     ac
    -0.13
    POSITIVE LOGITS
    ÄĻd
    0.19
    ãĥ©ãĥ¼
    0.17
    .EntityManager
    0.14
    OMPI
    0.14
     prive
    0.13
    æĵ
    0.13
    ottes
    0.13
    ɵ
    0.13
    keletal
    0.13
    erve
    0.13
    Act Density 0.248%

    No Known Activations