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

    Neuronpedia

    INDEX
    Explanations

    references to versions of items or works, particularly in the context of articles or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikt
    -0.17
    ãĥ¼ãĥĬ
    -0.16
    roy
    -0.15
    ayers
    -0.15
    ernen
    -0.15
    viar
    -0.15
    ilk
    -0.14
    ensch
    -0.14
    keit
    -0.14
    vers
    -0.14
    POSITIVE LOGITS
    ed
    0.36
    ing
    0.33
    ality
    0.29
    ned
    0.27
    ning
    0.24
    naires
    0.22
    nement
    0.22
    naire
    0.22
    nable
    0.22
    ally
    0.21
    Act Density 0.046%

    No Known Activations