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

    Neuronpedia

    INDEX
    Explanations

    references to numerical or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.19
    adian
    -0.18
    ingle
    -0.16
    Ø´ÙħاÙĦÛĮ
    -0.16
    ied
    -0.15
    trip
    -0.15
    aters
    -0.15
    TES
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
    ings
    -0.14
    POSITIVE LOGITS
    wner
    0.17
    ëĭ¤
    0.16
    rganization
    0.16
    ãģĹãĤĩãģĨ
    0.15
    ìłģìľ¼ë¡ľ
    0.15
    kla
    0.14
    rientation
    0.14
    earn
    0.14
    uyá»ĥn
    0.14
    atic
    0.13
    Act Density 0.235%

    No Known Activations