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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eree
    -0.17
    ³
    -0.16
    ê´Ģ
    -0.14
     spraw
    -0.14
    495
    -0.14
    icari
    -0.14
    urgeon
    -0.14
    ãĥ£
    -0.13
     Byrne
    -0.13
    iesel
    -0.13
    POSITIVE LOGITS
    à¥įश
    0.14
     lượng
    0.14
    427
    0.14
    mile
    0.14
    åı·
    0.14
    wcs
    0.13
    siyon
    0.13
    /wait
    0.13
    orthand
    0.13
     crew
    0.13
    Act Density 0.372%

    No Known Activations