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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    so
    -0.18
    isin
    -0.16
    vided
    -0.15
    EGIN
    -0.14
    rema
    -0.14
    glich
    -0.14
    se
    -0.14
     Cabr
    -0.14
    scr
    -0.14
    riors
    -0.14
    POSITIVE LOGITS
    ardless
    0.18
    /stdc
    0.17
    arded
    0.16
    ÃŃl
    0.16
    eker
    0.15
     sure
    0.15
    aucoup
    0.15
    ((&
    0.14
    à¥Įà¤Ĥ
    0.13
    zos
    0.13
    Act Density 0.057%

    No Known Activations