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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ±ãĥĥãĥĪ
    -0.16
    alis
    -0.16
    para
    -0.16
    etag
    -0.15
    á»Ń
    -0.15
    cken
    -0.15
    ito
    -0.15
    à¥ĩà¤ļ
    -0.14
    .scalablytyped
    -0.14
    .Slf
    -0.14
    POSITIVE LOGITS
    ÑģÑĮ
    0.18
    soever
    0.16
    akes
    0.16
    upon
    0.15
    modo
    0.14
    ाà¤ĸण
    0.14
    raž
    0.14
    ãĥ³ãĥIJ
    0.14
    rub
    0.14
    .obtain
    0.14
    Act Density 0.045%

    No Known Activations