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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to the reader or listener and their actions or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eni
    -0.15
    undy
    -0.15
    ÑģÑĤ
    -0.15
    .firebaseapp
    -0.15
    à¹Ģà¸īล
    -0.14
    ossip
    -0.14
    lest
    -0.14
    İ
    -0.14
    ottes
    -0.14
    eneral
    -0.14
    POSITIVE LOGITS
     can
    0.23
    åı¯ä»¥
    0.18
     puedo
    0.17
     Serif
    0.16
     Can
    0.16
    Can
    0.16
    umpt
    0.16
    can
    0.16
    że
    0.15
     liebe
    0.15
    Act Density 0.126%

    No Known Activations