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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uddle
    -0.15
    sta
    -0.14
    idis
    -0.13
     scrim
    -0.13
    á»ī
    -0.13
    abl
    -0.13
     Arn
    -0.13
    TITLE
    -0.13
    kat
    -0.13
    iris
    -0.13
    POSITIVE LOGITS
    ëĿ½
    0.17
    atore
    0.16
    ean
    0.16
    Exited
    0.15
    ech
    0.15
    è¨ĢãģĦ
    0.15
    å´İ
    0.15
    ãĥ³ãĥĨ
    0.15
    SSF
    0.14
    ekt
    0.14
    Act Density 0.076%

    No Known Activations