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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antor
    -0.16
    uss
    -0.15
    oh
    -0.15
    hip
    -0.15
    illon
    -0.15
    umm
    -0.14
    à¥Ģà¤ķरण
    -0.14
    or
    -0.14
    avo
    -0.14
    hips
    -0.14
    POSITIVE LOGITS
    ylül
    0.15
    GMEM
    0.15
    ifar
    0.15
    á»ĥn
    0.14
    bracht
    0.14
     keer
    0.14
    è¨
    0.14
    ê¹
    0.14
    ENSION
    0.14
    oldem
    0.14
    Act Density 0.055%

    No Known Activations