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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĤÑĮÑģÑı
    -0.18
    imin
    -0.17
    bourg
    -0.17
    cola
    -0.16
    imore
    -0.15
    [--
    -0.15
    eselect
    -0.15
    ynet
    -0.15
    á»Ńi
    -0.14
    luv
    -0.14
    POSITIVE LOGITS
     Richt
    0.15
    950
    0.15
    otch
    0.14
    ingham
    0.14
    su
    0.14
     GLfloat
    0.14
     ones
    0.14
    ÙĤب
    0.14
    idx
    0.13
     ending
    0.13
    Act Density 0.030%

    No Known Activations