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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bsp
    -0.15
    glob
    -0.15
    isty
    -0.15
    inkel
    -0.15
    ooth
    -0.14
    cks
    -0.14
    neau
    -0.14
    ạch
    -0.14
    itto
    -0.14
    omes
    -0.14
    POSITIVE LOGITS
    orth
    0.17
    /down
    0.17
    icontrol
    0.16
    eview
    0.15
    eday
    0.15
    XHR
    0.15
    aeda
    0.15
    ruž
    0.14
    ToDate
    0.14
     latter
    0.14
    Act Density 0.052%

    No Known Activations