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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.18
    hood
    -0.15
    س
    -0.15
    coni
    -0.15
    esters
    -0.15
    berra
    -0.15
    iced
    -0.14
    zÅij
    -0.14
    .uk
    -0.14
    cury
    -0.14
    POSITIVE LOGITS
    /down
    0.25
    datable
    0.21
    sk
    0.18
    ture
    0.17
    shot
    0.16
    ãĥĮ
    0.15
     grub
    0.15
    turned
    0.15
    ended
    0.15
    ren
    0.14
    Act Density 0.061%

    No Known Activations