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

    Neuronpedia

    INDEX
    Explanations

    actions and consequences related to change and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.16
    agger
    -0.15
    iÄįky
    -0.15
    acket
    -0.14
    ajs
    -0.14
     totiž
    -0.14
    ofire
    -0.14
    entanyl
    -0.14
    udeau
    -0.14
    .chunk
    -0.14
    POSITIVE LOGITS
    ãĤ¸ãĤª
    0.18
    ly
    0.15
    .slim
    0.15
    utting
    0.14
    0.14
    pect
    0.14
    en
    0.13
    lias
    0.13
    dden
    0.13
    uts
    0.13
    Act Density 0.112%

    No Known Activations