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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "engage" and its variations, emphasizing active participation and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    خاÙĨÙĩ
    -0.20
     же
    -0.18
    owie
    -0.16
    ahoma
    -0.16
    cedures
    -0.16
    ãĥĥãĤ¯ãĤ¹
    -0.15
    ÎijÎļ
    -0.15
    оваÑĤелÑĮ
    -0.15
    rello
    -0.14
    uraa
    -0.14
    POSITIVE LOGITS
    Åij
    0.16
    /disable
    0.16
    uality
    0.15
    force
    0.14
    ä¿Ĺ
    0.14
    978
    0.14
    Ñģок
    0.14
     mortar
    0.13
    /pass
    0.13
    prise
    0.13
    Act Density 0.032%

    No Known Activations