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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and love

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    que
    -0.15
    олоÑĤ
    -0.15
    оваÑĢи
    -0.15
    ivism
    -0.15
    ovÃŃ
    -0.14
    unner
    -0.14
    plementation
    -0.14
    aux
    -0.14
    uman
    -0.14
    elles
    -0.14
    POSITIVE LOGITS
    /lo
    0.17
    rug
    0.16
    Lifecycle
    0.15
    itt
    0.14
    endale
    0.14
    sie
    0.14
    formation
    0.14
     tech
    0.14
    itan
    0.14
     Saunders
    0.13
    Act Density 0.054%

    No Known Activations