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

    Neuronpedia

    INDEX
    Explanations

    phrases related to superlatives and exceptional instances, particularly focusing on the word "ever"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viso
    -0.15
    éºĹ
    -0.15
    urette
    -0.14
    quine
    -0.14
    plet
    -0.14
    ery
    -0.14
    onus
    -0.14
    iani
    -0.14
     modulo
    -0.14
    ierte
    -0.14
    POSITIVE LOGITS
    lesen
    0.17
     kolo
    0.15
    ãģĬãĤĬ
    0.14
    /*č↵
    0.14
    .instances
    0.14
    :\/\/
    0.13
    ãĥ¬ãĤ¹
    0.13
    ุà¹ī
    0.13
    nehmer
    0.13
    ahat
    0.13
    Act Density 0.017%

    No Known Activations