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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing common knowledge or shared understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.17
    lemen
    -0.15
    pq
    -0.14
    xFE
    -0.14
    wers
    -0.14
    335
    -0.14
    ars
    -0.14
     option
    -0.14
    leness
    -0.13
    ky
    -0.13
    POSITIVE LOGITS
    ihu
    0.16
    ODO
    0.15
    fak
    0.15
    ãĥĨãĥ«
    0.15
     Mobil
    0.15
    ensa
    0.14
    zÄħd
    0.14
     çĿ
    0.14
    λÏĮ
    0.14
    iser
    0.14
    Act Density 0.063%

    No Known Activations