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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing varying degrees of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pager
    -0.17
    789
    -0.16
    bound
    -0.15
    ako
    -0.14
    ied
    -0.14
    iko
    -0.14
    ika
    -0.14
     ÙĪرز
    -0.14
    /Area
    -0.14
    ÏģιÏĥ
    -0.14
    POSITIVE LOGITS
    خت
    0.18
    awner
    0.16
    avian
    0.16
    ecycle
    0.15
    æ´ĭ
    0.15
    aldo
    0.15
    arehouse
    0.14
    ãĥªãĥ¼ãĤº
    0.14
    aign
    0.13
     alternative
    0.13
    Act Density 0.013%

    No Known Activations