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

    Neuronpedia

    INDEX
    Explanations

    phrases that express common knowledge or shared awareness among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullo
    -0.19
    plevel
    -0.16
    IOC
    -0.15
    llib
    -0.15
    ãģıãģł
    -0.15
    pcion
    -0.15
    ãĤĩ
    -0.14
    inker
    -0.14
    rying
    -0.14
     option
    -0.14
    POSITIVE LOGITS
    ãĥĨãĥ«
    0.17
    fak
    0.14
    ุà¸Ķ
    0.14
    ave
    0.14
    ril
    0.14
    cant
    0.14
     cov
    0.14
     Cov
    0.14
     kro
    0.13
    chor
    0.13
    Act Density 0.060%

    No Known Activations