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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the action of searching or looking for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĤ¯
    -0.18
    Å©ng
    -0.16
     Antar
    -0.16
    ãĥĥãĤ·ãĥ¥
    -0.15
    atti
    -0.14
    ãģ¼
    -0.14
    .myapplication
    -0.14
    WER
    -0.14
    iah
    -0.14
    ADDR
    -0.14
    POSITIVE LOGITS
    buat
    0.16
    anian
    0.15
     Begin
    0.15
    ĴĪ
    0.15
    ardo
    0.14
    orado
    0.14
    expand
    0.14
    ubes
    0.14
     Buchanan
    0.14
     Jew
    0.13
    Act Density 0.001%

    No Known Activations