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

    Neuronpedia

    INDEX
    Explanations

    references to specific frameworks or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uat
    -0.16
    ÅĪ
    -0.15
    ãĤįãģĨ
    -0.15
    istance
    -0.14
    opper
    -0.14
    mez
    -0.14
     Praze
    -0.13
    лек
    -0.13
    .export
    -0.13
    pole
    -0.13
    POSITIVE LOGITS
     âĨIJ
    0.17
    âĨIJ
    0.17
    ï¸
    0.17
    âĨĴâĨĴ
    0.17
    su
    0.15
     thoughts
    0.15
    etten
    0.14
    ãĥ³ãĥĩ
    0.14
    vem
    0.14
    ↵
    0.14
    Act Density 0.005%

    No Known Activations