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

    Neuronpedia

    INDEX
    Explanations

    code snippets containing variable definitions and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĨد
    -0.17
    ãĥ³ãĥĢ
    -0.15
    issy
    -0.15
    769
    -0.15
    ãģĭãĤı
    -0.14
    rotch
    -0.14
    //{{
    -0.14
    isay
    -0.14
    ISS
    -0.14
    culus
    -0.14
    POSITIVE LOGITS
    ahi
    0.15
    ammers
    0.15
    otti
    0.15
    ered
    0.15
    ubi
    0.14
     Drill
    0.14
    oton
    0.14
     Shaw
    0.14
    endor
    0.14
    anka
    0.13
    Act Density 0.014%

    No Known Activations