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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and their representations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BibitemShut
    -0.55
     للمعارف
    -0.55
    TagMode
    -0.52
    ../../
    -0.50
    gridView
    -0.49
    tast
    -0.48
    astra
    -0.48
    Literatuur
    -0.48
    ograp
    -0.47
    ArrowToggle
    -0.47
    POSITIVE LOGITS
    st
    0.77
    1
    0.76
    ️⃣
    0.58
    esModule
    0.54
    ⃣
    0.54
    ⁄
    0.46
    zzleHttp
    0.45
    ArgsConstructor
    0.44
     Utama
    0.42
    ″
    0.41
    Act Density 2.327%

    No Known Activations