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

    Neuronpedia

    INDEX
    Explanations

    modals and conditional language indicating potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    I
    -0.50
    We
    -0.49
    чак
    -0.47
    nella
    -0.46
    fw
    -0.45
    ow
    -0.44
     unaware
    -0.44
     крайней
    -0.44
     elettron
    -0.44
     we
    -0.43
    POSITIVE LOGITS
     itſelf
    1.14
    AddTagHelper
    0.95
    ArrowToggle
    0.94
    verwijspagina
    0.92
    Билгалдахарш
    0.88
    MigrationBuilder
    0.88
     autorytatywna
    0.88
    IVEREF
    0.87
     Numerade
    0.85
     AssemblyProduct
    0.84
    Act Density 0.565%

    No Known Activations