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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific letters or articles in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encre
    -0.93
     ―――――
    -0.91
    gameserver
    -0.89
     ་་
    -0.88
    AddTagHelper
    -0.87
    principalTable
    -0.85
     disambiguazione
    -0.84
     geslacht
    -0.83
    Personendaten
    -0.83
    Tikang
    -0.82
    POSITIVE LOGITS
     A
    1.58
    A
    1.21
    getA
    1.05
     a
    1.02
     S
    0.93
     C
    0.93
     U
    0.93
     D
    0.92
     F
    0.91
     B
    0.91
    Act Density 0.166%

    No Known Activations