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

    Neuronpedia

    INDEX
    Explanations

    text related to descriptions or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thenReturn
    -0.74
    Amicalement
    -0.74
    Theorem
    -0.70
     Theorem
    -0.67
     οποία
    -0.65
     Guel
    -0.65
    andaş
    -0.64
     pilar
    -0.64
     gặp
    -0.63
     aient
    -0.63
    POSITIVE LOGITS
     description
    1.52
     descriptions
    1.52
     descrip
    1.42
     Description
    1.29
    getDescription
    1.28
     descri
    1.27
    Description
    1.27
     DESCRIPTION
    1.25
     descriptors
    1.24
    descriptions
    1.22
    Act Density 0.144%

    No Known Activations