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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "What is" or related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     păr
    -0.45
     dieselben
    -0.44
     înc
    -0.42
     Ausbau
    -0.41
     Schluss
    -0.41
     désolés
    -0.41
    الحياه
    -0.41
     Hitze
    -0.41
     îl
    -0.40
     risol
    -0.40
    POSITIVE LOGITS
     definition
    0.83
     Definition
    0.80
    Definition
    0.69
     DEFINITION
    0.65
     meaning
    0.65
     definitions
    0.64
    DEFINITION
    0.64
     Definitions
    0.61
     defin
    0.59
    definition
    0.59
    Act Density 0.491%

    No Known Activations