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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terminology and formal language, often related to research or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    发表于
    -0.75
    StructEnd
    -0.68
     referrerpolicy
    -0.68
    uxxxx
    -0.67
    Explicación
    -0.59
    hirts
    -0.59
    Vidite
    -0.57
    ertale
    -0.56
    erialized
    -0.55
    estacks
    -0.55
    POSITIVE LOGITS
    TagMode
    0.65
     kasarigan
    0.65
    GeneratedValue
    0.59
     étoient
    0.56
     émotion
    0.55
     leb
    0.54
     بيها
    0.52
     vapeur
    0.52
    \{\\
    0.51
    APIView
    0.51
    Act Density 1.400%

    No Known Activations