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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to data processing and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data structures and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.74
    arak
    -0.73
    vernment
    -0.69
     Saturdays
    -0.66
     nightmares
    -0.65
    ECA
    -0.65
    utterstock
    -0.65
     Sundays
    -0.64
     Patton
    -0.63
    nos
    -0.62
    POSITIVE LOGITS
     descriptor
    0.86
     pointer
    0.85
     initialization
    0.83
     node
    0.81
    scape
    0.76
     output
    0.76
     nodes
    0.76
     \(
    0.75
     seq
    0.74
     (/
    0.74
    Act Density 0.400%

    No Known Activations