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

    Neuronpedia

    INDEX
    Explanations

    file paths and references to programming languages and libraries

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Watts
    -0.65
     TBA
    -0.64
     Cheong
    -0.61
     Ambrose
    -0.60
    ;;;;;;;;;;;;
    -0.59
     dismant
    -0.59
     Beir
    -0.58
     Quin
    -0.58
     Eighth
    -0.58
     Carroll
    -0.58
    POSITIVE LOGITS
    XXX
    1.06
    example
    1.01
    dir
    0.97
    xxx
    0.97
    ().
    0.96
    foo
    0.94
    Config
    0.90
    Debug
    0.88
    Version
    0.88
    Dir
    0.87
    Act Density 0.223%

    No Known Activations