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

    Neuronpedia

    INDEX
    Explanations

    references to server-related concepts and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    servers
    -0.18
    ayers
    -0.17
    ayer
    -0.17
    sar
    -0.16
    soever
    -0.16
    uggage
    -0.15
    οι
    -0.15
    olvers
    -0.15
    ConverterFactory
    -0.15
    keit
    -0.14
    POSITIVE LOGITS
    -side
    0.43
    Side
    0.32
    _side
    0.30
     side
    0.30
    fault
    0.29
     Side
    0.29
    -sided
    0.28
     sided
    0.26
    less
    0.26
    /client
    0.25
    Act Density 0.036%

    No Known Activations