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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming and coding syntax

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.77
    conservancy
    -0.66
     Architects
    -0.65
     confir
    -0.63
     �
    -0.61
     Syndrome
    -0.60
     Cooke
    -0.60
     equation
    -0.59
     «
    -0.58
     Russo
    -0.58
    POSITIVE LOGITS
    ")
    1.63
    ");
    1.61
    ").
    1.58
    "))
    1.54
    "]
    1.52
    "}
    1.46
    "/>
    1.43
    )",
    1.33
    "),
    1.33
    ";
    1.33
    Act Density 0.105%

    No Known Activations