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

    Neuronpedia

    INDEX
    Explanations

    code or programming-related syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     `${
    -0.89
    `${
    -0.82
     eslint
    -0.81
    const
    -0.80
     let
    -0.80
     const
    -0.78
     ItemStack
    -0.74
     LET
    -0.73
    constexpr
    -0.72
    let
    -0.72
    POSITIVE LOGITS
    var
    2.10
     var
    1.71
    Var
    0.98
    VAR
    0.96
     Var
    0.88
     VAR
    0.87
    vara
    0.75
     vari
    0.70
    vars
    0.68
    вар
    0.67
    Act Density 0.123%

    No Known Activations