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

    Neuronpedia

    INDEX
    Explanations

    discussions of accusations and their impacts on reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pled
    -0.16
    atis
    -0.16
     benchmark
    -0.15
     Benchmark
    -0.15
    목
    -0.14
    Redux
    -0.14
    bia
    -0.14
    Benchmark
    -0.14
    enu
    -0.14
    inho
    -0.14
    POSITIVE LOGITS
     migrationBuilder
    0.15
     Swamp
    0.15
    matrix
    0.14
    .IContainer
    0.14
    à¥Ģà¤ķरण
    0.14
    _inverse
    0.14
     Wei
    0.13
    warnings
    0.13
    gnore
    0.13
    readonly
    0.13
    Act Density 0.167%

    No Known Activations