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

    Neuronpedia

    INDEX
    Explanations

    references to experimental data and figures related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.49
    OGND
    -0.42
    ApiModelProperty
    -0.40
    rrggbb
    -0.38
    祝
    -0.36
    chartInstance
    -0.36
     utafitiHapana
    -0.35
     quien
    -0.34
     匿名
    -0.34
     Chwiliwch
    -0.34
    POSITIVE LOGITS
     namely
    0.65
    namely
    0.59
     antaranya
    0.59
     Namely
    0.56
     diantaranya
    0.56
     including
    0.55
    分別
    0.54
    分别是
    0.52
    including
    0.49
     viz
    0.47
    Act Density 1.196%

    No Known Activations