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

    Neuronpedia

    INDEX
    Explanations

    words related to administrative or technical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ман
    -0.17
    nez
    -0.16
     territories
    -0.15
     Territories
    -0.15
    icari
    -0.15
    wizard
    -0.15
     TAR
    -0.15
    .MODE
    -0.15
    isay
    -0.15
    dana
    -0.15
    POSITIVE LOGITS
    ora
    0.17
    .IContainer
    0.17
    rack
    0.15
     Ingram
    0.15
    .catalog
    0.15
    ORLD
    0.15
     ç«
    0.15
    hma
    0.15
    ToProps
    0.14
    crew
    0.14
    Act Density 0.005%

    No Known Activations