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

    Neuronpedia

    INDEX
    Explanations

    phrases related to insurance and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FOUNDATION
    -0.17
    agua
    -0.16
    ãĥ¥ãĥ¼
    -0.16
    crap
    -0.15
    deaux
    -0.15
    iska
    -0.15
    .Xaml
    -0.14
    ÑĢÑĸд
    -0.14
    oui
    -0.14
    tam
    -0.14
    POSITIVE LOGITS
    BOOLE
    0.15
    spir
    0.14
    .CreateCommand
    0.14
    ORK
    0.14
    段
    0.14
    éľį
    0.14
    ylie
    0.14
    FONT
    0.14
    ork
    0.13
    adÃŃ
    0.13
    Act Density 0.032%

    No Known Activations