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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to substantial concepts or topics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rette
    -0.16
    asin
    -0.16
    uge
    -0.16
     Stateless
    -0.15
     chod
    -0.15
    empo
    -0.15
    veloper
    -0.15
    RIGHT
    -0.14
     Dry
    -0.14
    lass
    -0.14
    POSITIVE LOGITS
     sal
    0.16
    leon
    0.15
    anco
    0.15
    fixture
    0.14
     Circ
    0.14
    143
    0.14
    703
    0.13
     Neb
    0.13
     floats
    0.13
     dile
    0.13
    Act Density 0.003%

    No Known Activations