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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the design and function of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮв
    -0.14
    atron
    -0.14
    мен
    -0.14
    ÑĢабаÑĤ
    -0.13
    orage
    -0.13
    agon
    -0.13
    ernal
    -0.13
    ãĥ¼ãĥ
    -0.13
    attice
    -0.13
    /ws
    -0.13
    POSITIVE LOGITS
     Gone
    0.15
    Gov
    0.15
    etÃŃ
    0.14
    pii
    0.14
     deliberate
    0.14
    Ĥ
    0.14
    REFIX
    0.14
    íĭĢ
    0.13
     lÃŃ
    0.13
    aju
    0.13
    Act Density 0.094%

    No Known Activations