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

    Neuronpedia

    INDEX
    Explanations

    instances of strong emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –
    -0.41
     –↵
    -0.27
     –↵↵
    -0.25
     --
    -0.25
    --
    -0.24
     âĢIJ
    -0.21
    âĶĢâĶĢ
    -0.21
    )--
    -0.19
     ï½ŀ
    -0.19
    ">--}}↵
    -0.18
    POSITIVE LOGITS
    ————————————————
    0.47
    ————————
    0.44
    ————
    0.37
    ——
    0.27
    âĨĴâĨĴ
    0.19
    ÂĿ
    0.18
     —↵↵
    0.18
     —
    0.17
    âĸł
    0.16
    ample
    0.16
    Act Density 0.071%

    No Known Activations