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

    Neuronpedia

    INDEX
    Explanations

    references to meeting recordings and their retrieval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ``
    -1.56
     ​
    -1.31
     $^{
    -1.28
    ‑
    -1.27
    -1.27
     
    -1.26
    ``
    -1.25
     $^{\
    -1.22
     ‐
    -1.19
     &#
    -1.18
    POSITIVE LOGITS
    …
    2.71
    "…
    2.21
    )…
    2.15
    …"
    2.14
    ?…
    1.92
    ,…
    1.91
    ”…
    1.88
    …)
    1.82
    …(
    1.80
    …」
    1.78
    Act Density 0.206%

    No Known Activations