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

    Neuronpedia

    INDEX
    Explanations

    references to specific people, places, and structured data indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    --
    -0.70
     --
    -0.63
    "--
    -0.61
    '--
    -0.60
    “...
    -0.57
    )--
    -0.56
    ---
    -0.54
    ...@
    -0.53
    yal
    -0.52
    .--
    -0.52
    POSITIVE LOGITS
     …
    0.82
    AddTagHelper
    0.72
     […]
    0.72
    WriteTagHelper
    0.68
     ….
    0.65
     GenerationType
    0.63
    ?…
    0.63
    […]
    0.61
    FormTagHelper
    0.60
    ,…
    0.58
    Act Density 1.551%

    No Known Activations