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

    Neuronpedia

    INDEX
    Explanations

    syntax related to programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ”…
    -0.79
    “…
    -0.75
    ,...
    -0.73
    "...
    -0.73
    ...»
    -0.72
    ,…
    -0.72
    **,
    -0.72
    ,**
    -0.72
    »,
    -0.71
    …,
    -0.69
    POSITIVE LOGITS
     .
    3.53
     .
    1.48
     `.
    1.47
     .\
    1.40
     [.
    1.38
     .)
    1.32
     ._
    1.30
     (.
    1.29
    (.
    1.29
    /.
    1.27
    Act Density 0.697%

    No Known Activations