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

    Neuronpedia

    INDEX
    Explanations

    references to sinks and related terms in the context of plumbing or data flows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sink or sinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Parr
    -0.58
     moitié
    -0.56
     Artur
    -0.52
     PMA
    -0.51
    MediaType
    -0.50
     Karlsson
    -0.50
    °•
    -0.49
     Philli
    -0.49
     Chapman
    -0.49
     Tradition
    -0.49
    POSITIVE LOGITS
     Sink
    1.31
    Sink
    1.27
    sink
    1.21
     sink
    1.17
     Sinks
    1.03
     sinks
    0.88
     sinking
    0.70
     sunk
    0.60
    帖最后由
    0.60
     sank
    0.59
    Act Density 0.001%

    No Known Activations