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

    Neuronpedia

    INDEX
    Explanations

    references to pipelines in various contexts

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

    pipeline development and infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sad
    -0.42
    mod
    -0.40
    (
    -0.38
    ,
    -0.35
    ellido
    -0.34
     Cra
    -0.34
     curious
    -0.34
     Mad
    -0.34
     Wed
    -0.34
    self
    -0.34
    POSITIVE LOGITS
     pipeline
    1.97
     Pipeline
    1.77
     pipelines
    1.77
    pipeline
    1.54
    Pipeline
    1.54
    ipeline
    1.24
     Pipe
    0.96
    elines
    0.95
     pipe
    0.93
    管道
    0.91
    Act Density 0.004%

    No Known Activations