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

    Neuronpedia

    INDEX
    Explanations

    mentions of dolphins and related terms in various contexts

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

    Dolphins, Marlins, Canadiens, Marseille

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ắ
    -0.47
     Rag
    -0.45
    <h2>
    -0.44
    大
    -0.43
     pieces
    -0.42
     &
    -0.41
     Sty
    -0.39
    RAG
    -0.38
     Raw
    -0.37
     waste
    -0.37
    POSITIVE LOGITS
     Dolphins
    2.39
     Dolphin
    2.09
     dolphins
    1.98
    Dolphin
    1.97
    olphins
    1.96
     dolphin
    1.87
    dolphin
    1.61
    🐬
    1.20
     Marlins
    0.93
     DOL
    0.75
    Act Density 0.009%

    No Known Activations