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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of "core" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ListView
    -0.51
     pinulongan
    -0.50
    Attribution
    -0.49
    Zambia
    -0.48
    ToSend
    -0.48
    ambiguation
    -0.48
    Tram
    -0.47
    achting
    -0.47
    noinspection
    -0.47
     yPos
    -0.46
    POSITIVE LOGITS
     core
    1.89
    Core
    1.80
     Core
    1.78
    core
    1.76
     CORE
    1.63
    CORE
    1.55
    核心
    1.36
    コア
    1.30
     cores
    1.30
     Cores
    1.19
    Act Density 0.079%

    No Known Activations