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

    Neuronpedia

    INDEX
    Explanations

    structured statements that involve conditional or causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.84
    Portale
    -0.70
    はじめに
    -0.70
     GenerationType
    -0.66
    MemoryWarning
    -0.62
     Paglinawan
    -0.61
    RegressionTest
    -0.61
     {},
    -0.61
    ########.
    -0.58
     الدولى
    -0.58
    POSITIVE LOGITS
     amelyek
    0.52
    satunya
    0.51
    ագրություններ
    0.50
    fer
    0.47
     mà
    0.46
    Viited
    0.45
     DialogInterface
    0.45
    Vezi
    0.45
     esboço
    0.44
    WIRE
    0.43
    Act Density 0.811%

    No Known Activations