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

    Neuronpedia

    INDEX
    Explanations

    terminology related to dictionaries and their compilation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thâu
    -0.60
     CURIAM
    -0.58
    DockStyle
    -0.57
    ?')
    -0.55
    RegistryLite
    -0.54
     _)
    -0.53
    migrationBuilder
    -0.51
    的吗
    -0.50
     betreff
    -0.49
     umgeben
    -0.49
    POSITIVE LOGITS
    ，
    0.88
    。
    0.63
    而
    0.47
     mà
    0.39
    ،
    0.39
    来
    0.38
    makeConstraints
    0.38
    來
    0.38
     lại
    0.36
    を
    0.36
    Act Density 0.019%

    No Known Activations