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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terminology related to optimization and bounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.90
     jspb
    -0.77
    脚注の使い方
    -0.73
    GOTREF
    -0.71
    UnusedPrivate
    -0.63
    TintMode
    -0.59
     createSprite
    -0.58
     queſta
    -0.58
    MigrationBuilder
    -0.57
     ProtoMessage
    -0.56
    POSITIVE LOGITS
     best
    0.65
     highest
    0.60
    best
    0.58
    max
    0.57
     maximum
    0.56
    最
    0.55
    Max
    0.55
    argmax
    0.55
     greatest
    0.54
     max
    0.53
    Act Density 0.707%

    No Known Activations