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

    Neuronpedia

    INDEX
    Explanations

    expressions that assert the existence or state of something, often in a definitional or explanatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.60
     contextLoads
    -0.56
     AssemblyTitle
    -0.49
    المناصب
    -0.49
    StructEnd
    -0.48
    ViewImports
    -0.48
     SafeMath
    -0.46
    makeText
    -0.45
    บ้าง
    -0.44
    中でも
    -0.44
    POSITIVE LOGITS
     twofold
    1.11
     threefold
    0.77
     simple
    0.71
    在于
    0.70
     summed
    0.61
     obvious
    0.60
     finding
    0.60
     simply
    0.59
     evident
    0.57
    simply
    0.57
    Act Density 0.409%

    No Known Activations