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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.98
    Portale
    -0.96
    脚注の使い方
    -0.94
    Datuak
    -0.88
     المعيارى
    -0.82
     Biôgrafia
    -0.81
    исленность
    -0.80
     kasarigan
    -0.79
     SafeMath
    -0.78
     GenerationType
    -0.78
    POSITIVE LOGITS
    3
    0.62
    1
    0.60
     
    0.58
    4
    0.57
    5
    0.56
    2
    0.56
    7
    0.53
    9
    0.52
    6
    0.50
    ̈́
    0.46
    Act Density 2.562%

    No Known Activations