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

    Neuronpedia

    INDEX
    Explanations

    quantitative relationships and changes in variables within mathematical formulations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    net
    -0.54
     +
    -0.49
    Net
    -0.48
     net
    -0.46
    defineProperty
    -0.45
     le
    -0.42
     combined
    -0.41
     G
    -0.41
     Net
    -0.41
     
    -0.40
    POSITIVE LOGITS
    +#+
    0.89
    \{\\
    0.88
    ंदीखरीदारी
    0.83
     myſelf
    0.80
     وتسجيلات
    0.76
     protoimpl
    0.75
    RUnlock
    0.72
     ſeveral
    0.72
     pleaſure
    0.71
     GetEnumerator
    0.71
    Act Density 0.065%

    No Known Activations