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

    Neuronpedia

    INDEX
    Explanations

    numbers and numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seventeen
    -0.88
     Seventeen
    -0.78
     ten
    -0.73
    تقاوى
    -0.73
     eighteen
    -0.70
     CreateTagHelper
    -0.69
     eleven
    -0.69
     thirteen
    -0.69
     twelve
    -0.69
     twenty
    -0.69
    POSITIVE LOGITS
    CompilerServices
    0.45
     congrès
    0.44
    Sep
    0.43
    Chham
    0.42
     wzglę
    0.42
    nack
    0.41
    田市
    0.41
     verra
    0.40
     anteriore
    0.40
     TestBed
    0.40
    Act Density 0.285%

    No Known Activations