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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons and thresholds related to temperatures and other metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.74
    httphttps
    -0.64
    الإنجليزية
    -0.63
    vants
    -0.55
    Примітки
    -0.55
    出版年
    -0.54
    abestanden
    -0.53
     kaarangay
    -0.48
    Enllaços
    -0.47
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
     expectations
    0.92
     what
    0.87
    expectations
    0.80
     expectation
    0.72
     Expectations
    0.69
     previous
    0.68
     expected
    0.68
     oczeki
    0.67
     twice
    0.66
    Expectations
    0.65
    Act Density 0.660%

    No Known Activations