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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dashed
    -0.73
     resurrected
    -0.66
     coma
    -0.66
     shattered
    -0.60
     blurred
    -0.60
     highlighted
    -0.59
     tradem
    -0.59
     revived
    -0.58
     groom
    -0.57
    ensional
    -0.57
    POSITIVE LOGITS
     fewer
    0.96
     surplus
    0.83
     brunt
    0.74
     annually
    0.73
     tonnes
    0.73
     watts
    0.71
    icum
    0.67
    grain
    0.66
     annual
    0.66
    SpaceEngineers
    0.66
    Act Density 0.124%

    No Known Activations