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

    Neuronpedia

    INDEX
    Explanations

    comparative terms related to levels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rates and levels within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leneck
    -0.78
    fecture
    -0.76
    ulhu
    -0.73
    vironment
    -0.72
    keleton
    -0.72
    ecast
    -0.72
    ologue
    -0.72
    icken
    -0.71
    rame
    -0.71
    pection
    -0.71
    POSITIVE LOGITS
     amounts
    1.86
     percentages
    1.76
     levels
    1.76
     rates
    1.76
     quantities
    1.71
     heights
    1.62
     volumes
    1.62
     thresholds
    1.59
     ratios
    1.59
     margins
    1.57
    Act Density 0.280%

    No Known Activations