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

    Neuronpedia

    INDEX
    Explanations

    structured time expressions like durations

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations and numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     substitutes
    -0.89
     strengths
    -0.74
     weights
    -0.73
     coefficients
    -0.72
     relics
    -0.72
     amenities
    -0.71
     keeper
    -0.71
     thinkers
    -0.70
     testers
    -0.70
     devs
    -0.69
    POSITIVE LOGITS
     tumultuous
    0.99
    successful
    0.97
    planned
    0.96
     protracted
    0.95
    romptu
    0.92
    frac
    0.90
    intensive
    0.90
    trial
    0.89
    month
    0.87
     publicized
    0.87
    Act Density 0.328%

    No Known Activations