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

    Neuronpedia

    INDEX
    Explanations

    words relating to nighttime or late activities

    oai_token-act-pair · gpt-3.5-turbo

    references to late-night television shows and their hosts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achu
    -0.85
     nomine
    -0.72
     intangible
    -0.71
     brim
    -0.70
     tolerance
    -0.69
     DOI
    -0.68
    âķIJ
    -0.67
     mirrors
    -0.64
     Rica
    -0.64
     gelatin
    -0.64
    POSITIVE LOGITS
    earth
    0.92
    angled
    0.91
    night
    0.90
    Earth
    0.85
    success
    0.84
    middle
    0.84
    period
    0.81
    early
    0.80
    Georg
    0.80
    model
    0.79
    Act Density 0.066%

    No Known Activations