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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases indicating a scale or ranking

    oai_token-act-pair · gpt-3.5-turbo

    references to firearms and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peoples
    -0.70
     Philos
    -0.68
     Hels
    -0.66
    achu
    -0.65
     Papa
    -0.65
     Loll
    -0.62
    heit
    -0.61
    idered
    -0.60
     Pixie
    -0.60
     backstage
    -0.60
    POSITIVE LOGITS
    operated
    0.85
    linked
    0.85
    eligible
    0.85
    zone
    0.83
    breaker
    0.83
    adjusted
    0.81
    site
    0.80
    rate
    0.80
    mask
    0.79
    rival
    0.79
    Act Density 0.077%

    No Known Activations