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

    Neuronpedia

    INDEX
    Explanations

    mentions of movie premieres and related events

    oai_token-act-pair · gpt-3.5-turbo

    references to premieres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urg
    -0.76
    akia
    -0.75
    ordinate
    -0.73
    surface
    -0.73
    warts
    -0.72
    agh
    -0.71
    nuts
    -0.70
    asses
    -0.69
    oso
    -0.68
    croft
    -0.67
    POSITIVE LOGITS
     episode
    0.96
     screenings
    0.95
     screening
    0.90
     premiere
    0.90
     countdown
    0.89
     airing
    0.84
     reel
    0.81
     episodes
    0.79
     premie
    0.78
    éĹĺ
    0.76
    Act Density 0.055%

    No Known Activations