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

    Neuronpedia

    INDEX
    Explanations

    mentions of being on or performing on a stage

    oai_token-act-pair · gpt-3.5-turbo

    references to "stage" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umar
    -0.79
    vironment
    -0.77
    entimes
    -0.72
    vernment
    -0.72
    ipop
    -0.71
    zzle
    -0.69
    £ı
    -0.67
    anguages
    -0.67
    etheless
    -0.67
    versely
    -0.66
    POSITIVE LOGITS
    room
    1.05
    rooms
    0.98
    craft
    0.95
    yard
    0.90
    goers
    0.88
    hands
    0.87
    wright
    0.86
    floor
    0.82
    house
    0.80
    roller
    0.77
    Act Density 0.018%

    No Known Activations