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

    Neuronpedia

    INDEX
    Explanations

    the name of theaters or venues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of theaters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bring
    -0.83
    aunder
    -0.81
    nir
    -0.70
    vironment
    -0.70
    rontal
    -0.68
    unin
    -0.67
    20439
    -0.66
    yg
    -0.65
    erry
    -0.64
     probable
    -0.64
    POSITIVE LOGITS
     Theatre
    1.15
     Workshop
    1.11
     Royale
    1.02
     Theater
    0.97
    wright
    0.91
     Company
    0.89
     Rooms
    0.89
    eers
    0.88
    Walk
    0.85
     Orchestra
    0.84
    Act Density 0.010%

    No Known Activations