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

    Neuronpedia

    INDEX
    Explanations

    names of specific physical rooms or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific rooms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.75
    olk
    -0.72
    yright
    -0.66
     drawn
    -0.65
     dubious
    -0.65
    ublished
    -0.64
    involved
    -0.63
    outed
    -0.62
    drawn
    -0.61
    riend
    -0.61
    POSITIVE LOGITS
     Room
    1.52
     Rooms
    1.18
    Room
    1.11
     Door
    0.92
     Floor
    0.90
     Cell
    0.81
     Soup
    0.80
     Syndrome
    0.79
     Theatre
    0.79
     Disorders
    0.78
    Act Density 0.009%

    No Known Activations