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

    Neuronpedia

    INDEX
    Explanations

    mentions of different fictional worlds or settings within text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of "world"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.95
    sbm
    -0.87
    ifer
    -0.84
    oug
    -0.78
    etsk
    -0.76
     Mehran
    -0.74
    aturday
    -0.72
    odox
    -0.71
    ++++
    -0.71
     actionGroup
    -0.69
    POSITIVE LOGITS
    liness
    1.12
    building
    1.11
    wide
    0.89
    scape
    0.89
     domination
    0.86
    arium
    0.83
    view
    0.83
    builders
    0.81
    views
    0.80
    spawn
    0.77
    Act Density 0.067%

    No Known Activations