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

    Neuronpedia

    INDEX
    Explanations

    descriptions of landscapes and environmental settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.14
    æĬ¼
    -0.14
    Overflow
    -0.14
    _overflow
    -0.13
     Drawer
    -0.13
     corridors
    -0.13
     Trails
    -0.13
    821
    -0.13
    еÑģÑı
    -0.13
    overflow
    -0.12
    POSITIVE LOGITS
     horizon
    0.34
     distant
    0.29
     buildings
    0.28
     houses
    0.28
     clouds
    0.25
     sky
    0.23
    hor
    0.23
     rooft
    0.23
     roofs
    0.23
     trees
    0.22
    Act Density 0.155%

    No Known Activations