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

    Neuronpedia

    INDEX
    Explanations

    instances of characters observing or gazing at others in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inward
    -0.16
    ader
    -0.15
    iew
    -0.15
    ayd
    -0.14
    unta
    -0.14
    dam
    -0.14
    ht
    -0.14
     znam
    -0.14
    ury
    -0.13
    om
    -0.13
    POSITIVE LOGITS
     around
    0.17
     sky
    0.17
     down
    0.17
     towards
    0.17
     over
    0.16
     toward
    0.16
     tern
    0.15
     away
    0.15
     up
    0.15
    RGBA
    0.15
    Act Density 0.068%

    No Known Activations