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

    Neuronpedia

    INDEX
    Explanations

    references to notable buildings and tourist attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heard
    -0.15
     Sink
    -0.15
    gren
    -0.14
    odial
    -0.14
    allah
    -0.14
    Bounds
    -0.14
     downstream
    -0.14
    unte
    -0.14
     Alley
    -0.13
     torpedo
    -0.13
    POSITIVE LOGITS
     observation
    0.33
     platform
    0.29
     rooftop
    0.28
     platforms
    0.28
     lookout
    0.28
     tower
    0.27
    observation
    0.27
     Observation
    0.27
     viewing
    0.27
     viewpoint
    0.27
    Act Density 0.170%

    No Known Activations