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

    Neuronpedia

    INDEX
    Explanations

    references to natural landscapes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "landscape" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.89
    abad
    -0.79
    uster
    -0.79
    ibo
    -0.78
    ule
    -0.76
    idel
    -0.75
    etts
    -0.75
    istration
    -0.75
    ials
    -0.73
    ishops
    -0.73
    POSITIVE LOGITS
    scape
    1.07
     landscape
    0.86
     Rover
    0.85
     Photographer
    0.82
     landscapes
    0.80
    cape
    0.78
     backdrop
    0.72
     Architecture
    0.72
     wallpaper
    0.70
     Setting
    0.69
    Act Density 0.019%

    No Known Activations