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

    Neuronpedia

    INDEX
    Explanations

    words related to physical landscapes

    oai_token-act-pair · gpt-3.5-turbo

    references to landscapes and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.91
    thood
    -0.80
    ibo
    -0.79
    rone
    -0.77
    uster
    -0.76
    etts
    -0.76
    ulate
    -0.74
    umption
    -0.74
    uana
    -0.74
    conn
    -0.73
    POSITIVE LOGITS
    scape
    1.03
     landscapes
    0.88
    ttes
    0.85
     Rover
    0.82
     vegetation
    0.81
     backdrop
    0.81
     landscape
    0.80
    cape
    0.80
    MAP
    0.77
     gardens
    0.73
    Act Density 0.029%

    No Known Activations