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

    Neuronpedia

    INDEX
    Explanations

    references to walls and wall-related features or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oss
    -0.16
    lemn
    -0.15
    exus
    -0.15
    oga
    -0.15
    ald
    -0.14
    лав
    -0.14
    esus
    -0.14
    INU
    -0.14
    λικά
    -0.14
    ood
    -0.14
    POSITIVE LOGITS
     walls
    0.20
    -mounted
    0.19
    sWith
    0.18
    -wall
    0.17
     wall
    0.17
    å£ģ
    0.17
    aver
    0.16
    ych
    0.16
    /window
    0.16
    town
    0.16
    Act Density 0.040%

    No Known Activations