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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Area
    -0.16
     ?><?
    -0.16
    ubat
    -0.15
     NSStringFromClass
    -0.15
    ]={↵
    -0.15
    моÑĢ
    -0.15
     principalTable
    -0.14
    .hm
    -0.14
    %B
    -0.14
    /***/
    -0.14
    POSITIVE LOGITS
     site
    0.39
    site
    0.32
    -site
    0.29
     scene
    0.29
     premises
    0.28
     premise
    0.28
     location
    0.25
    scene
    0.24
    âĢIJ
    0.23
    âĢij
    0.23
    Act Density 0.075%

    No Known Activations