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

    Neuronpedia

    INDEX
    Explanations

    objects and their placement in pockets or bags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    екаÑĢ
    -0.16
    ingleton
    -0.14
     pedest
    -0.14
    lage
    -0.14
     plywood
    -0.14
     rugs
    -0.14
     دار
    -0.14
    andles
    -0.14
    ÑĢг
    -0.14
    LAG
    -0.14
    POSITIVE LOGITS
     pocket
    0.44
     pockets
    0.42
    -pocket
    0.33
    Pocket
    0.30
     Pocket
    0.29
    pur
    0.27
     purse
    0.24
     coat
    0.24
    Âłp
    0.23
     cargo
    0.23
    Act Density 0.060%

    No Known Activations