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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to quality and material attributes in product descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bero
    -0.15
     Greenwood
    -0.15
    gorm
    -0.15
    woo
    -0.14
     Morrison
    -0.14
    ral
    -0.14
     mess
    -0.14
     scar
    -0.14
    aktion
    -0.14
    -0.14
    POSITIVE LOGITS
    lius
    0.17
    chwitz
    0.16
    ,strong
    0.15
    SCII
    0.15
    odÃŃ
    0.15
    Ùģات
    0.14
    åĩºåĵģ
    0.14
    olas
    0.14
    undy
    0.14
    åĭĻ
    0.14
    Act Density 0.069%

    No Known Activations