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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to textual materials and content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.82
     shenan
    -0.81
     intersper
    -0.80
     cushi
    -0.78
     encomp
    -0.75
     tupperware
    -0.73
     increa
    -0.73
     affor
    -0.71
     swarovski
    -0.71
     hairc
    -0.71
    POSITIVE LOGITS
     material
    1.32
    material
    1.32
     Material
    1.20
    Material
    1.20
     materials
    1.19
    materials
    1.15
     Materials
    1.06
    MATERIAL
    1.06
     MATERIAL
    1.05
    aterial
    1.04
    Act Density 0.047%

    No Known Activations