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

    Neuronpedia

    INDEX
    Explanations

    instructions for hands-on activities or crafts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     welding
    -0.15
    assis
    -0.15
    udies
    -0.14
     disin
    -0.14
    Slim
    -0.14
    exist
    -0.14
     Lynch
    -0.14
     stitching
    -0.13
     slim
    -0.13
     legal
    -0.13
    POSITIVE LOGITS
     technique
    0.18
     Technique
    0.16
    imd
    0.15
    SError
    0.15
    .lesson
    0.15
    ếp
    0.15
    è§Ĥçľĭ
    0.14
    ĮĢ
    0.14
    éĢ¸
    0.14
     thao
    0.14
    Act Density 0.197%

    No Known Activations