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

    Neuronpedia

    INDEX
    Explanations

    mentions of libraries and their collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fat
    -0.15
     Fat
    -0.15
    ilate
    -0.14
    ijken
    -0.14
    imson
    -0.13
    asy
    -0.13
     FAT
    -0.13
    arda
    -0.13
     Goods
    -0.13
     veniam
    -0.13
    POSITIVE LOGITS
     Boxes
    0.26
     Finding
    0.26
     finding
    0.24
     boxes
    0.24
    Finding
    0.23
     box
    0.23
    Boxes
    0.23
    finding
    0.23
     Box
    0.23
    Processed
    0.23
    Act Density 0.030%

    No Known Activations