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

    Neuronpedia

    INDEX
    Explanations

    references to animal handling and enclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swelling
    -0.15
     inflation
    -0.14
     museums
    -0.14
     lug
    -0.14
     fund
    -0.14
    iens
    -0.14
     puff
    -0.14
     domestic
    -0.13
     libraries
    -0.13
    bos
    -0.13
    POSITIVE LOGITS
     pens
    0.28
     cage
    0.25
     Pens
    0.25
     cages
    0.25
     kenn
    0.24
     pen
    0.23
    wire
    0.23
     crate
    0.23
     wire
    0.23
    Wire
    0.22
    Act Density 0.042%

    No Known Activations