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

    Neuronpedia

    INDEX
    Explanations

    references to pets and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĽĦ
    -0.16
     Ngá»įc
    -0.15
    .nano
    -0.15
    ucas
    -0.14
     Animals
    -0.14
    oire
    -0.14
     Garn
    -0.14
    unan
    -0.14
     Tatto
    -0.14
    942
    -0.14
    POSITIVE LOGITS
     treat
    0.31
     treats
    0.28
     Kong
    0.27
     toys
    0.27
     Treat
    0.26
     fetch
    0.26
     bones
    0.26
     bone
    0.25
     toy
    0.25
     sque
    0.24
    Act Density 0.030%

    No Known Activations