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

    Neuronpedia

    INDEX
    Explanations

    references to toys in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.16
    iyon
    -0.15
    mers
    -0.15
    stag
    -0.15
    pheric
    -0.15
    stk
    -0.15
    nock
    -0.15
    wy
    -0.14
    eners
    -0.14
    anter
    -0.14
    POSITIVE LOGITS
    toy
    0.19
     toy
    0.18
     toys
    0.16
    acht
    0.16
    oh
    0.16
    Toy
    0.15
     Toy
    0.15
    nton
    0.15
    ama
    0.14
    iet
    0.14
    Act Density 0.008%

    No Known Activations