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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to lists or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apa
    -0.15
    ced
    -0.15
    iro
    -0.15
    osti
    -0.15
    agram
    -0.14
    uela
    -0.14
    ometers
    -0.14
    gable
    -0.14
    sea
    -0.14
    uster
    -0.14
    POSITIVE LOGITS
    eners
    0.20
    askell
    0.19
    erv
    0.17
    itty
    0.17
    eming
    0.17
    ENER
    0.16
    icle
    0.16
    -unstyled
    0.15
    oke
    0.15
    ear
    0.15
    Act Density 0.024%

    No Known Activations