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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "read" and related terms that indicate reading activity or comprehension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andom
    -0.17
    vrier
    -0.17
    eldorf
    -0.17
    kes
    -0.15
    chner
    -0.15
    owe
    -0.15
    partment
    -0.15
    ideos
    -0.14
    xi
    -0.14
    gia
    -0.14
    POSITIVE LOGITS
    just
    0.35
    /view
    0.30
    /watch
    0.30
    /list
    0.29
    /write
    0.27
     aloud
    0.26
    ied
    0.26
    apt
    0.24
    mitted
    0.24
     comprehension
    0.24
    Act Density 0.075%

    No Known Activations