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

    Neuronpedia

    INDEX
    Explanations

    references to reading or written text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "read" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.70
    ño
    -0.69
    pload
    -0.64
    Credit
    -0.64
    afort
    -0.63
    ctions
    -0.63
    ella
    -0.62
    henko
    -0.59
    Enlarge
    -0.58
    ction
    -0.58
    POSITIVE LOGITS
     aloud
    1.34
    just
    1.16
     comprehension
    1.11
    mitt
    0.91
    dress
    0.87
    ied
    0.87
     excerpts
    0.86
     books
    0.84
    write
    0.84
    itatively
    0.82
    Act Density 0.031%

    No Known Activations