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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "read" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "read" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ño
    -0.73
    afort
    -0.68
    ovie
    -0.68
    xon
    -0.67
    Enlarge
    -0.65
    ctions
    -0.65
    pload
    -0.64
    berus
    -0.64
    avior
    -0.63
     WWF
    -0.63
    POSITIVE LOGITS
     aloud
    1.32
    just
    1.11
     comprehension
    1.03
    mitt
    0.92
    dress
    0.88
     excerpts
    0.81
    write
    0.81
    mill
    0.79
    ied
    0.79
    Write
    0.78
    Act Density 0.027%

    No Known Activations