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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "look" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scribed
    -0.73
    versive
    -0.67
    âĹ¼
    -0.67
    die
    -0.66
    oled
    -0.66
    fer
    -0.65
    ricular
    -0.65
    thus
    -0.65
    death
    -0.65
    EStreamFrame
    -0.64
    POSITIVE LOGITS
    ahead
    0.85
     LOOK
    0.75
    ENE
    0.72
     snipp
    0.71
    \\\\\\\\
    0.68
    ":"/
    0.67
    outs
    0.66
    checks
    0.66
    eyes
    0.66
    ogh
    0.66
    Act Density 0.053%

    No Known Activations