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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts to access more information or continue reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.80
    opard
    -0.72
    WC
    -0.70
    ascal
    -0.67
    UTION
    -0.67
    WP
    -0.67
    VC
    -0.66
    اÙĦ
    -0.65
    FL
    -0.65
    amel
    -0.65
    POSITIVE LOGITS
     aloud
    1.02
     Read
    0.90
    ahead
    0.86
    Write
    0.86
    htaking
    0.84
    estone
    0.81
    iness
    0.80
    sburg
    0.79
    ying
    0.78
    ied
    0.76
    Act Density 0.018%

    No Known Activations