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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols with positive associations

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings and expressions of enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ranking
    -0.38
     municip
    -0.36
    ãĥ¼ãĥĨãĤ£
    -0.35
    icter
    -0.33
     StarCraft
    -0.32
     geopolitical
    -0.32
     parity
    -0.32
    rovers
    -0.32
     incent
    -0.31
    uart
    -0.31
    POSITIVE LOGITS
    merce
    0.49
    .''
    0.41
    )."
    0.41
    leep
    0.41
    20439
    0.40
    .).
    0.40
    )].
    0.39
    SourceFile
    0.39
    ilantro
    0.39
    zzle
    0.38
    Act Density 3.127%

    No Known Activations