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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names such as Rash and Khalidi

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those related to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedented
    -0.86
    insula
    -0.84
    merce
    -0.84
    ciating
    -0.82
    psons
    -0.78
    govtrack
    -0.74
    opausal
    -0.73
    hedral
    -0.73
    regor
    -0.71
     Gutenberg
    -0.71
    POSITIVE LOGITS
     Rash
    1.03
    more
    0.76
    len
    0.76
    atile
    0.75
    tri
    0.74
    akh
    0.73
    Net
    0.72
    ash
    0.72
    encies
    0.70
    anu
    0.69
    Act Density 0.032%

    No Known Activations