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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to entertainment personalities

    oai_token-act-pair · gpt-3.5-turbo

    words related to births and their surrounding narratives or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keye
    -0.71
    keyes
    -0.66
    kered
    -0.63
     biology
    -0.62
     suc
    -0.62
     Floyd
    -0.61
    âĸ¬âĸ¬
    -0.61
     proprietary
    -0.60
     labeled
    -0.59
     vitro
    -0.59
    POSITIVE LOGITS
    irth
    0.86
    urst
    0.86
    ahu
    0.85
     Lauder
    0.85
    irling
    0.83
    lessness
    0.80
    arna
    0.78
     Leth
    0.76
    sers
    0.75
    shed
    0.74
    Act Density 0.017%

    No Known Activations