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

    Neuronpedia

    INDEX
    Explanations

    properties associated with a specific data model in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.03
     myſelf
    -1.02
     Jefus
    -0.99
     pleaſure
    -0.99
     purpoſe
    -0.97
     leaſt
    -0.95
     houſe
    -0.93
     iſt
    -0.90
     ſeveral
    -0.88
     Reſ
    -0.87
    POSITIVE LOGITS
    cale
    0.88
    cal
    0.62
    hr
    0.58
    </h2>
    0.55
    <eos>
    0.55
    ↵↵
    0.55
    .
    0.53
     (
    0.52
    "
    0.50
     
    0.49
    Act Density 0.167%

    No Known Activations