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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and their actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.90
     متعلقه
    -0.86
     Shogun
    -0.74
    fastjson
    -0.70
    llac
    -0.69
     &___
    -0.65
    kunta
    -0.62
     Tahiti
    -0.60
    perity
    -0.60
    dillera
    -0.60
    POSITIVE LOGITS
     Hogwarts
    0.93
     Harry
    0.87
     Dumbledore
    0.82
     Voldemort
    0.81
    Harry
    0.79
     Potter
    0.78
     harry
    0.77
     wizard
    0.76
    wizard
    0.72
     Hermione
    0.72
    Act Density 0.080%

    No Known Activations