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

    Neuronpedia

    INDEX
    Explanations

    references to a specific instance or object in a coding or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.88
     fubject
    -0.82
     myſelf
    -0.81
     purpoſe
    -0.79
     fhort
    -0.76
     uſed
    -0.75
     ſeveral
    -0.74
     faſt
    -0.73
     plufieurs
    -0.72
     leaſt
    -0.72
    POSITIVE LOGITS
     instance
    1.22
    Instance
    1.19
     example
    1.01
    instance
    0.95
    INSTANCE
    0.91
    example
    0.89
     Instance
    0.85
     INSTANCE
    0.82
     Example
    0.78
    实例
    0.76
    Act Density 0.103%

    No Known Activations