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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the influence of nature on human culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.82
     houſe
    -0.82
    ſelves
    -0.80
     ſche
    -0.79
     Савезне
    -0.79
     Majefty
    -0.78
    ſelf
    -0.78
     beginnetje
    -0.77
     betweenstory
    -0.77
     متعلقه
    -0.77
    POSITIVE LOGITS
     been
    0.99
     since
    0.93
     NSCoder
    0.82
     recently
    0.82
     recent
    0.81
     lately
    0.77
     recentemente
    0.74
     gotten
    0.70
    since
    0.69
    recently
    0.68
    Act Density 1.297%

    No Known Activations