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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    specific dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.57
     spoiler
    -0.55
     Silence
    -0.54
     Arkham
    -0.51
     proxies
    -0.50
     extant
    -0.49
    bidden
    -0.49
     Silent
    -0.49
    Emer
    -0.49
     improvements
    -0.48
    POSITIVE LOGITS
     29
    0.88
     27
    0.88
     26
    0.84
     19
    0.83
     31
    0.82
     28
    0.79
     21
    0.79
     23
    0.78
     25
    0.76
     22
    0.76
    Act Density 0.036%

    No Known Activations