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

    Neuronpedia

    INDEX
    Explanations

    strings indicating the end of an article or segment

    oai_token-act-pair · gpt-3.5-turbo

    indicators of additional content or further reading prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.74
     ende
    -0.69
    hement
    -0.67
    ector
    -0.65
     respectively
    -0.64
     hooked
    -0.63
     supervised
    -0.62
    sembly
    -0.61
     intermedi
    -0.61
     whichever
    -0.59
    POSITIVE LOGITS
    âĢ¢
    1.05
    âĻ¦
    0.94
    Comments
    0.91
    âĸº
    0.89
    Tags
    0.86
    Woman
    0.86
    âĹı
    0.82
    Recent
    0.81
    >>>
    0.80
    Report
    0.79
    Act Density 0.062%

    No Known Activations