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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and characters that might relate to technical information or data leaks

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.75
    DonaldTrump
    -0.70
     whiff
    -0.65
     stret
    -0.65
     globalization
    -0.64
     strongest
    -0.61
     mutual
    -0.60
     slightest
    -0.59
     brightest
    -0.58
    worldly
    -0.58
    POSITIVE LOGITS
    ae
    0.93
    wr
    0.86
    807
    0.85
    fe
    0.83
    708
    0.81
    }:
    0.80
    889
    0.80
    ea
    0.79
    328
    0.78
    ac
    0.77
    Act Density 0.014%

    No Known Activations