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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups or individuals in the context of news or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to service members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nichols
    -0.72
     Bauer
    -0.70
    hee
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
     Buffy
    -0.66
     Robbie
    -0.65
     bitterness
    -0.65
     ABV
    -0.65
     HIP
    -0.64
     Ryder
    -0.64
    POSITIVE LOGITS
    emen
    1.60
    ghan
    1.02
    ovic
    0.93
    folk
    0.93
    ufact
    0.90
    estyles
    0.89
    ilitation
    0.88
    isphere
    0.87
    pread
    0.86
    ople
    0.85
    Act Density 0.003%

    No Known Activations