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

    Neuronpedia

    INDEX
    Explanations

    scientific terms or related information

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations, acronyms, and initialisms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staples
    -0.69
    channelAvailability
    -0.68
     immediate
    -0.67
     offence
    -0.67
     approximate
    -0.62
     defect
    -0.60
     width
    -0.60
     overlap
    -0.60
     specifics
    -0.59
     yourselves
    -0.59
    POSITIVE LOGITS
    Äĩ
    0.89
    imaru
    0.87
    merce
    0.87
    quit
    0.82
    Äį
    0.80
    rencies
    0.80
    atari
    0.79
    ifix
    0.79
    enium
    0.76
    mega
    0.75
    Act Density 0.455%

    No Known Activations