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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names and locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gluten

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cells
    -0.67
     Orbit
    -0.66
     electrodes
    -0.66
     ev
    -0.64
     ESA
    -0.64
    immers
    -0.62
     Lith
    -0.61
     Brist
    -0.61
    bed
    -0.59
     Scand
    -0.59
    POSITIVE LOGITS
    uten
    1.27
    culosis
    0.89
     predec
    0.85
    elsen
    0.84
    htaking
    0.84
    hei
    0.83
    epend
    0.80
    avascript
    0.80
    uke
    0.78
    utenant
    0.77
    Act Density 0.009%

    No Known Activations