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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications such as journals, research institutes, universities, and specific research studies

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lift
    -0.75
    suff
    -0.68
    worldly
    -0.67
    obin
    -0.66
    overs
    -0.65
    butt
    -0.64
    comings
    -0.62
    lash
    -0.61
    ans
    -0.60
    Override
    -0.60
    POSITIVE LOGITS
     Inc
    1.15
     LLC
    1.11
     Ltd
    1.01
     aka
    0.92
     wherein
    0.79
     ISBN
    0.79
     chaired
    0.78
     LLP
    0.78
    Gall
    0.77
    Magikarp
    0.77
    Act Density 0.252%

    No Known Activations