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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically locations and companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obb
    -0.74
    iffe
    -0.71
    iott
    -0.70
    ount
    -0.66
     Dob
    -0.65
    acious
    -0.64
    abb
    -0.62
    forward
    -0.61
    unders
    -0.61
    NF
    -0.60
    POSITIVE LOGITS
    âĸ¬âĸ¬
    0.84
    eers
    0.84
    ching
    0.84
    eer
    0.82
    thia
    0.80
    neys
    0.80
    heed
    0.78
    seys
    0.76
     Alam
    0.75
    ney
    0.73
    Act Density 0.049%

    No Known Activations