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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to a specific entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific pattern or substring within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poppy
    -0.66
    20439
    -0.64
     AMERICA
    -0.62
     goose
    -0.61
     Winchester
    -0.60
    mpeg
    -0.60
     DMV
    -0.60
    DIT
    -0.59
     fide
    -0.57
     common
    -0.56
    POSITIVE LOGITS
    achu
    1.27
    ernel
    1.22
    ernels
    1.20
    rish
    1.11
    owski
    1.04
    ileaks
    1.02
    ku
    1.01
    yu
    1.00
    hs
    1.00
    owsky
    0.99
    Act Density 0.052%

    No Known Activations