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

    Neuronpedia

    INDEX
    Explanations

    references to physical structures like wings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wing" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¤
    -0.74
     Uz
    -0.70
     metab
    -0.70
    Interstitial
    -0.69
     Cumber
    -0.67
     Glock
    -0.64
     IMAGES
    -0.64
     Nare
    -0.63
     CBI
    -0.63
    âĶĢâĶĢ
    -0.62
    POSITIVE LOGITS
    tips
    1.38
    tip
    1.36
    nuts
    1.32
    nut
    1.23
    edly
    1.03
     Chun
    0.93
    erness
    0.93
    ners
    0.91
    notes
    0.89
    bill
    0.89
    Act Density 0.019%

    No Known Activations