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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Wil"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.83
     Butterfly
    -0.81
    ItemTracker
    -0.80
    oral
    -0.76
     shatter
    -0.71
    æĸ¹
    -0.71
     Parables
    -0.71
     crush
    -0.70
    âĶģ
    -0.69
    xual
    -0.66
    POSITIVE LOGITS
    mot
    1.11
    lem
    0.99
    fred
    0.99
     Whe
    0.95
    ibr
    0.92
    bur
    0.90
    cox
    0.90
    lette
    0.90
    mington
    0.90
    ters
    0.88
    Act Density 0.015%

    No Known Activations