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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coin
    -0.64
    âĻ¦
    -0.63
    PI
    -0.63
    bie
    -0.60
    alias
    -0.59
    —-
    -0.59
    Gi
    -0.58
    hack
    -0.58
    *****
    -0.58
    bery
    -0.58
    POSITIVE LOGITS
     been
    1.12
     undergone
    1.08
    iths
    1.02
     begun
    0.97
     previously
    0.96
     originally
    0.94
     gone
    0.90
     gotten
    0.86
     taken
    0.83
     flown
    0.83
    Act Density 0.160%

    No Known Activations