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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.71
     apology
    -0.62
    ocol
    -0.60
     Apart
    -0.60
     Recap
    -0.59
     Anyway
    -0.59
     ³³
    -0.58
    ********
    -0.57
     dispatch
    -0.57
     Saying
    -0.57
    POSITIVE LOGITS
    been
    1.31
     been
    1.30
     undergone
    1.06
     Been
    0.98
     endured
    0.96
     arisen
    0.95
     become
    0.94
    kell
    0.90
     existed
    0.89
     worked
    0.88
    Act Density 0.181%

    No Known Activations