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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "it" and related pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Exit
    -0.66
    Guest
    -0.64
     Wikipedia
    -0.62
    ãĤ¢
    -0.62
     trivia
    -0.61
    Translation
    -0.61
    Huh
    -0.61
    Interstitial
    -0.59
     Kinn
    -0.59
    central
    -0.58
    POSITIVE LOGITS
     expects
    1.13
     intends
    1.12
     regretted
    1.09
     hoped
    0.96
     hopes
    0.94
     anticip
    0.93
    'll
    0.93
     intend
    0.91
     received
    0.91
     believes
    0.90
    Act Density 0.102%

    No Known Activations