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

    Neuronpedia

    INDEX
    Explanations

    organizations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    the auxiliary verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.72
     Franch
    -0.67
     Badge
    -0.65
     TOD
    -0.63
    izable
    -0.62
    iosyncr
    -0.61
     landscapes
    -0.60
     proportions
    -0.59
    oyle
    -0.59
     barrels
    -0.58
    POSITIVE LOGITS
     notified
    1.25
     alerted
    1.18
     founded
    1.05
     contacted
    1.04
     informed
    1.02
     consulted
    0.98
     unable
    0.96
     able
    0.94
     briefed
    0.94
     fined
    0.94
    Act Density 0.166%

    No Known Activations