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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odd
    -0.77
    't
    -0.65
    riott
    -0.65
     Heights
    -0.63
    now
    -0.63
    NOW
    -0.62
     currently
    -0.59
    arta
    -0.59
     Mans
    -0.57
     Franch
    -0.57
    POSITIVE LOGITS
     judged
    0.99
     eaten
    0.95
     able
    0.95
     remembered
    0.94
     rewarded
    0.93
     replaced
    0.90
     punished
    0.90
    fall
    0.88
     greeted
    0.86
     sacrificed
    0.86
    Act Density 0.179%

    No Known Activations