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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     democrat
    -0.83
     indispensable
    -0.78
     compromises
    -0.72
     whatsoever
    -0.72
     irrelevant
    -0.71
     undermin
    -0.69
     fung
    -0.67
     bullshit
    -0.67
     transact
    -0.67
     stale
    -0.67
    POSITIVE LOGITS
     Initially
    1.10
     However
    1.04
     According
    1.04
     Previously
    0.99
     He
    0.99
     Asked
    0.97
     They
    0.97
     His
    0.96
     "@
    0.96
     While
    0.94
    Act Density 0.509%

    No Known Activations