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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it did" and variations involving the word "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.91
    ieval
    -0.75
    ãĤ´ãĥ³
    -0.74
    cific
    -0.73
    BuyableInstoreAndOnline
    -0.71
    RNA
    -0.68
    nor
    -0.68
    éĹĺ
    -0.66
    anchester
    -0.66
    mental
    -0.66
    POSITIVE LOGITS
     darn
    0.91
     damn
    0.91
     therein
    0.85
     importantly
    0.80
     damned
    0.79
     ain
    0.77
     downright
    0.76
     goddamn
    0.75
     awfully
    0.75
     cru
    0.75
    Act Density 0.323%

    No Known Activations