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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "it" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "it" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dding
    -0.65
     EVs
    -0.60
     foregoing
    -0.60
     Vill
    -0.57
     Fur
    -0.57
     Monetary
    -0.57
    elect
    -0.56
     Amph
    -0.56
     Sundays
    -0.56
     Spending
    -0.55
    POSITIVE LOGITS
    alian
    1.05
     occurred
    1.02
     consisted
    1.01
    unes
    0.99
     seems
    0.98
     appears
    0.97
     lasted
    0.93
     involves
    0.92
     seemed
    0.92
     occurs
    0.92
    Act Density 0.335%

    No Known Activations