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

    Neuronpedia

    INDEX
    Explanations

    pronouns and related words

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and verbs that refer to entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Militia
    -0.71
     RTX
    -0.70
    Care
    -0.69
     Kinn
    -0.68
     Lou
    -0.68
     OL
    -0.66
    CCC
    -0.66
     Karn
    -0.65
     LOT
    -0.65
     Passenger
    -0.64
    POSITIVE LOGITS
     contained
    0.95
     involve
    0.90
     intersect
    0.89
     occur
    0.88
     involves
    0.88
     contain
    0.87
     originate
    0.87
     occurring
    0.86
     coincide
    0.85
     arising
    0.84
    Act Density 0.815%

    No Known Activations