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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to speech

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and syntactical markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dres
    -0.75
     Azerb
    -0.74
     Borders
    -0.64
     Gibraltar
    -0.63
     Allied
    -0.63
     Calais
    -0.61
     Clarkson
    -0.60
     Jae
    -0.60
     marqu
    -0.60
     surn
    -0.60
    POSITIVE LOGITS
    Í
    0.85
     ][
    0.80
    quickShipAvailable
    0.79
    actionDate
    0.74
    amins
    0.73
     ]
    0.71
    aret
    0.70
    onut
    0.67
    ertain
    0.66
    lio
    0.65
    Act Density 0.091%

    No Known Activations