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

    Neuronpedia

    INDEX
    Explanations

    locations or directions mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to waiting and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.72
     unanswered
    -0.71
     reproduced
    -0.68
     wink
    -0.68
     unequivocally
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    mo
    -0.64
    etheless
    -0.62
     outright
    -0.62
     singular
    -0.61
    POSITIVE LOGITS
     renov
    0.87
     renovations
    0.77
    orate
    0.76
    interstitial
    0.75
     assignment
    0.75
     exams
    0.74
     assignments
    0.74
     duties
    0.74
     deliveries
    0.72
     shipment
    0.69
    Act Density 0.796%

    No Known Activations