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

    Neuronpedia

    INDEX
    Explanations

    negative descriptions or lack of something in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors regarding personal circumstances and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    su
    -0.79
    emin
    -0.74
    hurst
    -0.69
    âķIJ
    -0.68
     attRot
    -0.66
    Join
    -0.65
    Su
    -0.64
    usa
    -0.64
    CAST
    -0.63
    stand
    -0.62
    POSITIVE LOGITS
     embassies
    0.67
     corrid
    0.64
     loneliness
    0.63
    ocard
    0.63
    etheless
    0.62
    inventoryQuantity
    0.61
     wallets
    0.60
     hobbies
    0.60
     encyclopedia
    0.59
     goddamn
    0.58
    Act Density 0.502%

    No Known Activations