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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper names or nouns, particularly those that may refer to people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.67
    ::::::::
    -0.48
     Palest
    -0.48
    CLASSIFIED
    -0.48
    soever
    -0.47
     obser
    -0.46
     Princ
    -0.46
     livest
    -0.45
     Sabb
    -0.44
     FedEx
    -0.44
    POSITIVE LOGITS
    rake
    0.59
    ax
    0.58
    idine
    0.57
    utenberg
    0.54
    zon
    0.53
    ipers
    0.50
    acles
    0.50
    ioch
    0.49
    isk
    0.48
    idge
    0.48
    Act Density 0.519%

    No Known Activations