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

    Neuronpedia

    INDEX
    Explanations

    names of people within sentence structures

    oai_token-act-pair · gpt-3.5-turbo

    specific names of people, likely related to sports or celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.55
     morbid
    -0.53
    REF
    -0.53
     Canadians
    -0.53
    âĸĵ
    -0.51
     indul
    -0.51
     NETWORK
    -0.50
    ensional
    -0.50
     platinum
    -0.49
     regard
    -0.49
    POSITIVE LOGITS
     respectively
    0.72
    hetti
    0.72
     etc
    0.70
    imus
    0.70
    alli
    0.64
    ĪĴ
    0.64
     LLP
    0.63
    inton
    0.62
    iak
    0.62
    ];
    0.61
    Act Density 0.799%

    No Known Activations