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

    Neuronpedia

    INDEX
    Explanations

    references to setting, breaking, or surpassing records

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to record-setting achievements and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anqu
    -0.77
    iltr
    -0.75
    arty
    -0.74
    acted
    -0.70
     lav
    -0.70
    Solution
    -0.69
    vous
    -0.69
    rien
    -0.69
    igan
    -0.68
    xit
    -0.68
    POSITIVE LOGITS
     records
    1.49
     record
    1.48
     Guinness
    1.33
     Records
    1.23
     Record
    1.16
    record
    1.14
     milestone
    1.08
     mark
    1.03
     milestones
    0.99
     precedent
    0.96
    Act Density 0.141%

    No Known Activations