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

    Neuronpedia

    INDEX
    Explanations

    comparisons in performance or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to comparison and relative positioning in rankings or standings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGHTS
    -0.69
    kef
    -0.67
    oother
    -0.65
    fff
    -0.65
     WARN
    -0.65
    Ô
    -0.65
    Cmd
    -0.64
    CVE
    -0.61
    idav
    -0.61
    fw
    -0.61
    POSITIVE LOGITS
     competitors
    1.21
     rivals
    1.18
     contemporaries
    1.04
     peers
    1.03
     rival
    1.00
     competitor
    0.94
     others
    0.88
     giants
    0.88
     counterparts
    0.87
     comparable
    0.86
    Act Density 0.164%

    No Known Activations