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

    Neuronpedia

    INDEX
    Explanations

    phrases related to setting or breaking precedents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or historical precedents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.83
    yan
    -0.76
    tein
    -0.75
    atron
    -0.72
    kie
    -0.71
    riv
    -0.68
    igun
    -0.68
    OTOS
    -0.68
    aucuses
    -0.68
    atto
    -0.67
    POSITIVE LOGITS
     precedent
    1.16
     preced
    1.00
    DragonMagazine
    0.88
     precedence
    0.82
    faced
    0.69
    chall
    0.68
    setting
    0.68
    LR
    0.66
     enshr
    0.66
    Setting
    0.65
    Act Density 0.019%

    No Known Activations