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

    Neuronpedia

    INDEX
    Explanations

    elements associated with competitive events or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.71
     and
    -0.55
     etc
    -0.55
    /
    -0.54
     (
    -0.48
     &
    -0.47
     later
    -0.47
     Later
    -0.47
     فريبيس
    -0.47
     algemeen
    -0.47
    POSITIVE LOGITS
     penned
    0.94
     Monfieur
    0.91
    Folks
    0.89
     foes
    0.87
     Folks
    0.84
     critters
    0.83
     fella
    0.82
    KommentareTeilen
    0.82
     youngsters
    0.82
     Majefty
    0.81
    Act Density 0.448%

    No Known Activations