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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rankings or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating notable events or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EngineDebug
    -0.81
    ALSE
    -0.73
    Query
    -0.70
    mil
    -0.68
    uce
    -0.63
    roth
    -0.63
    ido
    -0.62
    122
    -0.62
    DragonMagazine
    -0.62
    ½
    -0.61
    POSITIVE LOGITS
    efficiency
    1.00
    clusively
    0.99
    ordinate
    0.91
     regards
    0.90
    animate
    0.89
    ducers
    0.89
    clusions
    0.89
     vitro
    0.88
     conjunction
    0.87
     lieu
    0.86
    Act Density 0.158%

    No Known Activations