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

    Neuronpedia

    INDEX
    Explanations

    numerical values expressed as ranges, with a focus on margins of error

    oai_token-act-pair · gpt-3.5-turbo

    numerical indicators of changes or fluctuations, particularly concerning declines and margins of error

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.98
    NetMessage
    -0.93
    rahim
    -0.88
    hots
    -0.84
    ively
    -0.82
    oros
    -0.80
    20439
    -0.79
    SourceFile
    -0.78
    ible
    -0.76
    istry
    -0.74
    POSITIVE LOGITS
    thur
    0.85
     Noon
    0.68
    terness
    0.67
     (-
    0.65
     Fidel
    0.65
     Nom
    0.65
     noon
    0.63
     Vie
    0.62
     Sax
    0.62
    cise
    0.61
    Act Density 0.039%

    No Known Activations