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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increasing the stakes or level of something

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing levels or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iculture
    -0.79
    nuts
    -0.70
    ï¸ı
    -0.66
    apons
    -0.65
    ammad
    -0.65
    OTS
    -0.65
    ersed
    -0.65
    umper
    -0.64
     Disaster
    -0.63
    assed
    -0.63
    POSITIVE LOGITS
     ante
    2.02
     prominence
    1.62
    Import
    1.46
     Import
    1.46
     relevance
    1.46
     rele
    1.16
    ei
    1.14
    eus
    1.00
     classmate
    1.00
     stature
    0.98
    Act Density 0.054%

    No Known Activations