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

    Neuronpedia

    INDEX
    Explanations

    words related to vocalization or speaking loudly

    oai_token-act-pair · gpt-3.5-turbo

    references to vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rand
    -0.75
     Taj
    -0.67
    FactoryReloaded
    -0.66
    ï¸
    -0.65
    Ô
    -0.65
     Louie
    -0.64
    uyomi
    -0.64
     Morning
    -0.63
     Firefly
    -0.63
     Lans
    -0.62
    POSITIVE LOGITS
     voc
    1.07
    oded
    0.97
    abulary
    0.96
    ationally
    0.96
    ally
    0.94
    voc
    0.91
    oder
    0.89
    ifer
    0.87
    learn
    0.85
    itive
    0.85
    Act Density 0.016%

    No Known Activations