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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications or details

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that signify various types of calls or commands, particularly in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     atmosp
    -0.71
     iTunes
    -0.70
     ammon
    -0.66
     bec
    -0.66
     Cannot
    -0.66
     SOFTWARE
    -0.64
     artif
    -0.63
     WhatsApp
    -0.63
     Invention
    -0.62
     SEE
    -0.62
    POSITIVE LOGITS
    rag
    1.19
    r
    1.13
    ron
    1.10
    rib
    1.08
    ra
    1.06
    RP
    1.06
    rab
    1.05
    rir
    1.04
    ray
    1.03
    rik
    1.02
    Act Density 0.289%

    No Known Activations