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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions, requirements, or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases related to limitations or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAG
    -0.73
    aldo
    -0.71
    oola
    -0.70
    ouf
    -0.69
    temp
    -0.67
    ãģ®
    -0.67
    oka
    -0.66
     Potato
    -0.66
    irin
    -0.66
    mber
    -0.65
    POSITIVE LOGITS
     lawfully
    0.88
     warranted
    0.80
     deem
    0.80
     accordance
    0.79
     lawful
    0.78
     complying
    0.77
     obtaining
    0.77
     deemed
    0.76
     explicitly
    0.75
    withstanding
    0.75
    Act Density 0.446%

    No Known Activations