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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or processes requiring specific steps or procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Born
    -0.69
    çīĪ
    -0.68
    mare
    -0.68
     Originally
    -0.66
     awoken
    -0.65
    Come
    -0.65
    >]
    -0.63
    女
    -0.62
    natureconservancy
    -0.61
    ouf
    -0.59
    POSITIVE LOGITS
    geries
    1.18
     reuse
    1.09
    gery
    1.06
     purposes
    1.02
     sale
    1.00
     inclusion
    0.92
     further
    0.90
     processing
    0.89
     retrieval
    0.89
     verification
    0.89
    Act Density 0.208%

    No Known Activations