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

    Neuronpedia

    INDEX
    Explanations

    keywords related to publishing and sharing information, such as "posted" or "introduced."

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions taken or decisions made in an official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sierra
    -0.66
    istries
    -0.66
    oro
    -0.63
    Fit
    -0.61
     edge
    -0.60
    mare
    -0.60
     stripes
    -0.60
     relationships
    -0.59
     mutants
    -0.59
    enance
    -0.59
    POSITIVE LOGITS
     unanimously
    0.93
     aback
    0.83
     by
    0.79
    terday
    0.73
     exting
    0.72
     yesterday
    0.71
     psychiat
    0.71
     Borough
    0.67
     beforehand
    0.66
     earlier
    0.65
    Act Density 0.315%

    No Known Activations