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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal references

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blat
    -0.69
     dwell
    -0.66
     Rebell
    -0.65
    oir
    -0.64
     wander
    -0.64
     untold
    -0.63
     NEVER
    -0.61
    ggles
    -0.59
     drown
    -0.59
    hide
    -0.59
    POSITIVE LOGITS
     unanimously
    0.98
     authorizing
    0.90
     appointing
    0.80
     accord
    0.80
     approving
    0.79
     decree
    0.78
     pledging
    0.78
     outlining
    0.77
    PDF
    0.75
    displayText
    0.73
    Act Density 0.249%

    No Known Activations