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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant events or accomplishments related to legislation or policy-making

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     prefers
    -0.79
     fishes
    -0.78
     liking
    -0.76
    ahs
    -0.72
     toilets
    -0.70
     searched
    -0.68
     contracted
    -0.68
     perished
    -0.67
     motions
    -0.66
     consulted
    -0.65
    POSITIVE LOGITS
     culmination
    1.11
     sympt
    0.97
     testament
    0.97
     reminder
    0.90
     confirmation
    0.89
     unprecedented
    0.88
     precedent
    0.87
     emblem
    0.85
     vind
    0.85
     acknowledgment
    0.82
    Act Density 3.898%

    No Known Activations