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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official institutions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to social structures and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ðŁ
    -0.75
    âĢ
    -0.73
     âĢ
    -0.72
     ®
    -0.70
     ðŁij
    -0.68
     âľ
    -0.67
    âľ
    -0.64
     âĻ
    -0.60
     ðŁĺ
    -0.59
    âĺ
    -0.59
    POSITIVE LOGITS
     occasions
    0.93
    vironments
    0.89
     meetings
    0.88
    goers
    0.87
     sessions
    0.86
     gatherings
    0.85
     events
    0.83
     guests
    0.81
     rooms
    0.81
     scenes
    0.80
    Act Density 1.171%

    No Known Activations