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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the end or beginning of a message or note

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to directives or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Closed
    -0.62
     assass
    -0.61
     blight
    -0.61
     squats
    -0.59
     bombings
    -0.59
     blasphemy
    -0.58
     things
    -0.57
     deeds
    -0.57
     eviction
    -0.57
     poaching
    -0.56
    POSITIVE LOGITS
     consumers
    1.14
     shareholders
    1.07
     listeners
    1.02
     clinicians
    0.99
     taxpayers
    0.98
     policymakers
    0.97
     readers
    0.95
     stakeholders
    0.94
     investors
    0.94
    payers
    0.92
    Act Density 0.741%

    No Known Activations