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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making a decisive or final action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "pulling the plug" on various situations or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.81
    nown
    -0.81
    nces
    -0.80
    arcity
    -0.73
    urdue
    -0.70
    ukemia
    -0.70
    chance
    -0.69
    lished
    -0.68
    hof
    -0.68
    umbered
    -0.67
    POSITIVE LOGITS
     levers
    1.06
     curtain
    1.04
     punches
    1.04
     strings
    0.94
     wagon
    0.88
     stool
    0.88
     curtains
    0.87
     lever
    0.86
     trigger
    0.84
     drawer
    0.83
    Act Density 0.096%

    No Known Activations