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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and competition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to power dynamics and gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.72
    atl
    -0.69
     pigeon
    -0.68
     Mock
    -0.67
    bats
    -0.66
    ippi
    -0.66
     Photographer
    -0.65
    é¾įå
    -0.65
    çīĪ
    -0.65
     Nationwide
    -0.65
    POSITIVE LOGITS
     levers
    0.89
     ignition
    0.81
     amplification
    0.81
     propulsion
    0.80
     acceleration
    0.80
     superpower
    0.75
     amplifier
    0.74
    ierrez
    0.73
     wielded
    0.72
     pedals
    0.72
    Act Density 0.442%

    No Known Activations