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

    Neuronpedia

    INDEX
    Explanations

    historical figures

    oai_token-act-pair · gpt-3.5-turbo

    statements of identification or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶
    -0.67
     launches
    -0.63
     rollout
    -0.63
    boarding
    -0.63
    mates
    -0.62
    fires
    -0.62
     launch
    -0.61
    olutions
    -0.61
    urances
    -0.61
    fy
    -0.60
    POSITIVE LOGITS
     remembered
    1.28
     credited
    1.28
     believed
    1.07
     depicted
    1.04
     recounted
    1.02
     now
    1.00
     revered
    1.00
     regarded
    0.99
     commemor
    0.96
     pictured
    0.95
    Act Density 0.320%

    No Known Activations