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

    Neuronpedia

    INDEX
    Explanations

    individuals based on specific criteria such as homeownership, occupations, or citizenships

    oai_token-act-pair · gpt-3.5-turbo

    phrases and clauses that reference individuals or groups defined by the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anyway
    -0.71
    Magikarp
    -0.69
     Grip
    -0.67
    "]=>
    -0.65
     Bound
    -0.65
    interstitial
    -0.64
     Watching
    -0.64
     Camer
    -0.63
    Translation
    -0.62
     Bullet
    -0.61
    POSITIVE LOGITS
     violate
    1.20
     exceed
    1.17
     qualify
    1.14
     undergo
    1.09
     underwent
    1.03
     comply
    1.02
     exceeded
    1.00
     aren
    0.98
     wish
    0.98
     intend
    0.97
    Act Density 0.128%

    No Known Activations