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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as places and names involved in incidents or crimes

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and verbs related to a specific individual in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Watching
    -0.80
     disadvant
    -0.68
     Dominion
    -0.62
    Higher
    -0.59
     Gors
    -0.59
     Definitions
    -0.59
     Millenn
    -0.58
     Cities
    -0.57
     SEO
    -0.57
    Insert
    -0.57
    POSITIVE LOGITS
     underwent
    1.38
     remained
    1.15
     fled
    1.14
     was
    1.13
     surrendered
    1.10
     reportedly
    1.09
    'd
    1.08
     escaped
    1.07
     pleaded
    1.07
     suffered
    1.06
    Act Density 0.256%

    No Known Activations