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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly locations such as cities in news articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically opening parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     expire
    -0.69
     treats
    -0.64
     discrim
    -0.64
     hops
    -0.64
     registry
    -0.63
     elect
    -0.62
     macros
    -0.62
     majesty
    -0.62
     multiplication
    -0.61
     retard
    -0.61
    POSITIVE LOGITS
    Reuters
    1.25
    Thom
    1.08
    CBS
    0.98
    AFP
    0.96
    CNN
    0.95
    emphasis
    0.93
    via
    0.92
    credit
    0.92
    formerly
    0.91
    CN
    0.87
    Act Density 0.045%

    No Known Activations