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

    Neuronpedia

    INDEX
    Explanations

    instances of people speaking to others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" and its relevance in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.82
     signatures
    -0.81
    casts
    -0.77
    evidence
    -0.77
     indexes
    -0.73
    orders
    -0.73
    coins
    -0.72
    etsk
    -0.72
    grounds
    -0.71
     impacts
    -0.71
    POSITIVE LOGITS
     handful
    1.03
     colleague
    1.03
    rouse
    1.01
     woman
    1.01
     fellow
    0.99
     bunch
    0.98
     dozen
    0.96
     classmate
    0.95
     friend
    0.92
     couple
    0.89
    Act Density 0.292%

    No Known Activations