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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases with a high level of contrast or comparison in socioeconomic contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of the article "a" followed by descriptors or nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agents
    -0.78
    Attempts
    -0.72
    achu
    -0.69
    agree
    -0.69
    words
    -0.68
    Ac
    -0.68
    Own
    -0.68
    evidence
    -0.67
    Ord
    -0.67
     Mysteries
    -0.65
    POSITIVE LOGITS
     handful
    1.23
     bunch
    1.14
     consequ
    1.09
     lot
    1.08
    cknowled
    1.07
     slew
    1.04
     plethora
    1.01
     few
    1.01
    rouse
    1.00
     couple
    1.00
    Act Density 0.194%

    No Known Activations