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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of communication or transmission

    oai_token-act-pair · gpt-3.5-turbo

    references to methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.89
     unemploy
    -0.80
    aphael
    -0.69
     worshipped
    -0.66
    olor
    -0.61
     lasted
    -0.61
     characterized
    -0.61
     greets
    -0.61
    igue
    -0.61
     Indies
    -0.60
    POSITIVE LOGITS
     combination
    0.95
     prism
    0.93
     lens
    0.83
     backdoor
    0.82
     sheer
    0.79
    stand
    0.79
     vantage
    0.77
     means
    0.75
     proxy
    0.75
     standpoint
    0.75
    Act Density 0.340%

    No Known Activations