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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "As you can see" or similar expressions are used

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate observation or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.70
    kefeller
    -0.69
    idity
    -0.67
    enders
    -0.62
    idal
    -0.62
    lling
    -0.61
    lled
    -0.61
    mens
    -0.61
    inki
    -0.60
    rang
    -0.59
    POSITIVE LOGITS
    ,
    0.88
     (),
    0.82
    .,
    0.74
    ,.
    0.73
    ,,
    0.73
    ,-
    0.71
     by
    0.70
    ,,,,
    0.65
    é¾įåĸļ士
    0.65
    (),
    0.65
    Act Density 0.056%

    No Known Activations