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

    Neuronpedia

    INDEX
    Explanations

    instances where something is replaced or done differently than expected

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrast or an alternative perspective being introduced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emate
    -0.62
    andestine
    -0.62
    oran
    -0.58
    eria
    -0.57
     Flavoring
    -0.56
     Nev
    -0.56
    AG
    -0.56
     Calif
    -0.55
     Wash
    -0.55
    nce
    -0.55
    POSITIVE LOGITS
    Ļ½
    0.74
    ":"/
    0.71
    roman
    0.69
     opt
    0.68
     succumb
    0.67
     relied
    0.66
     chose
    0.65
     opting
    0.65
    ocus
    0.64
    «ĺ
    0.63
    Act Density 0.019%

    No Known Activations