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

    Neuronpedia

    INDEX
    Explanations

    references to the original source or publication of an article

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the publication history of articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    respective
    -0.84
     preferably
    -0.81
    ĪĴ
    -0.79
    ichever
    -0.76
     nonetheless
    -0.75
     invariably
    -0.70
     thence
    -0.66
     constantly
    -0.65
     whichever
    -0.65
     hurry
    -0.64
    POSITIVE LOGITS
    ËĪ
    0.65
     Publication
    0.65
     October
    0.61
    INGTON
    0.59
     Kad
    0.59
     August
    0.59
     February
    0.59
     Ocean
    0.59
     March
    0.59
     online
    0.58
    Act Density 0.117%

    No Known Activations