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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals, such as government officials and developers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, organizations, or authorities in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foreigners
    -0.59
    untarily
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.58
    owship
    -0.56
    ront
    -0.56
    odied
    -0.55
    req
    -0.55
    eatures
    -0.54
    bedroom
    -0.54
    pires
    -0.54
    POSITIVE LOGITS
     onwards
    0.76
     whereby
    0.68
     tho
    0.68
     regarding
    0.65
     insofar
    0.64
     ;)
    0.62
     who
    0.62
    ´
    0.62
    's
    0.61
    erity
    0.60
    Act Density 0.697%

    No Known Activations