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

    Neuronpedia

    INDEX
    Explanations

    places, countries or institutions that have emerged, known, or recognized for certain characteristics, developments, or statuses

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating emergence or recognition of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Posts
    -0.63
    unn
    -0.62
    iannopoulos
    -0.60
    roups
    -0.60
    ults
    -0.59
    intend
    -0.59
    ison
    -0.59
     motions
    -0.57
    ires
    -0.57
    views
    -0.57
    POSITIVE LOGITS
     one
    1.00
     synonymous
    0.93
     an
    0.91
     a
    0.88
     pioneer
    0.86
     birthplace
    0.85
     America
    0.84
     Britain
    0.82
     arguably
    0.81
    pires
    0.81
    Act Density 0.184%

    No Known Activations