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

    Neuronpedia

    INDEX
    Explanations

    mentions of languages and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to languages and geographical regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dispatch
    -0.62
    gently
    -0.61
    blocking
    -0.61
    911
    -0.59
    livion
    -0.58
    onew
    -0.57
    abuse
    -0.56
    oward
    -0.55
    posal
    -0.55
    dding
    -0.54
    POSITIVE LOGITS
     oldest
    0.69
     descendant
    0.68
     hybrids
    0.66
     birthplace
    0.65
     descendants
    0.64
    aceae
    0.63
     subdiv
    0.63
     tert
    0.60
     geographically
    0.60
     belongs
    0.60
    Act Density 1.887%

    No Known Activations