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

    Neuronpedia

    INDEX
    Explanations

    keywords related to geographical locations and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and entities, particularly related to New Zealand and California

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clinical
    -0.76
    regnancy
    -0.71
    hesda
    -0.70
    ocese
    -0.69
    rador
    -0.68
    nsic
    -0.68
    orting
    -0.68
    ordered
    -0.68
    unction
    -0.68
    ordering
    -0.67
    POSITIVE LOGITS
     Kiw
    1.07
    igans
    0.89
     Hots
    0.79
    icol
    0.74
     Garc
    0.74
    lar
    0.72
    wings
    0.72
    itar
    0.71
     Californ
    0.71
     Swarm
    0.71
    Act Density 0.015%

    No Known Activations