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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and associated actions or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     capitals
    -0.83
     organis
    -0.76
    âĹ¼
    -0.75
    cffff
    -0.75
    CONCLUS
    -0.73
     analys
    -0.73
     challeng
    -0.71
     eluc
    -0.71
     pse
    -0.71
     forecasting
    -0.70
    POSITIVE LOGITS
     Doe
    1.30
     Ramirez
    1.13
     Hernandez
    1.13
     Gonzalez
    1.12
     Bundy
    1.10
     Lopez
    1.09
     Paddock
    1.08
     Rodriguez
    1.08
     Zimmerman
    1.07
     Martinez
    1.06
    Act Density 0.214%

    No Known Activations