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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Daniel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    packing
    -0.73
    sites
    -0.72
     actionGroup
    -0.70
    roxy
    -0.67
    STER
    -0.67
    minded
    -0.64
    sylv
    -0.64
    recy
    -0.64
    othal
    -0.63
    around
    -0.62
    POSITIVE LOGITS
     Boone
    1.02
     Corm
    0.96
     Webster
    0.93
     Frie
    0.92
     Patrick
    0.90
     Bryan
    0.87
     Kahn
    0.86
     Handler
    0.83
     Hann
    0.83
    ity
    0.83
    Act Density 0.030%

    No Known Activations