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

    Neuronpedia

    INDEX
    Explanations

    references to private entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to private entities or private matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.80
    amaz
    -0.79
    wolves
    -0.78
    ————————
    -0.71
    tto
    -0.69
    aukee
    -0.67
    andise
    -0.67
    ostic
    -0.67
    orsi
    -0.66
    awa
    -0.65
    POSITIVE LOGITS
     sector
    1.26
     equity
    1.02
    sector
    0.96
     Sector
    0.89
     residences
    0.88
     jets
    0.88
     investigator
    0.85
     rented
    0.77
     sectors
    0.77
     affairs
    0.77
    Act Density 0.036%

    No Known Activations