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

    Neuronpedia

    INDEX
    Explanations

    references to private settings or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to private entities or private information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.84
    xual
    -0.81
    Dispatch
    -0.78
    obo
    -0.77
     GOODMAN
    -0.76
    orsi
    -0.72
    Frames
    -0.70
    DAY
    -0.70
    GGGG
    -0.69
    ï¸
    -0.69
    POSITIVE LOGITS
     sector
    1.04
     equity
    0.92
    sector
    0.87
     jets
    0.82
    ised
    0.81
     private
    0.80
     affairs
    0.80
     rented
    0.76
     ownership
    0.75
     residences
    0.73
    Act Density 0.022%

    No Known Activations