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

    Neuronpedia

    INDEX
    Explanations

    phrases related to names and titles

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hub
    -0.67
     Grind
    -0.65
    ggle
    -0.62
     booze
    -0.61
    chuk
    -0.60
     Barbar
    -0.56
     shoppers
    -0.56
     plenty
    -0.54
     bush
    -0.54
     motorists
    -0.54
    POSITIVE LOGITS
     :=
    0.95
     );
    0.82
     ),
    0.80
     (),
    0.80
     ):
    0.79
    channelAvailability
    0.78
    Offline
    0.77
    ,,,,,,,,
    0.76
    )--
    0.75
     )]
    0.75
    Act Density 0.234%

    No Known Activations