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

    Neuronpedia

    INDEX
    Explanations

    text related to legal proceedings and court events

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     semblance
    -0.72
     shroud
    -0.71
     fragmentation
    -0.69
     mosqu
    -0.67
     classification
    -0.63
     shelf
    -0.62
     Panc
    -0.62
     mole
    -0.61
     proportional
    -0.61
     charm
    -0.61
    POSITIVE LOGITS
    sure
    1.04
    ł
    1.01
    ¹
    0.98
    there
    0.97
    then
    0.95
    especially
    0.93
    ª
    0.92
    perhaps
    0.89
    why
    0.89
    QB
    0.87
    Act Density 0.122%

    No Known Activations