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

    Neuronpedia

    INDEX
    Explanations

    words related to compliance and oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deportivos
    -0.64
     ilman
    -0.63
     Mercure
    -0.62
    AddressBook
    -0.60
    adl
    -0.59
    Composable
    -0.59
     Langford
    -0.58
     Rashford
    -0.58
     erythrocytes
    -0.58
     nomme
    -0.58
    POSITIVE LOGITS
    %")
    1.02
     out
    0.98
    abestanden
    0.95
     up
    0.94
    @@@@@@@@
    0.90
     }}"></
    0.84
     {}'.
    0.81
    $}}
    0.80
    )$_
    0.79
     Matth
    0.78
    Act Density 0.499%

    No Known Activations