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

    Neuronpedia

    INDEX
    Explanations

    mentions or instances of specific legislative or regulatory actions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of regulations or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aples
    -0.83
    si
    -0.82
    \\\\\\\\
    -0.76
    vae
    -0.73
    oooooooooooooooo
    -0.73
    ciating
    -0.72
    ostic
    -0.71
    lique
    -0.70
    oj
    -0.69
    utm
    -0.68
    POSITIVE LOGITS
    arian
    0.85
    witz
    0.83
    terday
    0.83
    ters
    0.82
    arians
    0.81
    ment
    0.81
    MENTS
    0.80
     measures
    0.80
    ary
    0.79
    measures
    0.79
    Act Density 0.020%

    No Known Activations