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

    Neuronpedia

    INDEX
    Explanations

    instances where something or someone is considered superior or exempt from rules or standards

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "above" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Introduced
    -0.74
     Instruments
    -0.67
    DAY
    -0.67
    dll
    -0.66
    rol
    -0.65
    Access
    -0.64
    ãĤ¹ãĥĪ
    -0.63
    Express
    -0.63
    20439
    -0.63
    Mail
    -0.63
    POSITIVE LOGITS
    ground
    1.03
    perty
    0.97
    mentioned
    0.80
     grade
    0.74
    yp
    0.72
    uckland
    0.71
    aucus
    0.70
     infinity
    0.69
    hand
    0.68
    lihood
    0.68
    Act Density 0.020%

    No Known Activations