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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and monetary values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moody
    -0.71
     produ
    -0.67
     Goldstein
    -0.66
     Dunk
    -0.65
     Sed
    -0.65
     Gors
    -0.65
     Amber
    -0.64
     assum
    -0.64
     Wolfe
    -0.63
     Bri
    -0.63
    POSITIVE LOGITS
    HOME
    1.14
    GOP
    1.07
    true
    1.06
    false
    1.04
    this
    0.99
    _.
    0.98
    True
    0.97
    EDIT
    0.91
    tw
    0.90
    tm
    0.89
    Act Density 0.019%

    No Known Activations