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

    Neuronpedia

    INDEX
    Explanations

    terms related to different modes or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to various operational modes or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.86
    mony
    -0.86
    owan
    -0.83
    iannopoulos
    -0.75
    areth
    -0.74
    bones
    -0.73
    istani
    -0.72
    roma
    -0.72
    ingly
    -0.71
    bone
    -0.69
    POSITIVE LOGITS
     selector
    0.83
    etting
    0.75
     parity
    0.73
     upgr
    0.72
     enabled
    0.71
     Shift
    0.67
     mode
    0.66
     activated
    0.66
     modes
    0.65
    ounce
    0.64
    Act Density 0.039%

    No Known Activations