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

    Neuronpedia

    INDEX
    Explanations

    commands related to technology or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to voice commands and interactions with devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fiat
    -0.67
    utm
    -0.66
     Democr
    -0.66
     Wheat
    -0.65
    bid
    -0.65
    Rat
    -0.64
     Lot
    -0.63
    Nit
    -0.63
    Otherwise
    -0.63
     CFR
    -0.62
    POSITIVE LOGITS
     commands
    1.47
     command
    1.05
     Commands
    1.04
     commanded
    1.00
    eering
    0.99
    command
    0.95
    ngth
    0.82
     prompt
    0.79
    uits
    0.78
     commanding
    0.78
    Act Density 0.006%

    No Known Activations