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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to operational modes or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?>
    -0.71
    ************
    -0.66
     fluorine
    -0.66
    ിച്ച
    -0.66
     Kear
    -0.63
    xss
    -0.63
     Bellas
    -0.63
    ']->
    -0.62
    fetch
    -0.62
     methyl
    -0.62
    POSITIVE LOGITS
     Mode
    1.77
    modes
    1.65
     MODE
    1.65
     Modes
    1.65
     mode
    1.64
     modes
    1.64
    mode
    1.62
    Mode
    1.54
    Modes
    1.53
    setMode
    1.47
    Act Density 0.075%

    No Known Activations