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

    Neuronpedia

    INDEX
    Explanations

    different modes or states described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '){
    -0.70
    ?>
    -0.68
     LoggerFactory
    -0.67
     {}\
    -0.64
    ')){
    -0.63
    '],
    -0.63
    сылкі
    -0.63
    ************
    -0.62
     ""){
    -0.62
    ’”
    -0.62
    POSITIVE LOGITS
     Mode
    3.39
     mode
    3.33
    mode
    3.25
    Mode
    3.19
     MODE
    3.06
     modes
    2.93
    MODE
    2.81
     Modes
    2.79
    modes
    2.74
    Modes
    2.60
    Act Density 0.051%

    No Known Activations