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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparative decrease or lower frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.84
    bingen
    -0.80
    endphp
    -0.79
    arnia
    -0.76
    extAlignment
    -0.74
     BoxDecoration
    -0.74
    httphttps
    -0.72
    туга
    -0.70
     الحره
    -0.69
     FileWriter
    -0.69
    POSITIVE LOGITS
     less
    2.19
     Less
    2.04
    Less
    2.02
     LESS
    1.95
    less
    1.70
     moins
    1.53
    LESS
    1.49
     menos
    1.48
     leſs
    1.43
     weniger
    1.39
    Act Density 0.099%

    No Known Activations