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

    Neuronpedia

    INDEX
    Explanations

    French words that indicate items of clarification or question-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </i>
    -0.77
     "
    -0.70
     
    -0.69
    므로
    -0.68
     “
    -0.68
     (
    -0.67
     dan
    -0.65
     ‘
    -0.63
     '
    -0.62
    ,
    -0.62
    POSITIVE LOGITS
     Efq
    1.08
     doubtnut
    1.07
     Anſ
    1.05
    ſelves
    1.02
     للمعارف
    0.98
     itſelf
    0.98
     myſelf
    0.97
    expandindo
    0.97
     raiſ
    0.96
     avoient
    0.95
    Act Density 0.021%

    No Known Activations