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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assistance or helpfulness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ‘’
    -0.73
    ”
    -0.70
     ‘’
    -0.61
    …………………………………………
    -0.59
      
    -0.58
    ’’
    -0.57
     ”
    -0.56
     ‘
    -0.56
    useEffect
    -0.54
    ,,
    -0.54
    POSITIVE LOGITS
    Искәрмәләр
    0.89
     doubtnut
    0.84
    ].)
    0.84
    FWIW
    0.83
     ་་
    0.83
     Paglinawan
    0.83
     heh
    0.82
    eabouts
    0.81
     ―――――
    0.81
     coö
    0.80
    Act Density 0.352%

    No Known Activations