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

    Neuronpedia

    INDEX
    Explanations

    references to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.80
    addGap
    -0.75
     numberOfRows
    -0.70
     оригіналу
    -0.66
    volves
    -0.66
     Sélectionnez
    -0.66
     entail
    -0.65
     entails
    -0.63
     '\\;'
    -0.62
    )}_
    -0.61
    POSITIVE LOGITS
     who
    1.55
    who
    1.09
     knows
    0.91
     whom
    0.91
     knew
    0.87
     want
    0.83
    Who
    0.83
     understands
    0.82
     wants
    0.81
     Who
    0.81
    Act Density 0.635%

    No Known Activations