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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "communicate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.65
     :
    -0.61
    complexContent
    -0.60
    unmodifiable
    -0.60
     opérés
    -0.60
    awia
    -0.57
     GenerationType
    -0.56
    makeText
    -0.56
    jsxFileName
    -0.56
     Affiliation
    -0.56
    POSITIVE LOGITS
     councils
    1.04
     council
    1.00
     Councils
    0.91
     communicate
    0.89
     Communicating
    0.87
     COUNCIL
    0.84
     communicating
    0.84
    council
    0.83
     Council
    0.82
     Communicate
    0.81
    Act Density 0.086%

    No Known Activations