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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "join."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ể
    -0.59
     McFarland
    -0.57
    neros
    -0.57
     Hess
    -0.57
     
    -0.56
     nouveaux
    -0.56
     nouveau
    -0.55
      
    -0.54
     grade
    -0.54
    maco
    -0.54
    POSITIVE LOGITS
     Jolie
    1.13
    makeConstraints
    1.06
     JOIN
    1.05
    JOIN
    1.03
    join
    1.02
     Joaquin
    1.00
    joins
    0.94
     Joints
    0.94
     Jodie
    0.91
     Joins
    0.90
    Act Density 0.007%

    No Known Activations