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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "create" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     μην
    -0.79
     Pomona
    -0.71
    qos
    -0.71
     linf
    -0.69
     marins
    -0.69
     afge
    -0.66
     Pawn
    -0.64
     Strap
    -0.64
    mirante
    -0.64
    ersonic
    -0.63
    POSITIVE LOGITS
    Creates
    1.06
     Creates
    1.06
    creates
    1.05
     creations
    1.03
    creat
    1.00
     creat
    1.00
     Creators
    0.99
     creation
    0.98
     CREATE
    0.98
     Creation
    0.98
    Act Density 0.109%

    No Known Activations