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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turned" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ente
    -0.19
    ajo
    -0.15
    ovÄĽ
    -0.14
    anik
    -0.14
    sap
    -0.14
    iteur
    -0.14
    unger
    -0.14
     FactoryGirl
    -0.14
    Ñĭп
    -0.14
    ioso
    -0.14
    POSITIVE LOGITS
     turn
    0.38
     turning
    0.38
     turned
    0.36
    turn
    0.36
     turns
    0.35
    -turn
    0.34
     Turn
    0.33
     TURN
    0.33
    Turn
    0.33
    .turn
    0.32
    Act Density 0.093%

    No Known Activations