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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turn" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    illerato
    -0.42
    Organisateur
    -0.42
    Lik
    -0.40
    şiv
    -0.40
    contexts
    -0.40
     createContext
    -0.39
    ronpa
    -0.39
    gow
    -0.38
     AnyObject
    -0.38
    不清
    -0.38
    POSITIVE LOGITS
     Turn
    1.41
     turn
    1.38
     turned
    1.35
    Turn
    1.34
     turning
    1.34
     Turned
    1.34
    Turned
    1.34
     TURN
    1.32
     Turning
    1.31
    turn
    1.30
    Act Density 0.048%

    No Known Activations