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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turn" and its variations, indicating a focus on turning or transitions

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

    turn over, turn to, turn out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Säure
    -0.36
    agu
    -0.36
     frumo
    -0.35
    postId
    -0.35
    afa
    -0.34
    GroupID
    -0.34
     Babcock
    -0.34
     Espinoza
    -0.34
    árol
    -0.33
    doPost
    -0.32
    POSITIVE LOGITS
     turned
    1.08
     Turn
    1.05
     Turned
    1.03
    TURN
    1.03
    turn
    1.02
    Turn
    1.01
    Turned
    1.00
    turned
    1.00
     TURN
    0.95
     turning
    0.94
    Act Density 0.011%

    No Known Activations