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 changes or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %)$
    -0.79
     Majefty
    -0.78
    essentiel
    -0.77
     femininas
    -0.76
     essenziale
    -0.75
     weihnachten
    -0.75
     GMA
    -0.75
    DotNetBar
    -0.75
    벤트
    -0.74
     صوتيه
    -0.74
    POSITIVE LOGITS
     TURN
    1.53
     turn
    1.45
     Turn
    1.45
    TURN
    1.37
    Turn
    1.36
     turns
    1.35
     turned
    1.33
     Turns
    1.27
    Turns
    1.27
     turning
    1.24
    Act Density 0.047%

    No Known Activations