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

    Neuronpedia

    INDEX
    Explanations

    the word "starting" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
     Réponses
    -0.75
     adeno
    -0.71
    ктан
    -0.71
    ulitis
    -0.68
     embolism
    -0.68
     Bevan
    -0.68
    hasMoreElements
    -0.68
    ertos
    -0.67
    mouseleave
    -0.67
    POSITIVE LOGITS
     starting
    2.42
     Starting
    2.40
    Starting
    2.37
    starting
    2.20
     STARTING
    2.15
    STARTING
    2.00
     Beginning
    1.49
    Beginning
    1.48
     beginning
    1.42
    beginning
    1.31
    Act Density 0.070%

    No Known Activations