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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "act" in different forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sterili
    -0.54
     Patria
    -0.53
     kaynağından
    -0.53
    ่าง
    -0.53
    abetes
    -0.52
    betic
    -0.51
    <table>
    -0.50
     paradis
    -0.50
     grati
    -0.50
     rät
    -0.49
    POSITIVE LOGITS
     ACT
    0.89
     act
    0.75
     acts
    0.74
     Acts
    0.74
    ACT
    0.72
     Act
    0.72
     Actu
    0.68
     Acton
    0.67
    bootstrapcdn
    0.67
    act
    0.64
    Act Density 0.259%

    No Known Activations