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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "activity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.42
    The
    -0.40
    enumi
    -0.39
    Pur
    -0.38
    <bos>
    -0.38
    <>
    -0.38
    ならない
    -0.37
    なければならない
    -0.37
     Gründen
    -0.37
    concaten
    -0.37
    POSITIVE LOGITS
     reactivity
    0.71
    ivity
    0.71
    ativity
    0.70
    Reactivity
    0.69
     Reactivity
    0.69
     inactivity
    0.67
    tivity
    0.66
     ACTIVITY
    0.65
     activity
    0.64
     radioactivity
    0.63
    Act Density 0.018%

    No Known Activations