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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain temporal indicators and conjunctions indicating conditions or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;
    -0.48
    :
    -0.47
     app
    -0.44
    。
    -0.42
     Mazar
    -0.42
     fleur
    -0.42
    ServletConfig
    -0.42
    ।
    -0.39
     diyor
    -0.39
    ::
    -0.38
    POSITIVE LOGITS
     ddelweddau
    1.04
     متعلقه
    1.04
    ंदीखरीदारी
    0.91
    HideFlags
    0.90
     étant
    0.87
    ieważ
    0.85
     NSCoder
    0.82
     essendo
    0.82
    ագրություններ
    0.82
     jsPsych
    0.81
    Act Density 0.278%

    No Known Activations