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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical expressions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instructions in technical or math text that direct the reader to compute or compare values (e.g., evaluate, calculate, determine which is greater, find a greatest common divisor)

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    ſelf
    -0.99
    ſelves
    -0.94
     increí
    -0.93
     ویکی‌پدی
    -0.89
     témoig
    -0.88
     queſta
    -0.88
     müſſen
    -0.86
     Verſ
    -0.85
    ロウィン
    -0.84
     estadounid
    -0.83
    POSITIVE LOGITS
    .
    0.38
     //
    0.38
    ed
    0.36
     (
    0.35
     B
    0.34
    pr
    0.33
     
    0.33
    1
    0.33
    inter
    0.33
    ↵↵
    0.33
    Act Density 0.188%

    No Known Activations