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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or formulas

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

    Characters often preceding the letter "t"

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation involving t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tender
    -0.67
     Tran
    -0.66
     Tro
    -0.62
    Tri
    -0.60
     Tur
    -0.60
    EndInit
    -0.59
     Tem
    -0.59
     Tap
    -0.59
     Tal
    -0.59
     Tetra
    -0.58
    POSITIVE LOGITS
     t
    2.47
    t
    2.34
    ｔ
    1.30
    𝑡
    1.08
    𝐭
    0.97
     т
    0.95
    𝘁
    0.89
    𝒕
    0.87
    tA
    0.87
    𝙩
    0.83
    Act Density 0.808%

    No Known Activations