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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation related to variables and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tom
    -0.28
     tar
    -0.25
     te
    -0.23
     tro
    -0.22
     tor
    -0.21
    /t
    -0.21
     tomb
    -0.20
     trom
    -0.20
     toll
    -0.20
    åı°
    -0.20
    POSITIVE LOGITS
    -T
    0.42
    _T
    0.41
    ÂłÐ¢
    0.40
    ÂłT
    0.39
    Т
    0.38
    	T
    0.36
    [T
    0.35
     à¤Ł
    0.35
    ,T
    0.35
    (T
    0.34
    Act Density 0.166%

    No Known Activations