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

    Neuronpedia

    INDEX
    Explanations

    strings and patterns related to whitespace and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acher
    -0.16
    969
    -0.16
    Ñĥки
    -0.16
    ufe
    -0.15
    urum
    -0.15
    merce
    -0.15
    merc
    -0.14
    HEME
    -0.14
    éĴ
    -0.14
     phys
    -0.14
    POSITIVE LOGITS
    Ranges
    0.15
    YY
    0.14
     surroundings
    0.14
    ä¸Ī
    0.14
    0.14
     Correct
    0.13
    ona
    0.13
    unkt
    0.13
    vely
    0.13
    Tracks
    0.13
    Act Density 0.024%

    No Known Activations