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

    Neuronpedia

    INDEX
    Explanations

    colons used to introduce lists or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cabul
    -0.81
    vailability
    -0.65
    HasForeignKey
    -0.63
    mies
    -0.62
    (.*
    -0.59
    imbawa
    -0.59
     Chwiliwch
    -0.58
     squ
    -0.58
    vací
    -0.57
     deb
    -0.57
    POSITIVE LOGITS
    :
    1.63
    .:
    1.55
    _:
    1.52
    *:
    1.46
    +:
    1.46
    ®:
    1.45
    !:
    1.44
    ：
    1.44
    %:
    1.43
    ✨:
    1.41
    Act Density 0.725%

    No Known Activations