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

    Neuronpedia

    INDEX
    Explanations

    actions related to signing documents and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deniz
    -0.51
    3
    -0.50
     przechowy
    -0.48
    期刊论文
    -0.48
    Халык
    -0.47
     энциклопедия
    -0.47
     Campbell
    -0.47
    CppMethod
    -0.47
    velli
    -0.46
    hamel
    -0.46
    POSITIVE LOGITS
     Sign
    1.06
    Sign
    0.99
     Signing
    0.96
     sign
    0.96
    Signing
    0.91
     SIGN
    0.90
     signing
    0.86
    SIGN
    0.85
    sign
    0.84
    Signs
    0.84
    Act Density 0.099%

    No Known Activations