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

    Neuronpedia

    INDEX
    Explanations

    words related to verification and confirmation processes

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

    phrases involving confirmation or verification actions, particularly in non-English languages.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     is
    -0.51
     L
    -0.51
    -
    -0.50
     has
    -0.49
    াঁ
    -0.49
     l
    -0.49
    sp
    -0.48
    đ
    -0.47
     sh
    -0.47
    sh
    -0.47
    POSITIVE LOGITS
     Wikimedijinoj
    1.06
     مرئيه
    1.03
    hyrchwyd
    0.99
     useContext
    0.97
     Theſe
    0.93
    fjspx
    0.93
    oodles
    0.92
    (!__
    0.91
     useHistory
    0.90
    Rüyada
    0.90
    Act Density 0.039%

    No Known Activations