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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific connectors in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.16
    æį·
    -0.15
    fait
    -0.15
    اÙĨات
    -0.15
    egot
    -0.14
     Äijá»įc
    -0.14
    εÏĩ
    -0.14
    olet
    -0.14
    inate
    -0.14
    ãn
    -0.14
    POSITIVE LOGITS
    odo
    0.16
     Pend
    0.15
    ace
    0.15
    acea
    0.15
    cdecl
    0.14
    unto
    0.14
     bus
    0.14
     lead
    0.13
     squ
    0.13
     terminal
    0.13
    Act Density 0.002%

    No Known Activations