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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ðŀдна
    -0.15
     ÑģооÑĤвеÑĤ
    -0.15
     ÄIJó
    -0.15
    Ãłng
    -0.14
    emos
    -0.14
    -BEGIN
    -0.14
    ále
    -0.14
    abi
    -0.14
    âng
    -0.14
     zum
    -0.13
    POSITIVE LOGITS
     Ide
    0.17
     Inspir
    0.17
     Exist
    0.17
     célib
    0.17
     Us
    0.17
     Ve
    0.16
     Habit
    0.16
     Moment
    0.16
     Prostitutas
    0.16
     Pos
    0.16
    Act Density 0.044%

    No Known Activations