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

    Neuronpedia

    INDEX
    Explanations

    sections of code or method declarations in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused52>
    -1.07
    <unused41>
    -1.07
    <unused23>
    -1.07
    <unused28>
    -1.07
    <unused8>
    -1.07
    [@BOS@]
    -1.07
    <unused14>
    -1.07
    <unused16>
    -1.07
    <unused68>
    -1.07
    <unused74>
    -1.07
    POSITIVE LOGITS
     hubungan
    0.19
     obligaciones
    0.18
     Edad
    0.18
     respectivas
    0.18
     Namens
    0.17
                
    0.17
     partenaire
    0.17
     entran
    0.17
     duração
    0.16
     respective
    0.16
    Act Density 0.002%

    No Known Activations