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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Thomas" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     digitais
    -0.62
     verrou
    -0.62
     águas
    -0.58
    Độ
    -0.56
     enfans
    -0.56
     entanto
    -0.56
     préc
    -0.55
     glisser
    -0.54
    WriteByte
    -0.54
    <!--[
    -0.54
    POSITIVE LOGITS
     reduced
    1.25
     Reduced
    1.24
     reducing
    1.18
     reduction
    1.18
    reduced
    1.14
     REDUC
    1.14
     Reduction
    1.12
     reduce
    1.11
     Reducing
    1.09
    Reduced
    1.08
    Act Density 0.066%

    No Known Activations