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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal concepts and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HOWEVER
    -0.22
     Doch
    -0.17
     Yet
    -0.17
    Yet
    -0.17
     elsewhere
    -0.15
    tery
    -0.15
    ãĢĤãģĹãģĭãģĹ
    -0.14
     terra
    -0.14
    Nevertheless
    -0.14
    xin
    -0.14
    POSITIVE LOGITS
     sondern
    0.41
     sino
    0.40
     بÙĦÚ©Ùĩ
    0.38
     nor
    0.28
     but
    0.24
     anymore
    0.22
     बल
    0.21
     Nor
    0.18
    also
    0.18
     mÃł
    0.18
    Act Density 0.082%

    No Known Activations