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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases and relationships between subjects and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     idéia
    -0.56
     existência
    -0.52
     économies
    -0.51
     ilman
    -0.49
     että
    -0.49
     obstante
    -0.49
    </caption>
    -0.48
    vedades
    -0.47
     }^{(
    -0.46
     rezerv
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.76
    endphp
    0.75
     Mentre
    0.71
    Diwedd
    0.69
     Paglinawan
    0.69
     progresses
    0.68
    ToMove
    0.68
     patr
    0.68
    Exeunt
    0.67
     prepares
    0.66
    Act Density 0.151%

    No Known Activations