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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FunctionFlags
    -0.62
     ब्रेकडाउन
    -0.54
    /**
    -0.54
     mergeFrom
    -0.50
     MainAxisSize
    -0.47
    Населення
    -0.47
    statechange
    -0.46
    最快更新
    -0.46
    adaptiveStyles
    -0.46
     entanto
    -0.46
    POSITIVE LOGITS
     even
    0.68
     siquiera
    0.61
    even
    0.59
     навіть
    0.57
     EVEN
    0.55
    Even
    0.53
     даже
    0.52
     barely
    0.50
    EVEN
    0.50
     Even
    0.49
    Act Density 0.219%

    No Known Activations