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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future intentions or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     đã
    -0.54
    はじめに
    -0.52
     bislang
    -0.51
     umumnya
    -0.49
    дель
    -0.49
    tometer
    -0.49
    vermectin
    -0.47
    anthrene
    -0.47
    <bos>
    -0.47
    PropertyGroup
    -0.46
    POSITIVE LOGITS
    IndentedString
    0.78
     soon
    0.76
    GEBURTSDATUM
    0.76
     propOrder
    0.72
    soon
    0.70
     eventually
    0.69
     someday
    0.69
    featureID
    0.68
    Eventually
    0.68
     inevitably
    0.67
    Act Density 0.195%

    No Known Activations