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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untura
    -0.49
    intree
    -0.47
    phemy
    -0.46
    Bentley
    -0.45
     presto
    -0.45
    orithmic
    -0.43
    στό
    -0.43
    Avril
    -0.42
     transnational
    -0.41
    rancy
    -0.41
    POSITIVE LOGITS
    ########.
    0.87
    rungsseite
    0.76
    XmlAccessorType
    0.75
    transQ
    0.75
    ConstraintMaker
    0.74
     noDo
    0.74
    Gön
    0.73
     ویکی‌پدیای
    0.72
    Personensuche
    0.72
    IndentedString
    0.71
    Act Density 0.037%

    No Known Activations