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

    Neuronpedia

    INDEX
    Explanations

    negations and contractions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ')}}"
    -0.63
    "%(
    -0.59
    ')):
    -0.59
     ]]
    -0.59
     '*')
    -0.58
    __':
    -0.56
     som
    -0.55
     $,
    -0.55
     }}</
    -0.54
    <?=$
    -0.54
    POSITIVE LOGITS
     незавершена
    0.88
     estekak
    0.81
    Personensuche
    0.80
     المعيارى
    0.71
    UnknownFieldSet
    0.71
     <=",
    0.70
     ujednoznacz
    0.69
     myſelf
    0.68
    GEBURTSDATUM
    0.68
     ModelExpression
    0.67
    Act Density 0.204%

    No Known Activations