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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dataSnapshot
    -0.63
     ${\
    -0.59
     Hartley
    -0.58
    rangea
    -0.58
     Teres
    -0.58
    centerX
    -0.57
    ${\
    -0.57
     Moreno
    -0.56
    Hinweise
    -0.55
     Rowley
    -0.55
    POSITIVE LOGITS
     opposed
    1.68
    opposed
    1.25
     oppose
    0.95
     opposes
    0.90
     HttpNotFound
    0.78
    TestingModule
    0.70
    XmlAccessorType
    0.69
    ORGE
    0.67
    yntaxException
    0.67
     oppos
    0.65
    Act Density 0.109%

    No Known Activations