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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attitudes or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "attitude."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.93
    ÄŁ
    -0.87
    icles
    -0.86
    icle
    -0.78
    oval
    -0.76
    idden
    -0.75
     Printed
    -0.71
    weet
    -0.71
    onga
    -0.70
    aneously
    -0.70
    POSITIVE LOGITS
     attitude
    1.23
     toward
    1.03
     towards
    0.99
     attitudes
    0.95
     indifference
    0.81
     Towards
    0.79
    uation
    0.74
     conformity
    0.73
     perv
    0.73
     disposition
    0.72
    Act Density 0.018%

    No Known Activations