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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or unexpected findings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating persistence despite adversity or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.88
    Topic
    -0.70
    Marg
    -0.69
    onement
    -0.68
    window
    -0.67
    Reviewer
    -0.67
    isu
    -0.67
    bye
    -0.66
    Topics
    -0.66
    ONSORED
    -0.66
    POSITIVE LOGITS
     setbacks
    0.82
     warnings
    0.81
     fact
    0.78
     advances
    0.78
     setback
    0.78
     efforts
    0.77
     limitations
    0.76
     slight
    0.75
     lack
    0.75
     objections
    0.74
    Act Density 0.139%

    No Known Activations