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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social structures and relationships

    oai_token-act-pair · gpt-3.5-turbo

    instances of betrayal and loyalty in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.59
     Pwr
    -0.55
    asus
    -0.54
     Eater
    -0.53
     WARN
    -0.50
     Burke
    -0.49
    WARE
    -0.48
    apter
    -0.48
     Fault
    -0.48
     Timeline
    -0.47
    POSITIVE LOGITS
     etc
    0.79
    etc
    0.75
     respectively
    0.70
    âĢ¦)
    0.60
     pregn
    0.59
    vil
    0.58
     latter
    0.56
    ald
    0.56
     scissors
    0.54
    foundland
    0.54
    Act Density 0.481%

    No Known Activations