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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive pronouns followed by a form of 'have.'

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their relationships with groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.67
     fault
    -0.61
     havoc
    -0.60
    Minor
    -0.59
     spoilers
    -0.58
    oys
    -0.57
    irection
    -0.57
     Mayhem
    -0.56
    blogspot
    -0.56
    odox
    -0.56
    POSITIVE LOGITS
     afforded
    1.13
     bestowed
    0.90
     possess
    0.88
     garnered
    0.87
     receive
    0.85
     derive
    0.85
     enjoyed
    0.83
     gained
    0.83
     possesses
    0.83
     receives
    0.81
    Act Density 0.225%

    No Known Activations