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

    Neuronpedia

    INDEX
    Explanations

    instances where some person or entity expresses a specific sentiment or opinion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.71
     flourish
    -0.64
     Recession
    -0.63
     Weasley
    -0.62
    ossom
    -0.60
    acly
    -0.59
     looms
    -0.59
    IZE
    -0.57
     flows
    -0.57
     perish
    -0.57
    POSITIVE LOGITS
     honoured
    0.88
     pleased
    0.76
     unequiv
    0.75
     categor
    0.75
     aware
    0.74
     glad
    0.72
     owed
    0.72
    rael
    0.71
     unaware
    0.71
     honored
    0.71
    Act Density 0.198%

    No Known Activations