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

    Neuronpedia

    INDEX
    Explanations

    words related to social, psychological, and economic concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personality traits influenced by social perceptions and biases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -1.01
    wered
    -0.85
     Armageddon
    -0.83
    çīĪ
    -0.83
     Ammunition
    -0.81
    atron
    -0.79
    Company
    -0.76
     Manufacturer
    -0.75
     Bullets
    -0.74
    eday
    -0.73
    POSITIVE LOGITS
     behavioral
    1.44
     behaviors
    1.39
     cognitive
    1.38
     psychologists
    1.32
     perceptual
    1.31
     behavioural
    1.28
     biases
    1.27
     predictive
    1.26
     neural
    1.25
     unconsciously
    1.25
    Act Density 0.898%

    No Known Activations