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

    Neuronpedia

    INDEX
    Explanations

    adjectives intensifying a personal preference for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong personal preferences or fandom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çķ
    -0.77
     plantations
    -0.70
     omin
    -0.68
     incrim
    -0.68
    eworks
    -0.67
    tein
    -0.66
     overshadow
    -0.65
     scrimmage
    -0.64
     allegations
    -0.64
     undercut
    -0.62
    POSITIVE LOGITS
     believer
    1.09
     sucker
    1.04
     OCD
    1.01
     proud
    0.96
     avid
    0.95
     myself
    0.95
     lucky
    0.92
     fortunate
    0.92
     obsessive
    0.90
     geek
    0.88
    Act Density 0.256%

    No Known Activations